Article(id=1149781958227616684, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149781952959574654, articleNumber=null, orderNo=null, doi=10.12404/j.issn.1671-1815.2403379, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1715097600000, receivedDateStr=2024-05-08, revisedDate=1735228800000, revisedDateStr=2024-12-27, acceptedDate=null, acceptedDateStr=null, onlineDate=1752058980756, onlineDateStr=2025-07-09, pubDate=1743091200000, pubDateStr=2025-03-28, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1752058980756, onlineIssueDateStr=2025-07-09, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1752058980756, creator=13701087609, updateTime=1752058980756, updator=13701087609, issue=Issue{id=1149781952959574654, tenantId=1146029695717560320, journalId=1146123166801305609, year='2025', volume='25', issue='9', pageStart='3529', pageEnd='3967', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1752058979501, creator=13701087609, updateTime=1776333392421, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1251596220226027613, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149781952959574654, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1251596220226027614, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149781952959574654, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=3749, endPage=3759, ext={EN=ArticleExt(id=1149781958521217965, articleId=1149781958227616684, tenantId=1146029695717560320, journalId=1146123166801305609, language=EN, title=High-altitude Electromagnetic Pulse Parameter Identification and Experimental Verification, columnId=1156262729162810294, journalTitle=Science Technology and Engineering, columnName=Papers·Automation and Computational Technology, runingTitle=null, highlight=null, articleAbstract=

In dynamic wireless environments, the distortion of transmission waveform is inevitably present, deteriorating the accuracy of identifying high altitude electromagnetic pulse (HEMP) parameters. To address this issue, an extreme learning machine parameter identification network (ELM-PInet)-based parameter identification method was investigated, which leverages the characteristics of HEMP waveform and considers the impact of wireless channels, thereby improving the accuracy of HEMP parameter identification. To demonstrate the nonlinear effects of wireless channels, the transmission model of HEMP waveform was first constructed based on wireless transmission theory. Subsequently, an ELM-PInet was developed to suppress waveform distortion and improve the identification accuracy of HEMP parameters. Finally, the proposed method was validated through field irradiation test on the experimental platform. Simulation results demonstrate that compared to classical HEMP parameter identification methods, the identification accuracy of HEMP parameters is enhanced by the proposed method. Furthermore, the ELM-PInet-based parameter identification method exhibits its robustness against the impacts of different parameters. Additionally, the effectiveness of the proposed method is further validated through field irradiation experiments.

, correspAuthors=Chao-jin QING, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Chao-jin QING, Yin-jie ZHANG, Min-tao ZHANG, Mao-gang WEI, Hui LIN), CN=ArticleExt(id=1149782002951479707, articleId=1149781958227616684, tenantId=1146029695717560320, journalId=1146123166801305609, language=CN, title=高空核爆电磁脉冲的参数识别与实验验证, columnId=1156262729783567290, journalTitle=科学技术与工程, columnName=论文·自动化技术、计算机技术, runingTitle=null, highlight=null, articleAbstract=

在时变的无线场景中传输的高空核爆电磁脉冲(high altitude electromagnetic pulse, HEMP)不可避免地产生波形畸变,导致HEMP参数识别精确度显著地降低。为解决这一难题,考虑无线信道对HEMP波形的影响,利用其波形特征,研究基于极限学习机参数识别网络(extreme learning machine parameter identification network,ELM-PInet)的参数识别方法,以改善HEMP参数识别精确度。首先,从无线传输理论出发,构建HEMP波形传输模型,诠释无线信道对HEMP波形的非线性影响。随后,构建ELM-PInet进行波形畸变抑制,改善HEMP参数识别精度。最后,基于实验平台,对提出方法进行了现场辐照实验验证。仿真结果表明,相比于经典的HEMP参数识别方法,提出方法可改善HEMP参数的识别精度;针对不同的参数影响,ELM-PInet参数识别方法具有鲁棒性。同时,通过现场辐照实验进一步验证了提出方法的有效性。

, correspAuthors=卿朝进, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=bcWHDsD88sEFyeIKg7Qoig==, magXml=XlRdsAxNndIbQto/dyCq7Q==, pdfUrl=null, pdf=OYHsET8XP5xWSn6rBe79HA==, pdfFileSize=6518975, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=4E30Lv/GMLgUljDfYrm98A==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=lQVzOGO18YrPSDNxF/Ma/A==, mapNumber=null, authorCompany=null, fund=null, authors=

卿朝进(1978—),男,汉族,四川安岳人,博士(博士后),教授。研究方向:无线网络与通信。E-mail:

, authorsList=卿朝进, 张银杰, 张岷涛, 魏茂刚, 林辉)}, authors=[Author(id=1251595993909768665, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=qingchj@mail.xhu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1251595993993654748, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, authorId=1251595993909768665, language=EN, stringName=Chao-jin QING, firstName=Chao-jin, middleName=null, lastName=QING, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Electrical and Electronic Information, Xihua University, Chengdu 610039, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1251595994064957918, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, authorId=1251595993909768665, language=CN, stringName=卿朝进, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 西华大学电气与电子信息学院, 成都 610039, bio={"content":"

卿朝进(1978—),男,汉族,四川安岳人,博士(博士后),教授。研究方向:无线网络与通信。E-mail:

"}, bioImg=null, bioContent=

卿朝进(1978—),男,汉族,四川安岳人,博士(博士后),教授。研究方向:无线网络与通信。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1251595993649721801, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, xref=1, ext=[AuthorCompanyExt(id=1251595993662304715, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, companyId=1251595993649721801, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Electrical and Electronic Information, Xihua University, Chengdu 610039, China), AuthorCompanyExt(id=1251595993670693324, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, companyId=1251595993649721801, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 西华大学电气与电子信息学院, 成都 610039)])]), Author(id=1251595994127872480, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1251595994207564259, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, authorId=1251595994127872480, language=EN, stringName=Yin-jie ZHANG, firstName=Yin-jie, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Electrical and Electronic Information, Xihua University, Chengdu 610039, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1251595994266284516, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, authorId=1251595994127872480, language=CN, stringName=张银杰, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 西华大学电气与电子信息学院, 成都 610039, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1251595993649721801, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, xref=1, ext=[AuthorCompanyExt(id=1251595993662304715, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, companyId=1251595993649721801, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Electrical and Electronic Information, Xihua University, Chengdu 610039, China), AuthorCompanyExt(id=1251595993670693324, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, companyId=1251595993649721801, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 西华大学电气与电子信息学院, 成都 610039)])]), Author(id=1251595994333393383, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1251595994400502250, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, authorId=1251595994333393383, language=EN, stringName=Min-tao ZHANG, firstName=Min-tao, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Electrical and Electronic Information, Xihua University, Chengdu 610039, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1251595994455028204, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, authorId=1251595994333393383, language=CN, stringName=张岷涛, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 西华大学电气与电子信息学院, 成都 610039, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1251595993649721801, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, xref=1, ext=[AuthorCompanyExt(id=1251595993662304715, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, companyId=1251595993649721801, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Electrical and Electronic Information, Xihua University, Chengdu 610039, China), AuthorCompanyExt(id=1251595993670693324, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, companyId=1251595993649721801, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 西华大学电气与电子信息学院, 成都 610039)])]), Author(id=1251595994517942767, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1251595994614411762, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, authorId=1251595994517942767, language=EN, stringName=Mao-gang WEI, firstName=Mao-gang, middleName=null, lastName=WEI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 School of Computer and Software Engineering, Xihua University, Chengdu 610039, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1251595994689909236, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, authorId=1251595994517942767, language=CN, stringName=魏茂刚, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 西华大学计算机与软件工程学院, 成都 610039, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1251595993737802190, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, xref=2, ext=[AuthorCompanyExt(id=1251595993746190799, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, companyId=1251595993737802190, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 School of Computer and Software Engineering, Xihua University, Chengdu 610039, China), AuthorCompanyExt(id=1251595993754579408, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, companyId=1251595993737802190, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 西华大学计算机与软件工程学院, 成都 610039)])]), Author(id=1251595994765406711, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1251595994949956090, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, authorId=1251595994765406711, language=EN, stringName=Hui LIN, firstName=Hui, middleName=null, lastName=LIN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3 Chengdu Aerospace Kate Electromechanical Technology Co., Ltd., Chengdu 611730, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1251595995008676348, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, authorId=1251595994765406711, language=CN, stringName=林辉, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3 成都航天凯特机电科技有限公司, 成都 611730, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1251595993821688274, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, xref=3, ext=[AuthorCompanyExt(id=1251595993830076883, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, companyId=1251595993821688274, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 Chengdu Aerospace Kate Electromechanical Technology Co., Ltd., Chengdu 611730, China), AuthorCompanyExt(id=1251595993846854100, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, companyId=1251595993821688274, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 成都航天凯特机电科技有限公司, 成都 611730)])])], keywords=[Keyword(id=1251595995134505470, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=EN, orderNo=1, keyword=high altitude electromagnetic pulse (HEMP)), Keyword(id=1251595995193225728, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=EN, orderNo=2, keyword=waveform distortion), Keyword(id=1251595995260334593, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=EN, orderNo=3, keyword=parameter identification), Keyword(id=1251595995319054851, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=EN, orderNo=4, keyword=extreme learning machine), Keyword(id=1251595995390358021, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=EN, orderNo=5, keyword=wireless transmission), Keyword(id=1251595995465855496, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=EN, orderNo=6, keyword=irradiation experiment), Keyword(id=1251595995541352970, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=CN, orderNo=1, keyword=高空核爆电磁脉冲), Keyword(id=1251595995612656140, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=CN, orderNo=2, keyword=波形畸变), Keyword(id=1251595995683959310, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=CN, orderNo=3, keyword=参数识别), Keyword(id=1251595995788816912, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=CN, orderNo=4, keyword=极限学习机), Keyword(id=1251595995864314386, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=CN, orderNo=5, keyword=无线传输), Keyword(id=1251595995931423252, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=CN, orderNo=6, keyword=辐照试验)], refs=[Reference(id=1251595999215563371, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2022, volume=13, issue=2, pageStart=110, pageEnd=115, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=杜传报, 毛从光, 崔志同, journalName=现代应用物理, refType=null, unstructuredReference=杜传报, 毛从光, 崔志同, . 甚高频无线通信系统高空电磁脉冲易损性分析[J]. 现代应用物理, 2022, 13(2): 110-115, 161., articleTitle=甚高频无线通信系统高空电磁脉冲易损性分析, refAbstract=null), Reference(id=1251595999282672237, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2022, volume=13, issue=2, pageStart=110, pageEnd=115, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=Du Chuanbao, Mao Congguang, Cui Zhitong, journalName=Modern Applied Physics, refType=null, unstructuredReference=Du Chuanbao, Mao Congguang, Cui Zhitong, et al. Vulnerability analysis of high-altitude electromagnetic pulses in very high frequency wireless communication systems[J]. Modern Applied Physics, 2022, 13(2): 110-115, 161., articleTitle=Vulnerability analysis of high-altitude electromagnetic pulses in very high frequency wireless communication systems, refAbstract=null), Reference(id=1251595999345586799, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=文巧莉, journalName=118-136 MHz天线耦合强电磁脉冲特性及防护方法研究, refType=null, unstructuredReference=文巧莉. 118-136 MHz天线耦合强电磁脉冲特性及防护方法研究[D]. 南京: 南京信息工程大学, 2022., articleTitle=null, refAbstract=null), Reference(id=1251595999421084272, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=Wen Qiaoli, journalName=Research on the characteristics and protection methods of strong electromagnetic pulse coupling in 118-136 MHz antennas, refType=null, unstructuredReference=Wen Qiaoli. Research on the characteristics and protection methods of strong electromagnetic pulse coupling in 118-136 MHz antennas[D]. Nanjing: Nanjing University of Information Technology, 2022., articleTitle=null, refAbstract=null), Reference(id=1251595999500776049, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=Giri D V, Hoad R, Sabath F, journalName=High-power electromagnetic effects on electronic systems, refType=null, unstructuredReference=Giri D V, Hoad R, Sabath F. High-power electromagnetic effects on electronic systems[M]. London: Artech, 2020., articleTitle=null, refAbstract=null), Reference(id=1251595999567884914, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2023, volume=14, issue=3, pageStart=16, pageEnd=31, url=null, language=null, rfNumber=[4], rfOrder=5, authorNames=秦锋, 陈伟, 毛从光, journalName=现代应用物理, refType=null, unstructuredReference=秦锋, 陈伟, 毛从光, . 电力系统高空电磁脉冲效应研究综述[J]. 现代应用物理, 2023, 14(3): 16-31., articleTitle=电力系统高空电磁脉冲效应研究综述, refAbstract=null), Reference(id=1251595999634993779, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2023, volume=14, issue=3, pageStart=16, pageEnd=31, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=Qin Feng, Chen Wei, Mao Congguang, journalName=Modern Applied Physics, refType=null, unstructuredReference=Qin Feng, Chen Wei, Mao Congguang, et al. A review of research on high-altitude electromagnetic pulse effects in power systems[J]. Modern Applied Physics, 2023, 14(3): 16-31., articleTitle=A review of research on high-altitude electromagnetic pulse effects in power systems, refAbstract=null), Reference(id=1251595999702102644, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=7, authorNames=郭稳, journalName=强电磁脉冲下防护器件的冲击特性及组合使用方法的研究, refType=null, unstructuredReference=郭稳. 强电磁脉冲下防护器件的冲击特性及组合使用方法的研究[D]. 南京: 南京信息工程大学, 2023., articleTitle=null, refAbstract=null), Reference(id=1251595999765017205, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=Guo Wen, journalName=Research on the impact characteristics and combination usage of protective devices under strong electromagnetic pulse, refType=null, unstructuredReference=Guo Wen. Research on the impact characteristics and combination usage of protective devices under strong electromagnetic pulse[D] Nanjing: Nanjing University of Information Technology, 2023., articleTitle=null, refAbstract=null), Reference(id=1251595999827931766, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2003, volume=null, issue=8, pageStart=781, pageEnd=787, url=null, language=null, rfNumber=[6], rfOrder=9, authorNames=谢彦召, 王赞基, 王群书, journalName=强激光与粒子束, refType=null, unstructuredReference=谢彦召, 王赞基, 王群书, . 高空核爆电磁脉冲波形标准及特征分析[J]. 强激光与粒子束, 2003(8): 781-787., articleTitle=高空核爆电磁脉冲波形标准及特征分析, refAbstract=null), Reference(id=1251595999895040631, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2003, volume=null, issue=8, pageStart=781, pageEnd=787, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=Xie Yanzhao, Wang Zanji, Wang Qunshu, journalName=Intense Laser and Particle Beam, refType=null, unstructuredReference=Xie Yanzhao, Wang Zanji, Wang Qunshu, et al. Standard and characteristic analysis of electromagnetic pulse waveform for high-altitude nuclear explosions[J]. Intense Laser and Particle Beam, 2003(8): 781-787., articleTitle=Standard and characteristic analysis of electromagnetic pulse waveform for high-altitude nuclear explosions, refAbstract=null), Reference(id=1251595999953760888, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2009, volume=31, issue=2, pageStart=103, pageEnd=107, url=null, language=null, rfNumber=[7], rfOrder=11, authorNames=陶灵姣, 柴焱杰, 李智, journalName=指挥控制与仿真, refType=null, unstructuredReference=陶灵姣, 柴焱杰, 李智, . 高功率电磁环境下导弹发射阵地近地面电磁脉冲波形仿真[J]. 指挥控制与仿真, 2009, 31(2): 103-107., articleTitle=高功率电磁环境下导弹发射阵地近地面电磁脉冲波形仿真, refAbstract=null), Reference(id=1251596000025064057, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2009, volume=31, issue=2, pageStart=103, pageEnd=107, url=null, language=null, rfNumber=[7], rfOrder=12, authorNames=Tao Lingjiao, Chai Yanjie, Li Zhi, journalName=Command, Control and Simulation, refType=null, unstructuredReference=Tao Lingjiao, Chai Yanjie, Li Zhi, et al. Simulation of near ground electromagnetic pulse waveform of missile launch site in high power electromagnetic environment[J]. Command, Control and Simulation, 2009, 31(2): 103-107., articleTitle=Simulation of near ground electromagnetic pulse waveform of missile launch site in high power electromagnetic environment, refAbstract=null), Reference(id=1251596000087978618, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2022, volume=13, issue=2, pageStart=98, pageEnd=103, url=null, language=null, rfNumber=[8], rfOrder=13, authorNames=马良, 程引会, 郭景海, journalName=现代应用物理, refType=null, unstructuredReference=马良, 程引会, 郭景海. 高空电磁脉冲标准波形参数的时域确定方法[J]. 现代应用物理, 2022, 13(2): 98-103, 122., articleTitle=高空电磁脉冲标准波形参数的时域确定方法, refAbstract=null), Reference(id=1251596000159281787, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2022, volume=13, issue=2, pageStart=98, pageEnd=103, url=null, language=null, rfNumber=[8], rfOrder=14, authorNames=Ma Liang, Cheng Yinhui, Guo Jinghai, journalName=Modern Applied Physics, refType=null, unstructuredReference=Ma Liang, Cheng Yinhui, Guo Jinghai. Time domain determination method for standard waveform parameters of high-altitude electromagnetic pulses[J]. Modern Applied Physics, 2022, 13(2): 98-103, 122., articleTitle=Time domain determination method for standard waveform parameters of high-altitude electromagnetic pulses, refAbstract=null), Reference(id=1251596000230584956, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2008, volume=50, issue=1, pageStart=97, pageEnd=100, url=null, language=null, rfNumber=[9], rfOrder=15, authorNames=Mao C, Zhou H, journalName=IEEE Transactions on Electromagnetic Compatibility, refType=null, unstructuredReference=Mao C, Zhou H. Novel parameter estimation of double exponential pulse (EMP, UWB) by statistical means[J]. IEEE Transactions on Electromagnetic Compatibility, 2008, 50(1): 97-100., articleTitle=Novel parameter estimation of double exponential pulse (EMP, UWB) by statistical means, refAbstract=null), Reference(id=1251596000297693821, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[10], rfOrder=16, authorNames=王乾丞, journalName=核脉冲的参数识别及自适应成形方法, refType=null, unstructuredReference=王乾丞. 核脉冲的参数识别及自适应成形方法[D]. 成都: 成都理工大学, 2021., articleTitle=null, refAbstract=null), Reference(id=1251596000389968510, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[10], rfOrder=17, authorNames=Wang Qiancheng, journalName=Parameter identification and adaptive shaping method of nuclear pulses, refType=null, unstructuredReference=Wang Qiancheng. Parameter identification and adaptive shaping method of nuclear pulses[D]. Chengdu: Chengdu University of Technology, 2021., articleTitle=null, refAbstract=null), Reference(id=1251596000469660287, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2023, volume=65, issue=6, pageStart=1981, pageEnd=1989, url=null, language=null, rfNumber=[11], rfOrder=18, authorNames=Yang J, Cui Z, Cao F, journalName=IEEE Transactions on Electromagnetic Compatibility, refType=null, unstructuredReference=Yang J, Cui Z, Cao F, et al. Estimation method of bandwidth requirements for double exponential pulse measurement[J]. IEEE Transactions on Electromagnetic Compatibility, 2023, 65(6): 1981-1989., articleTitle=Estimation method of bandwidth requirements for double exponential pulse measurement, refAbstract=null), Reference(id=1251596000528380544, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=283, pageEnd=285, url=null, language=null, rfNumber=[12], rfOrder=19, authorNames=Chen P, Mao C, Wu G, journalName=2016 Asia-Pacific International Symposium on Electromagnetic Compatibility, refType=null, unstructuredReference=Chen P, Mao C, Wu G. Highest frequency estimation of HEMP standard waveforms[C]// 2016 Asia-Pacific International Symposium on Electromagnetic Compatibility. Shenzhen: IEEE, 2016: 283-285., articleTitle=Highest frequency estimation of HEMP standard waveforms, refAbstract=null), Reference(id=1251596000650015361, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2023, volume=50, issue=S1, pageStart=853, pageEnd=857, url=null, language=null, rfNumber=[13], rfOrder=20, authorNames=王锦锦, 程引会, 聂鑫, journalName=计算机科学, refType=null, unstructuredReference=王锦锦, 程引会, 聂鑫, . 基于机器学习的高空电磁脉冲环境快速计算方法[J]. 计算机科学, 2023, 50(S1): 853-857., articleTitle=基于机器学习的高空电磁脉冲环境快速计算方法, refAbstract=null), Reference(id=1251596000721318530, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2023, volume=50, issue=S1, pageStart=853, pageEnd=857, url=null, language=null, rfNumber=[13], rfOrder=21, authorNames=Wang Jinjin, Cheng Yinhui, Nie Xin, journalName=Computer Science, refType=null, unstructuredReference=Wang Jinjin, Cheng Yinhui, Nie Xin, et al. A fast calculation method for high altitude electromagnetic pulse environment based on machine learning[J]. Computer Science, 2023, 50(S1): 853-857., articleTitle=A fast calculation method for high altitude electromagnetic pulse environment based on machine learning, refAbstract=null), Reference(id=1251596000784233091, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2022, volume=21, issue=6, pageStart=3779, pageEnd=3791, url=null, language=null, rfNumber=[14], rfOrder=22, authorNames=Qing C, Dong L, Wang L, journalName=IEEE Transactions on Wireless Communications, refType=null, unstructuredReference=Qing C, Dong L, Wang L, et al. Joint model and data-driven receiver design for data-dependent superimposed training scheme with imperfect hardware[J]. IEEE Transactions on Wireless Communications, 2022, 21(6): 3779-3791., articleTitle=Joint model and data-driven receiver design for data-dependent superimposed training scheme with imperfect hardware, refAbstract=null), Reference(id=1251596000859730564, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2013, volume=55, issue=3, pageStart=532, pageEnd=538, url=null, language=null, rfNumber=[15], rfOrder=23, authorNames=Hoad R, Radasky W A, journalName=IEEE Transactions on Electromagnetic Compatibility, refType=null, unstructuredReference=Hoad R, Radasky W A. Progress in high-altitude electromagnetic pulse (HEMP) standardization[J]. IEEE Transactions on Electromagnetic Compatibility, 2013, 55(3): 532-538., articleTitle=Progress in high-altitude electromagnetic pulse (HEMP) standardization, refAbstract=null), Reference(id=1251596000931033733, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=537, pageEnd=539, url=null, language=null, rfNumber=[16], rfOrder=24, authorNames=Shi Y, Nie X, Zhu Z, journalName=2016 Asia-Pacific International Symposium on Electromagnetic Compatibility, refType=null, unstructuredReference=Shi Y, Nie X, Zhu Z, et al. A simplified method for parameter estimating of double exponential pulse[C]// 2016 Asia-Pacific International Symposium on Electromagnetic Compatibility. Shenzhen: IEEE, 2016: 537-539., articleTitle=A simplified method for parameter estimating of double exponential pulse, refAbstract=null), Reference(id=1251596001010725510, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[17], rfOrder=25, authorNames=International Electrotechnical Commission, journalName=Lundon, refType=null, unstructuredReference=International Electrotechnical Commission. Description of HEMP environment-radiation disturbance basic EMC publication:IEC 61000-2-9-1996[S]. Lundon: IEC,1996., articleTitle=null, refAbstract=null), Reference(id=1251596001082028679, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=1996, volume=38, issue=3, pageStart=400, pageEnd=413, url=null, language=null, rfNumber=[18], rfOrder=26, authorNames=Ianoz M, Nicoara B I C, Radasky W A, journalName=IEEE Transactions on EMC, refType=null, unstructuredReference=Ianoz M, Nicoara B I C, Radasky W A. Modeling of an EMP conducted environment[J]. IEEE Transactions on EMC, 1996, 38(3): 400-413., articleTitle=Modeling of an EMP conducted environment, refAbstract=null), Reference(id=1251596001149137544, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=1976, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[19], rfOrder=27, authorNames=Ricketts L W, Bridges J E, Miletta J, journalName=EMP radiation and protective techniques, refType=null, unstructuredReference=Ricketts L W, Bridges J E, Miletta J. EMP radiation and protective techniques[M]. New York: Wiley, 1976., articleTitle=null, refAbstract=null), Reference(id=1251596001203663497, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2020, volume=99, issue=null, pageStart=31330, pageEnd=31340, url=null, language=null, rfNumber=[20], rfOrder=28, authorNames=Wang J, Cui Y, Jiang H, journalName=IEEE Access, refType=null, unstructuredReference=Wang J, Cui Y, Jiang H, et al. Estimation of rice factor ratio for doubly selective fading channels[J]. IEEE Access, 2020, 99: 31330-31340., articleTitle=Estimation of rice factor ratio for doubly selective fading channels, refAbstract=null), Reference(id=1251596001270772362, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=1, pageEnd=5, url=null, language=null, rfNumber=[21], rfOrder=29, authorNames=Rahayu S, Iskandar, journalName=2023 9th International Conference on Wireless and Telematics, refType=null, unstructuredReference=Rahayu S, Iskandar. Study on MMSE-DFT based channel estimation for HAPS OFDM system[C]// 2023 9th International Conference on Wireless and Telematics. Solo: IEEE, 2023: 1-5., articleTitle=Study on MMSE-DFT based channel estimation for HAPS OFDM system, refAbstract=null), Reference(id=1251596001325298315, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2019, volume=99, issue=null, pageStart=90525, pageEnd=90537, url=null, language=null, rfNumber=[22], rfOrder=30, authorNames=Shah S I H, Khan S A, Ghauri S A, journalName=IEEE Access, refType=null, unstructuredReference=Shah S I H, Khan S A, Ghauri S A, et al. A novel hybrid cuckoo search- extreme learning machine approach for modulation classification[J]. IEEE Access, 2019, 99: 90525-90537., articleTitle=A novel hybrid cuckoo search- extreme learning machine approach for modulation classification, refAbstract=null), Reference(id=1251596001392407180, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2024, volume=10, issue=1, pageStart=107, pageEnd=121, url=null, language=null, rfNumber=[23], rfOrder=31, authorNames=Guo Y P, Zhong D, Sun H X, journalName=IEEE Transactions on Cognitive Communications and Networking, refType=null, unstructuredReference=Guo Y P, Zhong D, Sun H X, et al. SemiAMR: semi-supervised automatic modulation recognition with corrected pseudo-label and consistency regularization[J]. IEEE Transactions on Cognitive Communications and Networking, 2024, 10(1): 107-121., articleTitle=SemiAMR: semi-supervised automatic modulation recognition with corrected pseudo-label and consistency regularization, refAbstract=null), Reference(id=1251596001463710349, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=11, pageStart=110010, pageEnd=110022, url=null, language=null, rfNumber=[24], rfOrder=32, authorNames=Shi Y, Wang C, Ge G, journalName=IEEE Access, refType=null, unstructuredReference=Shi Y, Wang C, Ge G, et al. ELM-based discriminant auto-encoder and multi-kernel fusion for radar specific emitter identification[J]. IEEE Access, 2023(11): 110010-110022., articleTitle=ELM-based discriminant auto-encoder and multi-kernel fusion for radar specific emitter identification, refAbstract=null), Reference(id=1251596001526624910, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2020, volume=37, issue=6, pageStart=1683, pageEnd=1687, url=null, language=null, rfNumber=[25], rfOrder=33, authorNames=盛晓晨, 史旭东, 熊伟丽, journalName=计算机应用研究, refType=null, unstructuredReference=盛晓晨, 史旭东, 熊伟丽. 改进粒子群优化的极限学习机软测量建模方法[J]. 计算机应用研究, 2020, 37(6): 1683-1687., articleTitle=改进粒子群优化的极限学习机软测量建模方法, refAbstract=null), Reference(id=1251596001589539471, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2020, volume=37, issue=6, pageStart=1683, pageEnd=1687, url=null, language=null, rfNumber=[25], rfOrder=34, authorNames=Sheng Xiaochen, Shi Xudong, Xiong Weili, journalName=Computer Application Research, refType=null, unstructuredReference=Sheng Xiaochen, Shi Xudong, Xiong Weili. Soft sensing modeling method for extreme learning machine with improved particle swarm optimization[J]. Computer Application Research, 2020, 37(6): 1683-1687., articleTitle=Soft sensing modeling method for extreme learning machine with improved particle swarm optimization, refAbstract=null), Reference(id=1251596001656648336, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2020, volume=9, issue=6, pageStart=915, pageEnd=919, url=null, language=null, rfNumber=[26], rfOrder=35, authorNames=Qing C, Yu W, Cai B, journalName=IEEE Wireless Communication Letters, refType=null, unstructuredReference=Qing C, Yu W, Cai B, et al. ELM-based frame synchronization in burst-mode communication systems with nonlinear distortion[J]. IEEE Wireless Communication Letters, 2020, 9(6): 915-919., articleTitle=ELM-based frame synchronization in burst-mode communication systems with nonlinear distortion, refAbstract=null), Reference(id=1251596001706979985, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=1836, pageEnd=1841, url=null, language=null, rfNumber=[27], rfOrder=36, authorNames=Ding B, Qian H, Zhou J, journalName=2018 Chinese Control And Decision Conference, refType=null, unstructuredReference=Ding B, Qian H, Zhou J. Activation functions and their characteristics in deep neural networks[C]// 2018 Chinese Control And Decision Conference. Shenyang: IEEE, 2018: 1836-1841., articleTitle=Activation functions and their characteristics in deep neural networks, refAbstract=null), Reference(id=1251596001765700242, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2021, volume=40, issue=4, pageStart=1, pageEnd=10, url=null, language=null, rfNumber=[28], rfOrder=37, authorNames=张焕, 张庆, 于纪言, journalName=西华大学学报(自然科学版), refType=null, unstructuredReference=张焕, 张庆, 于纪言. 激活函数的发展综述及其性质分析[J]. 西华大学学报(自然科学版), 2021, 40(4): 1-10., articleTitle=激活函数的发展综述及其性质分析, refAbstract=null), Reference(id=1251596001828614803, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2021, volume=40, issue=4, pageStart=1, pageEnd=10, url=null, language=null, rfNumber=[28], rfOrder=38, authorNames=Zhang Huan, Zhang Qing, Yu Jiyan, journalName=Journal of Xihua University (Natural Science Edition), refType=null, unstructuredReference=Zhang Huan, Zhang Qing, Yu Jiyan. Overview of the development of activation function and its nature analysis[J]. Journal of Xihua University (Natural Science Edition), 2021, 40(4): 1-10., articleTitle=Overview of the development of activation function and its nature analysis, refAbstract=null), Reference(id=1251596001887335060, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=2, pageStart=528, pageEnd=535, url=null, language=null, rfNumber=[29], rfOrder=39, authorNames=尚艳芳, 李丽敏, 温宗周, journalName=科学技术与工程, refType=null, unstructuredReference=尚艳芳, 李丽敏, 温宗周, . 基于优化核极限学习机的泥石流危险性评估[J]. 科学技术与工程, 2023, 23(2): 528-535., articleTitle=基于优化核极限学习机的泥石流危险性评估, refAbstract=null), Reference(id=1251596001954443925, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=2, pageStart=528, pageEnd=535, url=null, language=null, rfNumber=[29], rfOrder=40, authorNames=Shang Yanfang, Li Limin, Wen Zongzhou, journalName=Science and Technology and Engineering, refType=null, unstructuredReference=Shang Yanfang, Li Limin, Wen Zongzhou, et al. Risk assessment of debris flow based on optimized kernel extreme learning machine[J]. Science and Technology and Engineering, 2023, 23(2): 528-535., articleTitle=Risk assessment of debris flow based on optimized kernel extreme learning machine, refAbstract=null), Reference(id=1251596002008969878, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=5, pageStart=1929, pageEnd=1935, url=null, language=null, rfNumber=[30], rfOrder=41, authorNames=安琪, 王占彬, 安国庆, journalName=科学技术与工程, refType=null, unstructuredReference=安琪, 王占彬, 安国庆, . 基于随机森林-遗传算法-极限学习机的非侵入式负荷识别方法[J]. 科学技术与工程, 2022, 22(5): 1929-1935., articleTitle=基于随机森林-遗传算法-极限学习机的非侵入式负荷识别方法, refAbstract=null), Reference(id=1251596002076078743, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=5, pageStart=1929, pageEnd=1935, url=null, language=null, rfNumber=[30], rfOrder=42, authorNames=An Qi, Wang Zhanbin, An Guoqing, journalName=Science and Technology and Engineering, refType=null, unstructuredReference=An Qi, Wang Zhanbin, An Guoqing, et al. A non-invasive load identification method based on random forest genetic algorithm extreme learning machine[J]. Science and Technology and Engineering, 2022, 22(5): 1929-1935., articleTitle=A non-invasive load identification method based on random forest genetic algorithm extreme learning machine, refAbstract=null), Reference(id=1251596002147381912, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2006, volume=70, issue=1/3, pageStart=489, pageEnd=501, url=null, language=null, rfNumber=[31], rfOrder=43, authorNames=Huang G B, Zhu Q Y, Siew C K, journalName=Neurocomputing, refType=null, unstructuredReference=Huang G B, Zhu Q Y, Siew C K. Extreme learning machine: theory and applications[J]. Neurocomputing, 2006, 70(1/3): 489-501., articleTitle=Extreme learning machine: theory and applications, refAbstract=null), Reference(id=1251596002206102169, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, doi=null, pmid=null, pmcid=null, year=2020, volume=69, issue=6, pageStart=6803, pageEnd=6807, url=null, language=null, rfNumber=[32], rfOrder=44, authorNames=Wu L, Zhang Z, Dang J, journalName=IEEE Transactions on Vehicular Technology, refType=null, unstructuredReference=Wu L, Zhang Z, Dang J, et al. Joint user identification and channel estimation over rician fading channels[J]. IEEE Transactions on Vehicular Technology, 2020, 69(6): 6803-6807., articleTitle=Joint user identification and channel estimation over rician fading channels, refAbstract=null)], funds=[Fund(id=1251595998800327264, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, awardId=62301447, language=CN, fundingSource=国家自然科学基金(62301447), fundOrder=null, country=null), Fund(id=1251595998859047522, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, awardId=2023YFG0316, language=CN, fundingSource=四川省科技计划(2023YFG0316), fundOrder=null, country=null), Fund(id=1251595998947127908, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, awardId=23GSC00004, language=CN, fundingSource=四川省科技计划“揭榜挂帅”项目(23GSC00004), fundOrder=null, country=null), Fund(id=1251595999014236774, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, awardId=Z1320929, language=CN, fundingSource=西华大学校重点项目(Z1320929), fundOrder=null, country=null), Fund(id=1251595999081345640, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, awardId=2021ITA10016, language=CN, fundingSource=中国高校产学研创新基金(2021ITA10016), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1251595993649721801, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, xref=1, ext=[AuthorCompanyExt(id=1251595993662304715, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, companyId=1251595993649721801, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Electrical and Electronic Information, Xihua University, Chengdu 610039, China), AuthorCompanyExt(id=1251595993670693324, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, companyId=1251595993649721801, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 西华大学电气与电子信息学院, 成都 610039)]), AuthorCompany(id=1251595993737802190, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, xref=2, ext=[AuthorCompanyExt(id=1251595993746190799, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, companyId=1251595993737802190, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 School of Computer and Software Engineering, Xihua University, Chengdu 610039, China), AuthorCompanyExt(id=1251595993754579408, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, companyId=1251595993737802190, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 西华大学计算机与软件工程学院, 成都 610039)]), AuthorCompany(id=1251595993821688274, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, xref=3, ext=[AuthorCompanyExt(id=1251595993830076883, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, companyId=1251595993821688274, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 Chengdu Aerospace Kate Electromechanical Technology Co., Ltd., Chengdu 611730, China), AuthorCompanyExt(id=1251595993846854100, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, companyId=1251595993821688274, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 成都航天凯特机电科技有限公司, 成都 611730)])], figs=[ArticleFig(id=1251595996111778328, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=EN, label=Fig.1, caption=Time-domain waveforms of HEMP for several E1 phases, figureFileSmall=aDcFbPo6ocE74XRU6CucsA==, figureFileBig=xfmWFehExnSifHVem0lT1Q==, tableContent=null), ArticleFig(id=1251595996183081498, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=CN, label=图1, caption=几种E1期的HEMP时域波形, figureFileSmall=aDcFbPo6ocE74XRU6CucsA==, figureFileBig=xfmWFehExnSifHVem0lT1Q==, tableContent=null), ArticleFig(id=1251595996292133404, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=EN, label=Fig.2, caption=Near-earth radiation exposure model of HEMP waveform, figureFileSmall=/dI9WAACvE0rSuJTQR0Hrg==, figureFileBig=KKTsu6jiWWLb8IaVMDzN/g==, tableContent=null), ArticleFig(id=1251595996363436574, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=CN, label=图2, caption=近地辐照模型下的HEMP波形, figureFileSmall=/dI9WAACvE0rSuJTQR0Hrg==, figureFileBig=KKTsu6jiWWLb8IaVMDzN/g==, tableContent=null), ArticleFig(id=1251595996413768224, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=EN, label=Fig.3, caption=The relative error of waveform parameters varies with β/α, figureFileSmall=DR1iLnnocGGXT0DN6oXoJA==, figureFileBig=XVPdESg1n7kOuTNTx3w8aw==, tableContent=null), ArticleFig(id=1251595996472488482, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=CN, label=图3, caption=波形参数的相对误差随β/α的变化曲线, figureFileSmall=DR1iLnnocGGXT0DN6oXoJA==, figureFileBig=XVPdESg1n7kOuTNTx3w8aw==, tableContent=null), ArticleFig(id=1251595996539597348, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=EN, label=Fig.4, caption=The variation curve of ${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$ with β/α under different Rice factors, figureFileSmall=NyuLvuA6n33cP+p4+IIBlQ==, figureFileBig=vOMMb+5sWbFs+jGM4hBsag==, tableContent=null), ArticleFig(id=1251595996598317606, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=CN, label=图4, caption=不同莱斯因子下${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$β/α的变化曲线, figureFileSmall=NyuLvuA6n33cP+p4+IIBlQ==, figureFileBig=vOMMb+5sWbFs+jGM4hBsag==, tableContent=null), ArticleFig(id=1251595996678009384, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=EN, label=Fig.5, caption=The variation curve of ${e}_{{T}_{\mathrm{r}}}$ with β/α under different Rice factors, figureFileSmall=S3cO6FkC12tiJmTuXMf5ug==, figureFileBig=b1SlwcmMfCQTXGP4o/XHAQ==, tableContent=null), ArticleFig(id=1251595996787061290, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=CN, label=图5, caption=不同莱斯因子下${e}_{{T}_{\mathrm{r}}}$β/α的变化曲线, figureFileSmall=S3cO6FkC12tiJmTuXMf5ug==, figureFileBig=b1SlwcmMfCQTXGP4o/XHAQ==, tableContent=null), ArticleFig(id=1251595996858364460, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=EN, label=Fig.6, caption=The variation curve of ${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$ with β/α under different multipath numbers, figureFileSmall=uo32D+fi4sP3n1NuqyPlyQ==, figureFileBig=q9LoA5B1mL9AC5L0hD293g==, tableContent=null), ArticleFig(id=1251595996942250542, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=CN, label=图6, caption=不同多径条数下${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$β/α的变化曲线, figureFileSmall=uo32D+fi4sP3n1NuqyPlyQ==, figureFileBig=q9LoA5B1mL9AC5L0hD293g==, tableContent=null), ArticleFig(id=1251595997000970800, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=EN, label=Fig.7, caption=The variation curve of ${e}_{{T}_{\mathrm{r}}}$ with β/α under different multipath numbers, figureFileSmall=MP+YFP5xTg0J0XLna9fPgg==, figureFileBig=awM8MByo74TYwoA2IEjpDA==, tableContent=null), ArticleFig(id=1251595997072273970, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=CN, label=图7, caption=不同多径条数下${e}_{{T}_{\mathrm{r}}}$β/α的变化曲线, figureFileSmall=MP+YFP5xTg0J0XLna9fPgg==, figureFileBig=awM8MByo74TYwoA2IEjpDA==, tableContent=null), ArticleFig(id=1251595997139382836, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=EN, label=Fig.8, caption=Verification of generalization of ${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$ under different Rice factors, figureFileSmall=ir9lVcrlOcO08q2JdZSXqw==, figureFileBig=K9EG5CvKihhxLH+/wSuKhw==, tableContent=null), ArticleFig(id=1251595997198103094, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=CN, label=图8, caption=不同莱斯因子下${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$的泛化性验证, figureFileSmall=ir9lVcrlOcO08q2JdZSXqw==, figureFileBig=K9EG5CvKihhxLH+/wSuKhw==, tableContent=null), ArticleFig(id=1251595997281989175, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=EN, label=Fig.9, caption=Verification of generalization of ${e}_{{T}_{\mathrm{r}}}$ under different Rice factors, figureFileSmall=U8JCGoUqw+c68eX0Dv55+w==, figureFileBig=zqx+u7KRhyNkyvJwZLZkIQ==, tableContent=null), ArticleFig(id=1251595997349098041, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=CN, label=图9, caption=不同莱斯因子下${e}_{{T}_{\mathrm{r}}}$的泛化性验证, figureFileSmall=U8JCGoUqw+c68eX0Dv55+w==, figureFileBig=zqx+u7KRhyNkyvJwZLZkIQ==, tableContent=null), ArticleFig(id=1251595997437178427, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=EN, label=Fig.10, caption=Verification of generalization of ${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$ under different multipath numbers, figureFileSmall=16zMIEI0uFnCD3BmbIlDRQ==, figureFileBig=yVoYUNk0oYOZr0IRSTVB5w==, tableContent=null), ArticleFig(id=1251595997533647421, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=CN, label=图10, caption=不同多径条数下${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$的泛化性验证, figureFileSmall=16zMIEI0uFnCD3BmbIlDRQ==, figureFileBig=yVoYUNk0oYOZr0IRSTVB5w==, tableContent=null), ArticleFig(id=1251595997592367679, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=EN, label=Fig.11, caption=Verification of generalization of ${e}_{{T}_{\mathrm{r}}}$ under different multipath numbers, figureFileSmall=CbPUtSiDgsdoLb1B1KX/Lg==, figureFileBig=8jadTLU9O/z0SIAUO2V5/g==, tableContent=null), ArticleFig(id=1251595997655282241, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=CN, label=图11, caption=不同多径条数下${e}_{{T}_{\mathrm{r}}}$的泛化性验证, figureFileSmall=CbPUtSiDgsdoLb1B1KX/Lg==, figureFileBig=8jadTLU9O/z0SIAUO2V5/g==, tableContent=null), ArticleFig(id=1251595997722391107, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=EN, label=Fig.12, caption=HEMP irradiation test layout, figureFileSmall=1weQwyJEAy4r2cYX5Q0ptA==, figureFileBig=Pjv2yjReVc0jQX01GbxhGQ==, tableContent=null), ArticleFig(id=1251595997781111365, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=CN, label=图12, caption=HEMP辐照试验布局, figureFileSmall=1weQwyJEAy4r2cYX5Q0ptA==, figureFileBig=Pjv2yjReVc0jQX01GbxhGQ==, tableContent=null), ArticleFig(id=1251595997848220231, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=EN, label=Fig.13, caption=On site measurement of HEMP electric field waveform, figureFileSmall=GgtzOXN2jgjXJa3suGeB5g==, figureFileBig=VSjaY0nXFV8RAIJaPiY5dA==, tableContent=null), ArticleFig(id=1251595997957272137, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=CN, label=图13, caption=现场实测HEMP电场波形, figureFileSmall=GgtzOXN2jgjXJa3suGeB5g==, figureFileBig=VSjaY0nXFV8RAIJaPiY5dA==, tableContent=null), ArticleFig(id=1251595998032769611, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=EN, label=Table 1, caption=

Parameters of HEMP waveforms for several E1 phases

, figureFileSmall=null, figureFileBig=null, tableContent=
参数 MIL-STD-461E
标准[17]
Bell实验室
标准[18]
1976年出版物
标准[19]
k0 1.30 1.05 1.04
α/s-1 4×107 4×106 1.5×106
β/s-1 6×108 4.76×108 2.6×108
tr/ns 2.5 4.1 7.8
tFWHM/ns 23 184 483
E0/(kV·m-1) 50 50 50
), ArticleFig(id=1251595998104072781, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=CN, label=表1, caption=

几种E1期的HEMP波形参数

, figureFileSmall=null, figureFileBig=null, tableContent=
参数 MIL-STD-461E
标准[17]
Bell实验室
标准[18]
1976年出版物
标准[19]
k0 1.30 1.05 1.04
α/s-1 4×107 4×106 1.5×106
β/s-1 6×108 4.76×108 2.6×108
tr/ns 2.5 4.1 7.8
tFWHM/ns 23 184 483
E0/(kV·m-1) 50 50 50
), ArticleFig(id=1251595998166987343, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=EN, label=Table 2, caption=

ELM-PInet network architecture

, figureFileSmall=null, figureFileBig=null, tableContent=
参数 输入层 隐藏层 输出层
神经元个数 L 4L Ns
激活函数 Linear Sigmoid Linear
), ArticleFig(id=1251595998250873425, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=CN, label=表2, caption=

ELM-PInet网络架构

, figureFileSmall=null, figureFileBig=null, tableContent=
参数 输入层 隐藏层 输出层
神经元个数 L 4L Ns
激活函数 Linear Sigmoid Linear
), ArticleFig(id=1251595998317982291, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=EN, label=Table 3, caption=

Offline training process of ELM-PInet

, figureFileSmall=null, figureFileBig=null, tableContent=
输入:训练样本和训练标签构成的训练样本集合$\{{y}_{i},{T}_{i}{\}}_{i=1}^{{N}_{\mathrm{t}}}$
输出:ELM-PInet网络参数{W,b,β}。
(1)根据CN(0,1),随机产生输入权重矩阵W、隐藏层偏置向量b
(2)FOR i = 1,2,…,Nt
根据样本{yi,Ti}、Wb,利用式(8)计算得到隐藏层输出矢量Hi
END FOR
(3)收集Nt组隐藏层输出矢量Hi,根据式(9)形成隐藏层输出矩阵H
(4)根据式(10)形成训练标签矩阵T
(5)基于隐藏层输出矩阵H和训练标签矩阵T,根据式(11)计算输出加重矩阵β
), ArticleFig(id=1251595998397674069, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=CN, label=表3, caption=

ELM-PInet离线训练过程

, figureFileSmall=null, figureFileBig=null, tableContent=
输入:训练样本和训练标签构成的训练样本集合$\{{y}_{i},{T}_{i}{\}}_{i=1}^{{N}_{\mathrm{t}}}$
输出:ELM-PInet网络参数{W,b,β}。
(1)根据CN(0,1),随机产生输入权重矩阵W、隐藏层偏置向量b
(2)FOR i = 1,2,…,Nt
根据样本{yi,Ti}、Wb,利用式(8)计算得到隐藏层输出矢量Hi
END FOR
(3)收集Nt组隐藏层输出矢量Hi,根据式(9)形成隐藏层输出矩阵H
(4)根据式(10)形成训练标签矩阵T
(5)基于隐藏层输出矩阵H和训练标签矩阵T,根据式(11)计算输出加重矩阵β
), ArticleFig(id=1251595998489948759, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=EN, label=Table 4, caption=

HEMP parameter identification based on ELM-PInet

, figureFileSmall=null, figureFileBig=null, tableContent=
输入:接收信号矢量y,网络参数{W,b,β}。
输出:HEMP的形状参数${\stackrel{\wedge }{t}}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}$${\stackrel{\wedge }{t}}_{\mathrm{r}}$
(1)根据接收信号样本y,利用式(12)计算ELM-PInet的输出O
(2)根据识别概率最大化,基于ELM-PInet的输出O,根据式(14)估计接收信号矢量y的种类$\stackrel{\wedge }{n}$est,获得估计参数{${\alpha }_{\stackrel{\wedge }{n}{\mathrm{ }}_{\mathrm{e}\mathrm{s}\mathrm{t}}}$,${\beta }_{\stackrel{\wedge }{n}{\mathrm{ }}_{\mathrm{e}\mathrm{s}\mathrm{t}}}$}。
(3)根据式(15),利用估计参数{${\alpha }_{\stackrel{\wedge }{n}{\mathrm{ }}_{\mathrm{e}\mathrm{s}\mathrm{t}}}$,${\beta }_{\stackrel{\wedge }{n}{\mathrm{ }}_{\mathrm{e}\mathrm{s}\mathrm{t}}}$}计算HEMP的半高宽${\stackrel{\wedge }{t}}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}$和上升时间${\stackrel{\wedge }{t}}_{\mathrm{r}}$
), ArticleFig(id=1251595998552863321, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=CN, label=表4, caption=

基于ELM-PInet的HEMP参数识别

, figureFileSmall=null, figureFileBig=null, tableContent=
输入:接收信号矢量y,网络参数{W,b,β}。
输出:HEMP的形状参数${\stackrel{\wedge }{t}}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}$${\stackrel{\wedge }{t}}_{\mathrm{r}}$
(1)根据接收信号样本y,利用式(12)计算ELM-PInet的输出O
(2)根据识别概率最大化,基于ELM-PInet的输出O,根据式(14)估计接收信号矢量y的种类$\stackrel{\wedge }{n}$est,获得估计参数{${\alpha }_{\stackrel{\wedge }{n}{\mathrm{ }}_{\mathrm{e}\mathrm{s}\mathrm{t}}}$,${\beta }_{\stackrel{\wedge }{n}{\mathrm{ }}_{\mathrm{e}\mathrm{s}\mathrm{t}}}$}。
(3)根据式(15),利用估计参数{${\alpha }_{\stackrel{\wedge }{n}{\mathrm{ }}_{\mathrm{e}\mathrm{s}\mathrm{t}}}$,${\beta }_{\stackrel{\wedge }{n}{\mathrm{ }}_{\mathrm{e}\mathrm{s}\mathrm{t}}}$}计算HEMP的半高宽${\stackrel{\wedge }{t}}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}$和上升时间${\stackrel{\wedge }{t}}_{\mathrm{r}}$
), ArticleFig(id=1251595998615777883, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=EN, label=Table 5, caption=

Relative error of HEMP waveform parameters under on-site measured data

, figureFileSmall=null, figureFileBig=null, tableContent=
参数 试验方法 相对误差/%
${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$ 本文方法 14.6
${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$ 文献[11] 17.1
${e}_{{T}_{\mathrm{r}}}$ 本文方法 10.3
${e}_{{T}_{\mathrm{r}}}$ 文献[11] 15.6
), ArticleFig(id=1251595998678692445, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781958227616684, language=CN, label=表5, caption=

现场实测数据下HEMP波形参数的相对误差

, figureFileSmall=null, figureFileBig=null, tableContent=
参数 试验方法 相对误差/%
${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$ 本文方法 14.6
${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$ 文献[11] 17.1
${e}_{{T}_{\mathrm{r}}}$ 本文方法 10.3
${e}_{{T}_{\mathrm{r}}}$ 文献[11] 15.6
)], attaches=null, journal=Journal(id=1146119176004939786, delFlag=0, nameCn=科学技术与工程, nameEn=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, issn=1671-1815, eissn=, cn=11-4688/T, coden=null, periodic=4, language=CN, oaType=是, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=UKU/O7GSka5polgCTkbIIw==, journalPrice=null, startedYear=null, abbrevIsoEn=Sci Technol Eng, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1754445529766, createdBy=null, updatedBy=13701087609, firstLetterCn=S, firstLetterEn=S, subjectCode=Natural Sciences, subjectName=自然科学, subjectCodeEn=Natural Sciences, subjectNameEn=null, picCn=UKU/O7GSka5polgCTkbIIw==, picEn=5hwlULoNwcbj3xUmVi9MAQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1159791870395564357, language=CN, name=科学技术与工程, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529793, updatedTime=1754445529793, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=http://www.stae.com.cn/jsygc/site/menus/20090429150146001, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1159791870441701702, language=EN, name=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529804, updatedTime=1754445529804, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1146123166801305609, websiteList=[Website(id=1148243202391400884, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/kxjsygc/CN, language=CN, createTime=1751692112777, createBy=18614031015, updateTime=1753520965431, updateBy=18614031015, name=科学技术与工程-中文站点, tplId=1146099689490845704, title=科学技术与工程, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148622798802673703, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=articleTextType, value=kx, createTime=1751782615614, updateTime=1751782615614, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798781702180, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=banner, value=null, createTime=1751782615609, updateTime=1751782615609, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798769119267, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1751782615606, updateTime=1751782615606, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798794285094, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751782615612, updateTime=1751782615612, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798790090789, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751782615611, updateTime=1751782615611, creator=18614031015, updator=18614031015)]), Website(id=1155914124811976731, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/kxjsygc/EN, language=EN, createTime=1753521003206, createBy=18614031015, updateTime=1753521003206, updateBy=18614031015, name=科学技术与工程-英文站点, tplId=1146101810881728533, title=Science Technology and Engineering, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155914371227308235, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=articleTextType, value=kx, createTime=1753521061952, updateTime=1753521061952, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371210531016, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=banner, value=null, createTime=1753521061947, updateTime=1753521061947, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371202142407, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1753521061945, updateTime=1753521061945, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371223113930, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753521061950, updateTime=1753521061950, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371218919625, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753521061949, updateTime=1753521061949, creator=18614031015, updator=18614031015)])], journalTitle=科学技术与工程, weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=Science Technology and Engineering, journalPhotoCn=UKU/O7GSka5polgCTkbIIw==, journalPhotoEn=5hwlULoNwcbj3xUmVi9MAQ==, journalFirstLetter=S, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=null, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2403379, detailUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2403379, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/PDF/10.12404/j.issn.1671-1815.2403379, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/PDF/10.12404/j.issn.1671-1815.2403379, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
高空核爆电磁脉冲的参数识别与实验验证
收藏切换
PDF下载
卿朝进 1 , 张银杰 1 , 张岷涛 1 , 魏茂刚 2 , 林辉 3
科学技术与工程 | 论文·自动化技术、计算机技术 2025,25(9): 3749-3759
收起
收藏切换
科学技术与工程 | 论文·自动化技术、计算机技术 2025, 25(9): 3749-3759
高空核爆电磁脉冲的参数识别与实验验证
全屏
卿朝进1 , 张银杰1, 张岷涛1, 魏茂刚2, 林辉3
作者信息
  • 1 西华大学电气与电子信息学院, 成都 610039
  • 2 西华大学计算机与软件工程学院, 成都 610039
  • 3 成都航天凯特机电科技有限公司, 成都 611730
  • 卿朝进(1978—),男,汉族,四川安岳人,博士(博士后),教授。研究方向:无线网络与通信。E-mail:

High-altitude Electromagnetic Pulse Parameter Identification and Experimental Verification
Chao-jin QING1 , Yin-jie ZHANG1, Min-tao ZHANG1, Mao-gang WEI2, Hui LIN3
Affiliations
  • 1 School of Electrical and Electronic Information, Xihua University, Chengdu 610039, China
  • 2 School of Computer and Software Engineering, Xihua University, Chengdu 610039, China
  • 3 Chengdu Aerospace Kate Electromechanical Technology Co., Ltd., Chengdu 611730, China
出版时间: 2025-03-28 doi: 10.12404/j.issn.1671-1815.2403379
文章导航
收藏切换

在时变的无线场景中传输的高空核爆电磁脉冲(high altitude electromagnetic pulse, HEMP)不可避免地产生波形畸变,导致HEMP参数识别精确度显著地降低。为解决这一难题,考虑无线信道对HEMP波形的影响,利用其波形特征,研究基于极限学习机参数识别网络(extreme learning machine parameter identification network,ELM-PInet)的参数识别方法,以改善HEMP参数识别精确度。首先,从无线传输理论出发,构建HEMP波形传输模型,诠释无线信道对HEMP波形的非线性影响。随后,构建ELM-PInet进行波形畸变抑制,改善HEMP参数识别精度。最后,基于实验平台,对提出方法进行了现场辐照实验验证。仿真结果表明,相比于经典的HEMP参数识别方法,提出方法可改善HEMP参数的识别精度;针对不同的参数影响,ELM-PInet参数识别方法具有鲁棒性。同时,通过现场辐照实验进一步验证了提出方法的有效性。

高空核爆电磁脉冲  /  波形畸变  /  参数识别  /  极限学习机  /  无线传输  /  辐照试验

In dynamic wireless environments, the distortion of transmission waveform is inevitably present, deteriorating the accuracy of identifying high altitude electromagnetic pulse (HEMP) parameters. To address this issue, an extreme learning machine parameter identification network (ELM-PInet)-based parameter identification method was investigated, which leverages the characteristics of HEMP waveform and considers the impact of wireless channels, thereby improving the accuracy of HEMP parameter identification. To demonstrate the nonlinear effects of wireless channels, the transmission model of HEMP waveform was first constructed based on wireless transmission theory. Subsequently, an ELM-PInet was developed to suppress waveform distortion and improve the identification accuracy of HEMP parameters. Finally, the proposed method was validated through field irradiation test on the experimental platform. Simulation results demonstrate that compared to classical HEMP parameter identification methods, the identification accuracy of HEMP parameters is enhanced by the proposed method. Furthermore, the ELM-PInet-based parameter identification method exhibits its robustness against the impacts of different parameters. Additionally, the effectiveness of the proposed method is further validated through field irradiation experiments.

high altitude electromagnetic pulse (HEMP)  /  waveform distortion  /  parameter identification  /  extreme learning machine  /  wireless transmission  /  irradiation experiment
卿朝进, 张银杰, 张岷涛, 魏茂刚, 林辉. 高空核爆电磁脉冲的参数识别与实验验证. 科学技术与工程, 2025 , 25 (9) : 3749 -3759 . DOI: 10.12404/j.issn.1671-1815.2403379
Chao-jin QING, Yin-jie ZHANG, Min-tao ZHANG, Mao-gang WEI, Hui LIN. High-altitude Electromagnetic Pulse Parameter Identification and Experimental Verification[J]. Science Technology and Engineering, 2025 , 25 (9) : 3749 -3759 . DOI: 10.12404/j.issn.1671-1815.2403379
高空核爆电磁脉冲(high altitude electromagnetic pulse, HEMP)能量范围主要集中在300 MHz以下,对工作在此频段内的无线通信设备造成严重威胁[1]。虽然现有大多数应用已根据防雷要求在天线端口安装雷电防护器,但能否有效抵挡HEMP的高强度冲击,仍有待进一步验证[2]。根据持续时间、峰值功率、上升时间和波形频谱的特点,HEMP波形分为早期(E1)、中期(E2)和晚期(E3)3个阶段[3]。对于天线、线缆等小尺度耦合结构主要关注E1阶段波形。E1阶段波形具有分布范围广、脉冲幅值大、频谱范围宽和作用时间短等特点,对无线通信设备威胁最大[4]。通过参数估计,预测E1阶段波形的能量、频谱、幅度和持续时间等特征,可以评估设备在不同HEMP冲击下的防护性能。因此,准确识别HEMP参数,对有效应对HEMP冲击极其重要[5]。然而,HEMP波形的复杂多变趋势,出现了诸如Bell试验室和MIL-STD-461E标准波形及其系列延伸波形等问题,给战场电子系统的生存带来了严峻的考验[6-7]。随着该领域研究和工程技术的持续发展,亟待与时俱进地改善HEMP波形参数识别精度,助力电子设备对HEMP冲激的针对性防护,显著提升中国电子设备在未来战场上的生存能力。
目前,已有一定数量的文献对HEMP的波形参数表征与识别进行了研究[6-12]。在文献[6]中,从时域参数、频谱、归一化累积能流谱和总能量密度等方面,比较了E1阶段HEMP的各种波形参数;文献[7]使用时域有限差分算法,分析了不同条件下近地面的电磁脉冲环境下的HEMP波形参数;文献[8]使用时域波形电磁范数的HEMP标准波形确定方法,表征了HEMP效应的响应参数与波形参数之间的关系。在脉冲波形参数识别方面,文献[9]使用统计方法对HEMP和超带宽脉冲进行参数估计;文献[10]使用粒子群算法进行核信号脉冲参数的识别;文献[11]推导了HEMP脉冲波形参数的相对误差与定标截止频率之间的关系,并基于关系曲线进行脉冲带宽估计;文献[12]推导了双指数波形的带宽,并讨论了测量该波形所需的最小带宽。尽管文献[6-12]在HEMP参数表征与识别方面取得了一定的进展,但在计算大量HEMP波形参数和场分布时,数值计算和拟合预测方法存在诸多问题,如计算时间长、拟合效果不理想等。为弥补这些缺陷和非线性因素,文献[13]使用机器学习方法建立多参数快速计算模型,批量计算HEMP波形参数,展示出了新颖的视角。
然而,文献[13]中基于机器学习的HEMP参数识别,仍面临诸多问题。如不断变化的无线场景影响参数的识别精度,没有考虑到HEMP无线传输带来的波形畸变,无线场景中的泛化性需要改善;收集大量的训练数据费时、费力、耗成本;训练时间长,参数调谐复杂,等等。相比之下,极限学习机(extreme learning machine, ELM)具有训练周期短、参数调谐简单(简单的矩阵求逆)、训练集数据量需求小(如104个样本),泛化能力强等优势[14]。因此,ELM在HEMP参数识别时可能更具有优势。
为此,现借助ELM的诸多优势,研究基于极限学习机参数识别网络(extreme learning machine parameter identification network,ELM-PInet)的参数识别方法,以改善HEMP参数识别精确度。具体地,根据HEMP近地辐照模型,收集畸变的HEMP波形数据,基于其数据特征构建ELM-PInet。利用神经网络求解非线性问题的优势,捕获信道特征并抑制非线性因素干扰,从而改善HEMP参数识别的精度。通过仿真实验验证所提方法可改善HEMP参数的识别精度,针对不同的参数影响,ELM-PInet参数识别方法具有鲁棒性;在训练信道参数和测试信道参数不同的情况下,验证本文方法的泛化性。此外,还搭建实验平台进行现场实验,利用收集的现场实验数据,验证提出方法在真实场景下的有效性。
在国际标准中,使用双指数波形作为HEMP的标准电场波形,其电场波形E(t)[15]可表示为
E(t)=$\left\{\begin{array}{ll}0,& t\le 0\\ {E}_{0}{k}_{0}({\mathrm{e}}^{-\alpha t}-{\mathrm{e}}^{-\beta t}),& t>0\end{array}\right.$
式(1)中:E0为电场的最大幅值;k0为归一化系数;αβ为波形指数参数。对电场波形E(t)进行采样,形成波形采样矢量E∈RL×1,其中,L表示一个HEMP波形的采样点数。
归一化系数k0可以根据αβ的取值计算得到。根据文献[9],k0可表示为
k0=$\frac{1}{{\mathrm{e}}^{-\alpha {t}_{\mathrm{m}\mathrm{a}\mathrm{x}}}-{\mathrm{e}}^{-\beta {t}_{\mathrm{m}\mathrm{a}\mathrm{x}}}}$
式(2)中:tmax为电场波形的峰值时刻,满足条件为
tmax=$\frac{\mathrm{l}\mathrm{n}\alpha -\mathrm{l}\mathrm{n}\beta }{\alpha -\beta }$
根据文献[9],取trtFWHM分别表示HEMP波形的上升时间和HEMP波形的半高宽。也即是,tr表示脉冲幅度取值从E0的10%上升到E0的90%的时间段;tFWHM表示脉冲信号从脉冲上升沿E0的50%处到脉冲下降沿E0的50%处的时间间隔。对于给定的参数αβ,trtFWHM是恒定的[9],可以根据式(4)[16]计算得到,即
$\left\{\begin{array}{l}{t}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}=\frac{1}{\alpha }\sqrt{5.4\frac{\alpha }{\beta }+0.485+{\Delta }_{1}}\\ {t}_{\mathrm{r}}=\frac{1}{{t}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}\frac{1.505+{\Delta }_{2}}{\alpha \beta }\end{array}\right.$
式(4)中:Δ1Δ2为校正项,其值为常数。根据文献[16],当$\frac{\beta }{\alpha }$>10时,Δ1≈0,Δ2≈-0.05。
对于天线、线缆等小尺度耦合结构,主要关注E1阶段波形。根据式(1)~式(4)的计算关系,E1时期HEMP的几种标准的波形参数如表1所示[7],其电场波形如图1所示。
图1中可以观察到,各标准均是通过修正系数k0把峰值定为50 kV/m。但时域参数却存在很大的变化,根据文献[7],可以将HEMP的波形持续时间分为3种主要类型,即较短(MIL-STD-461E标准),中等(Bell实验室标准),较长(1976年出版物标准)。其主要特点是上升沿变缓,持续时间变长。
考虑空对地辐照场景。HEMP波形经无线空间的传播后,到达接收机。在接收机观察到的HEMP波形可表示为

y(t)=E(t)⊗h(t,τ)+n(t)

式(5)中:E(t)为HEMP辐射波形[根据(1)表征];⊗表示线性卷积运算;h(t,τ)为HEMP波形经历的无线传输信道;n(t)为接收机的本地噪声,可模型化为高斯噪声[20],即n(t)~CN(0,σ2),其中σ2为噪声方差。对接收到的HEMP波形进行采样,形成HEMP波形矢量y∈CL×1
由于地面不可避免地存在树木、山丘等散射体或遮挡物,因此h(t,τ)通常可模型化为莱斯信道场景[21],即
h(t)=g$\sqrt{\frac{k}{k+1}}$hLoS(t)+g$\sqrt{\frac{1}{k+1}}$P$\stackrel{M-1}{\sum _{\mathcal{l}=0}}$hNLoS,(t)
式(6)中:g为大尺度衰落因子,由收发双方的距离与周围的高大遮挡物决定;k为莱斯因子,表示直射路径与等效多条反射路径的能量强度比;P为第条路径的功率;M为多径条数;hLoS为直射分量;hNLoS为非直射分量。根据表1中E1期的HEMP波形参数,给出近地辐照模型下的电场波形,如图2所示。
图2可以看出,相对于发射的标准HEMP波形,接收到的HEMP波形产生了畸变。这主要是由于HEMP波形在无线中传输,其经历多条路径形成了多径干扰;此外,收发机不可避免地存在噪声也是因素之一。波形的畸变进一步加剧了HEMP波形参数的识别困难。
需要注意的是,这里仅仅以3个典型HEMP波形为示例,阐述畸变影响。然而,现实中的HEMP波形随不同的参数设置会衍生出不计其数的实际HEMP波形。因此,精确识别HEMP波形参数难度极大。无线传输引起的HEMP波形畸变造成HEMP波形参数的精确识别更加困难,不得不从畸变失真视角研究与开发新的识别方法。
然而,现有的大多数研究,如文献[8],并没有考虑HEMP无线传输带来的波形畸变。因此,其识别到的HEMP波形参数的难以准确,亟待进一步改进。为解决这一问题,考虑无线传输对HEMP波形参数识别的影响;基于HEMP近地辐照信道模型,研究HEMP参数识别。
机器学习具有很强的表达能力,可以处理无线场景变化引起的非线性因素干扰[22]。然而,无线场景的变化会影响识别精度。此外,深度神经网络训练需要收集大量训练数据,面临费时费力、训练时间长、参数调谐复杂等问题[23]。相比之下,ELM具有训练周期短、参数调谐简单、训练集数据需求小以及泛化能力较强等优势[24-25]
ELM-PInet的网络架构如表2所示。其输入节点数为L,隐藏层节点数为4L以及输出层节点数为Ns
表2中,输入层节点数L由输入HEMP波形的数据长度给定。输出层的节点数Ns由需识别的HEMP波形参数种类给定。此外,隐藏层节点数为4L[26]。与隐藏层节点数为10L的文献[26]相比,表2给出ELM-PInet网络具有更少的网络参数。
根据文献[27],Sigmoid函数适用于解决分类问题。为此,将隐藏层的激活函数选择为Sigmoid函数。Sigmoid函数[27-28]可表示为
Sigmoid(x)=$\frac{1}{1+\mathrm{e}\mathrm{x}\mathrm{p}(-x)}$
不失一般性,ELM网络的输入层和输出层采用了线性激活函数。
通常情况下,深度神经网络训练需要百万量级甚至更多的样本数量。相比之下,ELM网络训练所需的样本数就小得多(如104个训练样本)[14]。这为收集现场辐照数据减轻了难度,也是采用ELM-PInet的主要原因之一。
步骤1 仿真数据集生成。
(1)参考文献[9]中αβ参数的取值,将HEMP波形参数β设置为β=6×108,参数βα的比值满足$\frac{\beta }{\alpha }$∈[15,180]。根据参数αβ和式(2)计算得到k0。然后,将k0代入式(1)计算得到E(t)。对HEMP波形E(t)进行采样,则一个HEMP波形包含L=2 000个采样数据。
(2)根据式(5)给出的HEMP近地辐照模型,生成接收信号y(t)。信道模型h(t,τ)由式(6)给出;其中,大尺度衰落系数g被归一化,并均匀分布在[0.1,1]范围内[31];莱斯因子取值为k=10;考虑多径条数为M=4,根据文献[20],每条路径的大小分别设置为:P0=0.65,P1=0.52,P2=0.45,P3=0.32。本地噪声方差设置为σ2=1。
(3)共生成Nt=104个训练样本,表示为$\{{y}_{i},{T}_{i}{\}}_{\mathrm{i}=1}^{{\mathrm{N}}_{t}}$。其中,yi∈RL×1表示第i个训练样本;Ti${\mathrm{R}}^{{\mathrm{N}}_{s}\times 1}$为第i个训练样本对应的训练标签。
步骤2 实测数据收集。
通过与某单位合作,搭建了HEMP的辐照实验平台。借助实验平台,采集了HEMP的电场波形。由于HEMP实验的复杂性和危险性,导致其实测数据十分难得。通过HEMP的辐照试验,采集到了数10组参数电场波形。现场实验生成的发射波形的参数根据MIL-STD-461E标准设置,即k0=1.3,α=4×107,β=6×108,tr=2.5 ns,tFWHM=23 ns,E0=50 kV/m。借助辐照实验平台收集到的数据进一步验证提出方法的有效性。
ELM-PInet的离线训练过程如表3所示。在ELM-PInet训练过程中,输入权重矩阵W∈R4L×L与隐藏层偏置矢量b∈R4L×1的各元素,根据分布CN(0,1)随机地生成[29-30]。对于第i(i=1,2,…,Nt)个训练样本{yi,Ti},ELM-PInet的隐藏层输出Hi∈R4L×1

Hi=Sigmoid(Wyi+b)

式(8)中:Sigmoid(·)为Sigmoid激活函数,由式(7)定义。根据式(8),收集NtHi,形成隐藏层输出矩阵H${\mathrm{R}}^{4\mathrm{L}\times {\mathrm{N}}_{t}}$,表示为
H=[H1,H2,…,${H}_{{N}_{\mathrm{t}}}$]
相应地,训练标签矩阵T${\mathrm{R}}^{4\mathrm{L}\times {\mathrm{N}}_{t}}$表示为
T=[T1,T2,…,${T}_{{N}_{\mathrm{t}}}$]
根据隐藏层输出矩阵H和训练标签矩阵T,计算输出加重矩阵β∈RL×4L

β=T×H

式(11)中:(·)为求Moore-Penrose伪逆操作[31]。最后,保存ELM-PInet的网络参数为{W,b,β}。
基于ELM-PInet的HEMP参数识别过程如表4所示。将接收信号矢量y作为ELM-PInet的输入,得到ELM-PInet网络的输出O${\mathrm{R}}^{{\mathrm{N}}_{s}\times 1}$,表示为

O=βSigmoid(Wy+b)

由于存在Ns类HEMP波形参数{{α1,β1},{α2,β2},…,{${\alpha }_{{N}_{\mathrm{s}}}$,${\beta }_{{N}_{\mathrm{s}}}$}},ELM-PInet网络的输出O表示为
O=$[{O}_{1},{O}_{2},\dots,{O}_{{N}_{\mathrm{s}}}{]}^{\mathrm{T}}$
根据识别概率最大化,从Ns类HEMP波形中识别出当前波形,表示为
${\stackrel{\wedge }{n}}_{\mathrm{e}\mathrm{s}\mathrm{t}}$=$\underset{1\le n\le {N}_{\mathrm{s}}}{\mathrm{a}\mathrm{r}\mathrm{g}\mathrm{m}\mathrm{a}\mathrm{x}}\left|{O}_{n}\right|$
基于估计到的${\stackrel{\wedge }{n}}_{\mathrm{e}\mathrm{s}\mathrm{t}}$,找到HEMP波形参数集合{{α1,β1},{α2,β2},…,{${\alpha }_{{N}_{\mathrm{s}}}$,${\beta }_{{N}_{\mathrm{s}}}$}}中对应的参数HEMP波形参数{α,β}的估计值为{${\alpha }_{\stackrel{\wedge }{n}{\mathrm{ }}_{\mathrm{e}\mathrm{s}\mathrm{t}}}$,${\beta }_{\stackrel{\wedge }{n}{\mathrm{ }}_{\mathrm{e}\mathrm{s}\mathrm{t}}}$}。从而,基于式(4),计算得到HEMP的半高宽${\stackrel{\wedge }{t}}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}$和上升时间${\stackrel{\wedge }{t}}_{\mathrm{r}}$分别为
$\left\{\begin{array}{l}{\stackrel{\wedge }{t}}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}=\frac{1}{{\alpha }_{\stackrel{\wedge }{n}{\mathrm{ }}_{\mathrm{e}\mathrm{s}\mathrm{t}}}}\sqrt{5.4\frac{{\alpha }_{\stackrel{\wedge }{n}{\mathrm{ }}_{\mathrm{e}\mathrm{s}\mathrm{t}}}}{{\beta }_{\stackrel{\wedge }{n}{\mathrm{ }}_{\mathrm{e}\mathrm{s}\mathrm{t}}}}+0.485+{\Delta }_{1}}\\ {\stackrel{\wedge }{t}}_{\mathrm{r}}=\frac{1}{{t}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}\frac{1.505+{\Delta }_{2}}{{\alpha }_{\stackrel{\wedge }{n}{\mathrm{ }}_{\mathrm{e}\mathrm{s}\mathrm{t}}}{\beta }_{\stackrel{\wedge }{n}{\mathrm{ }}_{\mathrm{e}\mathrm{s}\mathrm{t}}}}\end{array}\right.$
需要说明的是,估计到索引${\stackrel{\wedge }{n}}_{\mathrm{e}\mathrm{s}\mathrm{t}}$,等效于估计到了参数{${\alpha }_{\stackrel{\wedge }{n}{\mathrm{ }}_{\mathrm{e}\mathrm{s}\mathrm{t}}}$,${\beta }_{\stackrel{\wedge }{n}{\mathrm{ }}_{\mathrm{e}\mathrm{s}\mathrm{t}}}$},也等效于计算得到了半高宽${\stackrel{\wedge }{t}}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}$和上升时间${\stackrel{\wedge }{t}}_{\mathrm{r}}$。因此,在实际实现过程中,可以根据波形参数集合{{α1,β1},{α2,β2},…,{${\alpha }_{{N}_{\mathrm{s}}}$,${\beta }_{{N}_{\mathrm{s}}}$}},利用映射关系,提前形成${\stackrel{\wedge }{t}}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}$${\stackrel{\wedge }{t}}_{\mathrm{r}}$的集合{{${\stackrel{\wedge }{t}}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}{}_{,{\alpha }_{1}}$,${{\stackrel{\wedge }{t}}_{\mathrm{r}}}_{,{\beta }_{1}}$},{${{\stackrel{\wedge }{t}}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}_{,{\alpha }_{2}}$,${\stackrel{\wedge }{t}}_{\mathrm{r},{\beta }_{2}}$},…,{${{\stackrel{\wedge }{t}}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}_{,{\alpha }_{{N}_{\mathrm{s}}}}$,${\stackrel{\wedge }{t}}_{\mathrm{r},{\beta }_{{N}_{\mathrm{s}}}}$}}。从而利用查表法加速在线半高宽和上升时间的生成速度。
参考文献[9]中αβ参数的取值,将HEMP波形参数β设置为β=6×108,参数βα的比值满足$\frac{\beta }{\alpha }$∈[15,180]。根据文献[6],HEMP标准峰值场强幅值E0设置为50 kV/m。根据HEMP波形参数αβE0的取值,结合式(1)~式(3),生成HEMP波形E(t)。对生成的HEMP波形E(t)按L=2 000个采样点进行采样。信道模型h(t,τ)由式(6)给出;其中,大尺度衰落系数g被归一化,并均匀分布在区间[0.1,1]上[32];莱斯因子取值为k=10;考虑多径条数为M=4,参照文献[20]的功率设置,将每条无线传输路径的功率设置为:P0=0.65,P1=0.52,P2=0.45,P3=0.32。本地噪声方差设置为σ2=1。ELM-PInet输出的HEMP形状参数${\stackrel{\wedge }{t}}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}$${\stackrel{\wedge }{t}}_{\mathrm{r}}$的相对误差[11]定义为
$\left\{\begin{array}{l}{e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}=\left|1-\frac{{\stackrel{\wedge }{t}}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}{{t}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}\right|\times 100\mathrm{\%}\\ {e}_{{T}_{\mathrm{r}}}=\left|1-\frac{{\stackrel{\wedge }{t}}_{\mathrm{r}}}{{t}_{\mathrm{r}}}\right|\times 100\mathrm{\%}\end{array}\right.$
式(16)中:${\stackrel{\wedge }{t}}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}$${\stackrel{\wedge }{t}}_{\mathrm{r}}$分别为HEMP半高宽和上升时间的估计值。
为了验证本文方法的有效性,图3给出了HEMP波形半高宽${\stackrel{\wedge }{t}}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}$和上升时间${\stackrel{\wedge }{t}}_{\mathrm{r}}$的相对误差${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$${e}_{{T}_{\mathrm{r}}}$
在每个给定的$\frac{\beta }{\alpha }$取值下,本文方法得到的相对误差${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$${e}_{{T}_{\mathrm{r}}}$均要低于文献[11]方法计算得到的相对误差。例如,在$\frac{\beta }{\alpha }$=15时,本文方法和文献[11]计算得到的${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$分别为11.22%和13.67%。同样,本文方法和文献[11]计算得到的${e}_{{T}_{\mathrm{r}}}$分别为8.32%和9.55%。这说明了在HEMP波形畸变的情况下,本文方法的参数识别精度要优于文献[11]。其原因在于,文献[11]方法没有考虑HEMP无线传输带来的波形畸变。而本文方法采用ELM-Pinet提取无线传输的HEMP波形畸变特征,在一定程度上抑制了无线传输带来的非线性影响。因此,本文方法可以获得比文献[11]更低的相对误差。
随着参数值$\frac{\beta }{\alpha }$的增大,本文方法和文献[11]方法的相对误差均减小,直至保持相对稳定。例如,当$\frac{\beta }{\alpha }$从15增加到180,本文方法得到的${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$从11.22%减小到9.48%,文献[11]得到的${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$从13.67%减小到12.44%。同样,本文方法得到的${e}_{{T}_{\mathrm{r}}}$从8.32%减小到6.95%,文献[11]得到的${e}_{{T}_{\mathrm{r}}}$从9.55%减小到8.88%。在给定的所有情况下,本文方法的${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$${e}_{{T}_{\mathrm{r}}}$均低于文献[11]。这表明了即使无线场景发生变化,本文方法在处理由HEMP无线传输引起的非线性因素干扰方面仍然具有优势。
总体上,相比于文献[11],本文方法可以获得更低的参数相对误差。因此,提出方法可有效地改善HEMP参数识别精度。
首先,验证莱斯因子k对HEMP参数识别的影响。随后,在不同多径条数M的取值下,验证本文方法的健壮性。
为验证莱斯因子k对HEMP波形参数识别的影响,仿真了莱斯因子k为5、10和15时的相对误差,如图4图5所示。除莱斯因子k变化外,其他仿真参数与3.1节中所述的参数设置保持一致。
在莱斯因子相同时,本文方法得到的相对误差均要低于文献[11]。例如,在莱斯因子k=5的情况下,参数$\frac{\beta }{\alpha }$=15时,本文方法和文献[11]计算得到的${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$分别为11.64%和13.99%,计算得到的${e}_{{T}_{\mathrm{r}}}$分别为8.55%和9.78%。在参数$\frac{\beta }{\alpha }$=180时,本文方法和文献[11]计算得到的${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$分别为7.09%和9.08%,计算得到的${e}_{{T}_{\mathrm{r}}}$分别为8.55%和9.78%。这说明了对于给定莱斯因子,在任意参数$\frac{\beta }{\alpha }$下,本文方法可以获得更低的相对误差。验证了本文方法在莱斯因子影响下的有效性。
随着莱斯因子k的增大,本文方法和文献[11]方法得到的相对误差${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$${e}_{{T}_{\mathrm{r}}}$均随之减小。例如,在给定参数$\frac{\beta }{\alpha }$=180的情况下,莱斯因子k=5时,本文方法的${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$为9.69%。而在莱斯因子k=10和k=15的情况下,本文方法的${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$分别为9.48%和9.31%。同样,对于${e}_{{T}_{\mathrm{r}}}$也是如此。在给定参数$\frac{\beta }{\alpha }$=180的情况下,莱斯因子k=5时,本文方法的${e}_{{T}_{\mathrm{r}}}$为7.09%。而在k=10和k=15时,本文方法的${e}_{{T}_{\mathrm{r}}}$分别下降至6.95%和6.91%。这说明了莱斯因子越大,参数识别的相对误差越小。其原因是莱斯因子k增加,使得接收信号中直射分量占据了主要地位。尽管如此,在所有给定的情况下,本文方法的相对误差仍明显的低于文献[11]方法的相对误差。这意味着提出方法对莱斯因子的影响具有鲁棒性。
综上所述,在莱斯因子变化的情况下,相比于文献[11],本文方法可以获得更低的参数相对误差。从而验证了提出方法在改善HEMP参数识别精度上具有鲁棒性。
为验证多径条数M对HEMP波形参数识别的影响,仿真了在多径条数M为4、6和8时的相对误差,如图6图7所示。除多径条数M变化外,其他仿真参数与3.1节中所述的参数设置保持一致。
在多径条数相同时,本文方法得到的相对误差均要低于文献[11]。例如,在莱斯因子M=6的情况下,参数$\frac{\beta }{\alpha }$=15时,本文方法和文献[11]计算得到的${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$分别为12.47%和15.52%,计算得到的${e}_{{T}_{\mathrm{r}}}$分别为8.81%和10.87%。参数$\frac{\beta }{\alpha }$=180时,本文方法和文献[11]计算得到的${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$分别为10.77%和13.78%,计算得到的${e}_{{T}_{\mathrm{r}}}$分别为7.81%和9.83%。这说明了给定多径条数,在任意参数$\frac{\beta }{\alpha }$下,本文方法可以获得更低的相对误差。验证了本文方法在多径条数影响下的有效性。
随着多径条数M的增大,本文方法和文献[11]方法得到的相对误差均随之减小。例如,在给定参数$\frac{\beta }{\alpha }$=180的情况下,多径条数M=8时,本文方法的${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$为11.65%,文献[11]的${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$为14.67%。而在多径条数M=6和M=4的情况下,本文方法的${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$降至10.77%和9.49%,文献[11]的${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$降至13.78%和12.42%。同样,对于${e}_{{T}_{\mathrm{r}}}$也是如此。在给定参数$\frac{\beta }{\alpha }$=180的情况下,多径条数M=8时,本文方法的${e}_{{T}_{\mathrm{r}}}$为8.49%,文献[11]的${e}_{{T}_{\mathrm{r}}}$为10.53%。而在多径条数M=6和M=4时,本文方法的${e}_{{T}_{\mathrm{r}}}$降至7.81%和6.95%,文献[11]的${e}_{{T}_{\mathrm{r}}}$降至9.83%和8.88%。尽管如此,本文方法的相对误差仍明显低于文献[11]方法的相对误差。这说明了多径条数越大,参数识别的相对误差越大。其原因在于HEMP的脉冲能量很大,从而导致其经历多条路径形成的多径干扰对HEMP波形的影响极为显著。
由此可见,在多径条数变化的情况下,本文方法的相对误差性能仍优于文献[11],可以获得更低的相对误差。从而验证了提出方法在改善HEMP参数识别精度上具有鲁棒性。
首先,验证莱斯因子k对HEMP参数识别的泛化性影响。随后,在不同多径条数M的取值下,验证本文方法的泛化性。
为了验证莱斯因子对本文方法泛化性能的影响,仿真了莱斯因子k为5、和15的相对误差。利用莱斯因子k=10的HEMP波形数据来训练ELM-PInet的网络参数。同时,将k=5,k=10和k=15的HEMP波形数据用于ELM-PInet的在线运行。以反映训练信道参数与测试信道参数的差异。其仿真结果如图8图9所示。除莱斯因子k变化外,其他仿真参数与3.1节中所述的参数设置保持一致。
随着莱斯因子的增大,本文方法和文献[11]得到的相对误差均随之减小。例如,在$\frac{\beta }{\alpha }$=180的情况下,莱斯因子k=10时,本文方法的${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$为9.48%,文献[11]的${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$为12.44%。而在莱斯因子k=15和k=5的情况下,本文方法的${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$分别为10.98%和11.47%,文献[11]的${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$分别为12.31%和12.69%。同样,对于${e}_{{T}_{\mathrm{r}}}$也是如此。在给定参数$\frac{\beta }{\alpha }$=180的情况下,莱斯因子k=10时,本文方法的${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$为6.95%,文献[11]的${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$为8.83%。而在莱斯因子k=15和k=5时,本文方法的${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$增加至7.73%和8.01%,文献[11]的${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$分别为8.83%和9.09%。这说明在莱斯因子k=10时,本文方法的相对误差最低。其原因在于,ELM-PInet的网络参数是在莱斯因子k=10的条件下生成的。与莱斯因子k=15和k=5的情况相比,ELM-PInet包含更多莱斯因子k=10的数据特征。
在给定的参数$\frac{\beta }{\alpha }$内,当莱斯因子k=5,k=10和k=15时,文献[11]获得的相对误差逐渐降低。例如,在$\frac{\beta }{\alpha }$=180时,文献[11]的${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$依次为12.69%、12.44%和12.31%。这说明随着莱斯因子的增大,HEMP参数识别的相对误差会变得更小。其原因是莱斯因子越大,接收信号中直射分量占比更大,这意味着信道条件更好。
k=10进行ELM-PInet参数的训练,对没有经过训练的k=5和k=15,本文方法也取得了较低的相对误差,且比文献[11]方法好。这说明提出方法对没有训练过的信道参数同样能取得较好的性能,具有泛化性。
综上所述,在莱斯因子变化的情况下,本文方法仍然可以获得较好的参数识别精度。验证了本文方法在改善HEMP参数识别精度上具有泛化性。
为了验证多径条数对本文方法泛化性能的影响,仿真了多径条数M为4、6和8的相对误差,用以反映训练信道模型与测试信道模型的差异。使用多径条数M=4的HEMP波形数据来训练ELM-PInet的网络参数。同时,将多径条数为M=4、M=6和M=8情况下的HEMP波形数据用于ELM-PInet的在线运行。其结果如图10图11所示。除多径条数M变化外,其他仿真参数与3.1节中所述的参数设置保持一致。
在给定的$\frac{\beta }{\alpha }$范围内,随着多径条数的增大,本文方法和文献[11]得到的相对误差均随之减小。例如,在$\frac{\beta }{\alpha }$=15的情况下,多径条数M=8时,本文方法的${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$为13.0%,文献[11]的${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$为16.2%。而在多径条数M=6和M=4的情况下,本文方法的${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$降至12.72%和11.22%,文献[11]的${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$降至15.52%和13.67%。同样,对于${e}_{{T}_{\mathrm{r}}}$也是如此。在给定参数$\frac{\beta }{\alpha }$=15的情况下,多径条数M=8时,本文方法的${e}_{{T}_{\mathrm{r}}}$为8.91%,文献[11]的${e}_{{T}_{\mathrm{r}}}$为11.42%。而在多径条数M=6和M=4时,本文方法的${e}_{{T}_{\mathrm{r}}}$降至8.77%和8.32%,文献[11]的${e}_{{T}_{\mathrm{r}}}$降至10.87%和9.55%。此外,在本文方法中,相对于M=6和M=8,M=4时的${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$${e}_{{T}_{\mathrm{r}}}$明显更低。其原因是,在生成ELM-PInet的网络参数时,本文方法充分考虑了多径干扰对HEMP波形的影响。
对于所有给定的情况,本文方法获得的相对误差总是低于文献[11]。说明了对于多径条数的变化,本文方法在改善HEMP参数识别精度方面仍具有较好的效果。
M=4进行ELM-PInet参数的训练,对没有经过训练的M=6和M=8,本文方法也取得了较低的相对误差,且比文献[11]方法好。这说明提出方法对没有训练过的信道参数同样能取得较好的性能,具有泛化性。
综上所述,实验仿真表明,即使在训练信道参数和测试信道参数不同时,而本文方法仍然能够取得较低的相对误差,具有良好的泛化能力。这一结果验证了本文方法的可靠性,并为无线场景下的HEMP的参数识别提供了有力支持。
HEMP辐照试验中,使用垂直极化有界波模拟器开展脉冲辐照效应试验。该模拟器能产生上升沿为2.5 ns、脉宽为23 ns和电场强度峰值高达50 kV/m的双指数脉冲电场波形(即MIL-STD-461E标准波形)。其中,电场监测设备、垂直极化有界波模拟器和辐照试验场地的位置,如图12所示。
由于HEMP试验的复杂性、高成本开销和危险性,选择了MIL-STD-461E标准波形进行辐照实验验证,并采集了数10组的HEMP电场数据,其电场波形如图13所示。
利用本文方法和文献[11]的方法对试验采集的数10组MIL-STD-461E标准波形数据进行参数识别。根据式(16)获得HEMP形状参数(${\stackrel{\wedge }{t}}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}$${\stackrel{\wedge }{t}}_{\mathrm{r}}$)的相对误差,其结果如表5所示。
表5可知,本文方法得到的${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$${e}_{{T}_{\mathrm{r}}}$分别为14.6%和10.3%,文献[11]方法得到${e}_{{T}_{\mathrm{F}\mathrm{W}\mathrm{H}\mathrm{M}}}$${e}_{{T}_{\mathrm{r}}}$为17.1%和15.6%。现场实验结果表明,在无线传输导致HEMP波形畸变的情况下,本文方法的参数识别精度要优于文献[11]。特别地,本文方法在实测数据下也能得到较好的参数识别效果。结合仿真实验结果,证明了基于ELM-PInet的HEMP参数识别方法在真实场景下具有泛化性。
针对接收信号存在畸变的HEMP参数识别问题,研究了基于ELM-PInet的参数识别方法,以改善HEMP参数的识别精度。根据畸变的HEMP波形特征构建ELM-PInet,可以有效抑制无线传输产生的非线性因素干扰,从而改善HEMP参数识别精确度。最后,通过实验平台,获取现场实验数据进行HEMP参数识别。实验结果表明,对于莱斯因子和多径条数的影响,本文方法在提高HEMP参数识别精度方面具有鲁棒性。在现场测试中,与经典的HEMP参数估计方法相比,本文方法取得了更好的参数识别精度,进一步验证了提出方法的有效性。具体结论如下。
(1)从HEMP无线传输畸变的视角出发,研究HEMP参数识别方法。不同于经典的参数识别方法,在参数识别时考虑HEMP波形因无线传输带来的畸变。因此,相对于没有考虑无线传输引起畸变的HEMP参数识别,本文方法更加适用于真实场景。仿真结果表明:相对于经典的HEMP参数估计方法,本文方法获得的参数相对误差更低,能有效地提高HEMP形状参数的识别精度。通过获取精确的HEMP波形参数,从而有针对性地为我国现有的电子设备提供HEMP防护方法。
(2)为应对波形畸变引起HEMP参数识别精度降低的问题,提出了一种基于ELM-PInet的HEMP参数识别方法。根据HEMP近地辐照模型,获取畸变HEMP波形数据,基于畸变HEMP波形数据特征,构建ELM-PInet的网络参数进行参数识别。与传统的HEMP参数估计方法不同,本文方法将畸变的HEMP波形数据作为训练数据集。因此,本文方法能够有效处理无线场景变化造成的非线性因素干扰,降低HEMP参数识别结果的相对误差。仿真结果表明,对于莱斯因子和多径条数的影响,提出方法具有鲁棒性。在训练信道参数和测试信道参数不同时,提出方法仍然能够取得较低的相对误差,具有良好的泛化能力。
(3)搭建了实验平台进行现场实验,利用现场实验数据进行HEMP参数识别。通过辐照实验现场采集了数10组HEMP电场波形,结合已经训练好的ELM-PInet,进行HEMP参数识别。具体地,利用HEMP近地辐照模型获取畸变的HEMP波形数据训练ELM-PInet的网络参数,将采集的现场实验数据输入ELM-PInet进行HEMP波形参数的识别。现场实验结果进一步验证了提出方法的有效性。
  • 国家自然科学基金(62301447)
  • 四川省科技计划(2023YFG0316)
  • 四川省科技计划“揭榜挂帅”项目(23GSC00004)
  • 西华大学校重点项目(Z1320929)
  • 中国高校产学研创新基金(2021ITA10016)
参考文献 引证文献
排序方式:
[1]
杜传报, 毛从光, 崔志同, . 甚高频无线通信系统高空电磁脉冲易损性分析[J]. 现代应用物理, 2022, 13(2): 110-115, 161.
Du Chuanbao, Mao Congguang, Cui Zhitong, et al. Vulnerability analysis of high-altitude electromagnetic pulses in very high frequency wireless communication systems[J]. Modern Applied Physics, 2022, 13(2): 110-115, 161.
[2]
文巧莉. 118-136 MHz天线耦合强电磁脉冲特性及防护方法研究[D]. 南京: 南京信息工程大学, 2022.
Wen Qiaoli. Research on the characteristics and protection methods of strong electromagnetic pulse coupling in 118-136 MHz antennas[D]. Nanjing: Nanjing University of Information Technology, 2022.
[3]
Giri D V, Hoad R, Sabath F. High-power electromagnetic effects on electronic systems[M]. London: Artech, 2020.
[4]
秦锋, 陈伟, 毛从光, . 电力系统高空电磁脉冲效应研究综述[J]. 现代应用物理, 2023, 14(3): 16-31.
Qin Feng, Chen Wei, Mao Congguang, et al. A review of research on high-altitude electromagnetic pulse effects in power systems[J]. Modern Applied Physics, 2023, 14(3): 16-31.
[5]
郭稳. 强电磁脉冲下防护器件的冲击特性及组合使用方法的研究[D]. 南京: 南京信息工程大学, 2023.
Guo Wen. Research on the impact characteristics and combination usage of protective devices under strong electromagnetic pulse[D] Nanjing: Nanjing University of Information Technology, 2023.
[6]
谢彦召, 王赞基, 王群书, . 高空核爆电磁脉冲波形标准及特征分析[J]. 强激光与粒子束, 2003(8): 781-787.
Xie Yanzhao, Wang Zanji, Wang Qunshu, et al. Standard and characteristic analysis of electromagnetic pulse waveform for high-altitude nuclear explosions[J]. Intense Laser and Particle Beam, 2003(8): 781-787.
[7]
陶灵姣, 柴焱杰, 李智, . 高功率电磁环境下导弹发射阵地近地面电磁脉冲波形仿真[J]. 指挥控制与仿真, 2009, 31(2): 103-107.
Tao Lingjiao, Chai Yanjie, Li Zhi, et al. Simulation of near ground electromagnetic pulse waveform of missile launch site in high power electromagnetic environment[J]. Command, Control and Simulation, 2009, 31(2): 103-107.
[8]
马良, 程引会, 郭景海. 高空电磁脉冲标准波形参数的时域确定方法[J]. 现代应用物理, 2022, 13(2): 98-103, 122.
Ma Liang, Cheng Yinhui, Guo Jinghai. Time domain determination method for standard waveform parameters of high-altitude electromagnetic pulses[J]. Modern Applied Physics, 2022, 13(2): 98-103, 122.
[9]
Mao C, Zhou H. Novel parameter estimation of double exponential pulse (EMP, UWB) by statistical means[J]. IEEE Transactions on Electromagnetic Compatibility, 2008, 50(1): 97-100.
[10]
王乾丞. 核脉冲的参数识别及自适应成形方法[D]. 成都: 成都理工大学, 2021.
Wang Qiancheng. Parameter identification and adaptive shaping method of nuclear pulses[D]. Chengdu: Chengdu University of Technology, 2021.
[11]
Yang J, Cui Z, Cao F, et al. Estimation method of bandwidth requirements for double exponential pulse measurement[J]. IEEE Transactions on Electromagnetic Compatibility, 2023, 65(6): 1981-1989.
[12]
Chen P, Mao C, Wu G. Highest frequency estimation of HEMP standard waveforms[C]// 2016 Asia-Pacific International Symposium on Electromagnetic Compatibility. Shenzhen: IEEE, 2016: 283-285.
[13]
王锦锦, 程引会, 聂鑫, . 基于机器学习的高空电磁脉冲环境快速计算方法[J]. 计算机科学, 2023, 50(S1): 853-857.
Wang Jinjin, Cheng Yinhui, Nie Xin, et al. A fast calculation method for high altitude electromagnetic pulse environment based on machine learning[J]. Computer Science, 2023, 50(S1): 853-857.
[14]
Qing C, Dong L, Wang L, et al. Joint model and data-driven receiver design for data-dependent superimposed training scheme with imperfect hardware[J]. IEEE Transactions on Wireless Communications, 2022, 21(6): 3779-3791.
[15]
Hoad R, Radasky W A. Progress in high-altitude electromagnetic pulse (HEMP) standardization[J]. IEEE Transactions on Electromagnetic Compatibility, 2013, 55(3): 532-538.
[16]
Shi Y, Nie X, Zhu Z, et al. A simplified method for parameter estimating of double exponential pulse[C]// 2016 Asia-Pacific International Symposium on Electromagnetic Compatibility. Shenzhen: IEEE, 2016: 537-539.
[17]
International Electrotechnical Commission. Description of HEMP environment-radiation disturbance basic EMC publication:IEC 61000-2-9-1996[S]. Lundon: IEC,1996.
[18]
Ianoz M, Nicoara B I C, Radasky W A. Modeling of an EMP conducted environment[J]. IEEE Transactions on EMC, 1996, 38(3): 400-413.
[19]
Ricketts L W, Bridges J E, Miletta J. EMP radiation and protective techniques[M]. New York: Wiley, 1976.
[20]
Wang J, Cui Y, Jiang H, et al. Estimation of rice factor ratio for doubly selective fading channels[J]. IEEE Access, 2020, 99: 31330-31340.
[21]
Rahayu S, Iskandar. Study on MMSE-DFT based channel estimation for HAPS OFDM system[C]// 2023 9th International Conference on Wireless and Telematics. Solo: IEEE, 2023: 1-5.
[22]
Shah S I H, Khan S A, Ghauri S A, et al. A novel hybrid cuckoo search- extreme learning machine approach for modulation classification[J]. IEEE Access, 2019, 99: 90525-90537.
[23]
Guo Y P, Zhong D, Sun H X, et al. SemiAMR: semi-supervised automatic modulation recognition with corrected pseudo-label and consistency regularization[J]. IEEE Transactions on Cognitive Communications and Networking, 2024, 10(1): 107-121.
[24]
Shi Y, Wang C, Ge G, et al. ELM-based discriminant auto-encoder and multi-kernel fusion for radar specific emitter identification[J]. IEEE Access, 2023(11): 110010-110022.
[25]
盛晓晨, 史旭东, 熊伟丽. 改进粒子群优化的极限学习机软测量建模方法[J]. 计算机应用研究, 2020, 37(6): 1683-1687.
Sheng Xiaochen, Shi Xudong, Xiong Weili. Soft sensing modeling method for extreme learning machine with improved particle swarm optimization[J]. Computer Application Research, 2020, 37(6): 1683-1687.
[26]
Qing C, Yu W, Cai B, et al. ELM-based frame synchronization in burst-mode communication systems with nonlinear distortion[J]. IEEE Wireless Communication Letters, 2020, 9(6): 915-919.
[27]
Ding B, Qian H, Zhou J. Activation functions and their characteristics in deep neural networks[C]// 2018 Chinese Control And Decision Conference. Shenyang: IEEE, 2018: 1836-1841.
[28]
张焕, 张庆, 于纪言. 激活函数的发展综述及其性质分析[J]. 西华大学学报(自然科学版), 2021, 40(4): 1-10.
Zhang Huan, Zhang Qing, Yu Jiyan. Overview of the development of activation function and its nature analysis[J]. Journal of Xihua University (Natural Science Edition), 2021, 40(4): 1-10.
[29]
尚艳芳, 李丽敏, 温宗周, . 基于优化核极限学习机的泥石流危险性评估[J]. 科学技术与工程, 2023, 23(2): 528-535.
Shang Yanfang, Li Limin, Wen Zongzhou, et al. Risk assessment of debris flow based on optimized kernel extreme learning machine[J]. Science and Technology and Engineering, 2023, 23(2): 528-535.
[30]
安琪, 王占彬, 安国庆, . 基于随机森林-遗传算法-极限学习机的非侵入式负荷识别方法[J]. 科学技术与工程, 2022, 22(5): 1929-1935.
An Qi, Wang Zhanbin, An Guoqing, et al. A non-invasive load identification method based on random forest genetic algorithm extreme learning machine[J]. Science and Technology and Engineering, 2022, 22(5): 1929-1935.
[31]
Huang G B, Zhu Q Y, Siew C K. Extreme learning machine: theory and applications[J]. Neurocomputing, 2006, 70(1/3): 489-501.
[32]
Wu L, Zhang Z, Dang J, et al. Joint user identification and channel estimation over rician fading channels[J]. IEEE Transactions on Vehicular Technology, 2020, 69(6): 6803-6807.
2025年第25卷第9期
PDF下载
303
124
引用本文
BibTeX
文章信息
doi: 10.12404/j.issn.1671-1815.2403379
  • 接收时间:2024-05-08
  • 首发时间:2025-07-09
  • 出版时间:2025-03-28
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-05-08
  • 修回日期:2024-12-27
基金
国家自然科学基金(62301447)
四川省科技计划(2023YFG0316)
四川省科技计划“揭榜挂帅”项目(23GSC00004)
西华大学校重点项目(Z1320929)
中国高校产学研创新基金(2021ITA10016)
作者信息
    1 西华大学电气与电子信息学院, 成都 610039
    2 西华大学计算机与软件工程学院, 成都 610039
    3 成都航天凯特机电科技有限公司, 成都 611730
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2403379
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏