Article(id=1149769466151612831, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149769458706723113, articleNumber=null, orderNo=null, doi=10.12404/j.issn.1671-1815.2404712, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1719158400000, receivedDateStr=2024-06-24, revisedDate=1740412800000, revisedDateStr=2025-02-25, acceptedDate=null, acceptedDateStr=null, onlineDate=1752056002414, onlineDateStr=2025-07-09, pubDate=1747497600000, pubDateStr=2025-05-18, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1752056002414, onlineIssueDateStr=2025-07-09, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1752056002414, creator=13701087609, updateTime=1752056002414, updator=13701087609, issue=Issue{id=1149769458706723113, tenantId=1146029695717560320, journalId=1146123166801305609, year='2025', volume='25', issue='14', pageStart='5705', pageEnd='6154', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1752056000638, creator=13701087609, updateTime=1768456798957, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1218559392753041779, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149769458706723113, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1218559392753041780, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149769458706723113, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=6100, endPage=6108, ext={EN=ArticleExt(id=1149769466763981227, articleId=1149769466151612831, tenantId=1146029695717560320, journalId=1146123166801305609, language=EN, title=Aviation Cable Arc Fault Detection Based on Inception-BiLSTM, columnId=1156262731079607234, journalTitle=Science Technology and Engineering, columnName=Papers·Aeronautics and Astronautics, runingTitle=null, highlight=null, articleAbstract=

A method for diagnosing AC series arc faults based on the Inception module and BiLSTM (bidirectional long short-term memory) was proposed to address the challenge of identifying small current changes caused by arc faults in aviation cables. First, features of the raw current data were extracted by calculating the discrete sum of squares of the autocorrelation coefficient, Shannon entropy, and wavelet energy entropy. These features are then combined to form a new feature matrix, enhancing the original data's feature representation. Subsequently, the Inception-BiLSTM network learns from the feature matrix and ultimately completes the arc fault diagnosis. To validate the diagnostic performance of the model in practical environments, a series of experiments were conducted, including vibration tests, stress tests, and wet cable tests, based on an aviation cable arc fault simulation platform, with the experimental data being integrated as detection samples. The experimental results show that the proposed method achieves a high accuracy rate of 99.69% in identifying arc faults.

, correspAuthors=Dai LIU, 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=Dai LIU, Chen-hui LI), CN=ArticleExt(id=1149769510988723180, articleId=1149769466151612831, tenantId=1146029695717560320, journalId=1146123166801305609, language=CN, title=基于Inception-BiLSTM的航空电缆电弧故障检测, columnId=1156262731373208516, journalTitle=科学技术与工程, columnName=论文·航空、航天, runingTitle=null, highlight=null, articleAbstract=

针对航空电缆电弧故障引起的微小电流变化难以识别的问题,提出了一种基于Inception模块和双向长短期记忆网络(bidirectional long short-term memory,BiLSTM)的交流串联电弧故障诊断方法。首先通过计算自相关系数的离散平方和(discrete sum of squares of the atocorrelation coefficient)、信息熵(Shannon entropy)以及小波能量熵(wavelet energy entropy)提取原始电流数据的特征,将特征合并形成新的特征矩阵,对原始数据实现特征增强。之后Inception-BiLSTM网络利用特征矩阵进行学习,最后完成对电弧故障的诊断。为了验证模型在实际环境中的诊断性能,在充分考虑实际情况下,基于航空电缆电弧模拟实验平台进行了振动试验、应力实验以及潮湿电缆实验,并将实验数据整合作为检测样本。实验结果表明,本文方法对于识别电弧故障有着较高的准确度,可以达到99.69%。

, correspAuthors=刘岱, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=xA8GjLrU2L2DiZOBHO1FpQ==, magXml=6P+Z5mb6OzqH9J59SuAmFA==, pdfUrl=null, pdf=/u+w6oYWOPh2lTN0B66SFA==, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=Q+8Ooc8fCH2gYUMNyGKV8A==, mapNumber=null, authorCompany=null, fund=null, authors=

刘岱(1981—),男,汉族,天津人,硕士,讲师。研究方向:航空器维修及适航审定技术。E-mail:

, authorsList=刘岱, 李晨辉)}, authors=[Author(id=1179433899944984690, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=dliu@cauc.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1179433899999510645, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, authorId=1179433899944984690, language=EN, stringName=Dai LIU, firstName=Dai, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1. Emgineer Techniques Training Center,Civil Aviation University of China, Tianjin 300300, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1179433900058230902, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, authorId=1179433899944984690, language=CN, stringName=刘岱, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1. 中国民航大学工程技术训练中心, 天津 300300, bio={"content":"

刘岱(1981—),男,汉族,天津人,硕士,讲师。研究方向:航空器维修及适航审定技术。E-mail:

"}, bioImg=null, bioContent=

刘岱(1981—),男,汉族,天津人,硕士,讲师。研究方向:航空器维修及适航审定技术。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1179433899793989739, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, xref=null, ext=[AuthorCompanyExt(id=1179433899798184044, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, companyId=1179433899793989739, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. Emgineer Techniques Training Center,Civil Aviation University of China, Tianjin 300300, China), AuthorCompanyExt(id=1179433899806572653, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, companyId=1179433899793989739, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. 中国民航大学工程技术训练中心, 天津 300300)])]), Author(id=1179433900112756856, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, 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=1179433900179865722, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, authorId=1179433900112756856, language=EN, stringName=Chen-hui LI, firstName=Chen-hui, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2. College of Electronic Information and Automation,Civil Aviation University of China, Tianjin 300300, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1179433900238585979, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, authorId=1179433900112756856, language=CN, stringName=李晨辉, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2. 中国民航大学电子信息与自动化学院, 天津 300300, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1179433899869487214, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, xref=null, ext=[AuthorCompanyExt(id=1179433899877875823, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, companyId=1179433899869487214, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2. College of Electronic Information and Automation,Civil Aviation University of China, Tianjin 300300, China), AuthorCompanyExt(id=1179433899886264432, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, companyId=1179433899869487214, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2. 中国民航大学电子信息与自动化学院, 天津 300300)])])], keywords=[Keyword(id=1179433900372803708, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=EN, orderNo=1, keyword=inception module), Keyword(id=1179433900431523965, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=EN, orderNo=2, keyword=BiLSTM), Keyword(id=1179433900502827134, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=EN, orderNo=3, keyword=aviation cable arc fault), Keyword(id=1179433900574130303, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=EN, orderNo=4, keyword=features extraction), Keyword(id=1179433900641239168, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=CN, orderNo=1, keyword=Inception模块), Keyword(id=1179433900699959425, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=CN, orderNo=2, keyword=双向长短期记忆网络), Keyword(id=1179433900758679682, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=CN, orderNo=3, keyword=航空电缆电弧故障), Keyword(id=1179433900813205635, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=CN, orderNo=4, keyword=特征提取)], refs=[Reference(id=1179433904038625451, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, doi=null, pmid=null, pmcid=null, year=2023, volume=18, issue=3, pageStart=18, pageEnd=34, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=刘苏德, 王子昕, 靖子洋, journalName=电气工程学报, refType=null, unstructuredReference=刘苏德, 王子昕, 靖子洋, 等. 航空线缆电弧故障引发电气火灾研究综述[J]. 电气工程学报, 2023, 18(3): 18-34., articleTitle=航空线缆电弧故障引发电气火灾研究综述, refAbstract=null), Reference(id=1179433904101540012, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, doi=null, pmid=null, pmcid=null, year=2023, volume=18, issue=3, pageStart=18, pageEnd=34, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=Liu Sude, Wang Zixin, Jing Ziyang, journalName=Journal of Electrical Engineering, refType=null, unstructuredReference=Liu Sude, Wang Zixin, Jing Ziyang, et al. Review of research on electrical fires caused by arc faults in aviation cables[J]. Journal of Electrical Engineering, 2023, 18(3): 18-34., articleTitle=Review of research on electrical fires caused by arc faults in aviation cables, refAbstract=null), Reference(id=1179433904177037485, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, doi=null, pmid=null, pmcid=null, year=2019, volume=34, issue=14, pageStart=2913, pageEnd=2921, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=王尧, 张彦风, 牛峰, journalName=电工技术学报, refType=null, unstructuredReference=王尧, 张彦风, 牛峰, 等. 光伏直流电弧电磁辐射特性分析与量方法[J]. 电工技术学报, 2019, 34(14): 2913-2921., articleTitle=光伏直流电弧电磁辐射特性分析与量方法, refAbstract=null), Reference(id=1179433904244146350, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, doi=null, pmid=null, pmcid=null, year=2019, volume=34, issue=14, pageStart=2913, pageEnd=2921, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=Wang Yao, Zhang Yanfeng, Niu Feng, journalName=Transactions of China Electrotechnical Society, refType=null, unstructuredReference=Wang Yao, Zhang Yanfeng, Niu Feng, et al. Analysis and measurement methods of electromagnetic radiation characteristics of photovoltaic DC arc[J]. Transactions of China Electrotechnical Society, 2019, 34(14): 2913-2921., articleTitle=Analysis and measurement methods of electromagnetic radiation characteristics of photovoltaic DC arc, refAbstract=null), Reference(id=1179433904328032431, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, doi=null, pmid=null, pmcid=null, year=2022, volume=26, issue=3, pageStart=29, pageEnd=36, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=Zhao L, Zhou Y, Chen K L, journalName=IEEE Industry Applications Magazine, refType=null, unstructuredReference=Zhao L, Zhou Y, Chen K L, et al. High-speed arcing fault detection: using the light spectrum[J]. IEEE Industry Applications Magazine, 2022, 26(3): 29-36., articleTitle=High-speed arcing fault detection: using the light spectrum, refAbstract=null), Reference(id=1179433904407724208, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, doi=null, pmid=null, pmcid=null, year=2021, volume=70, issue=null, pageStart=1, pageEnd=10, url=null, language=null, rfNumber=[4], rfOrder=5, authorNames=Jiang R, Bao G, Hong Q, journalName=IEEE Transactions on Instrumentation and Measurement, refType=null, unstructuredReference=Jiang R, Bao G, Hong Q, et al. A coupling method for identifying arc faults based on short-observation-window SVDR[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 1-10., articleTitle=A coupling method for identifying arc faults based on short-observation-window SVDR, refAbstract=null), Reference(id=1179433904479027377, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, doi=null, pmid=null, pmcid=null, year=2023, volume=70, issue=2, pageStart=2026, pageEnd=2036, url=null, language=null, rfNumber=[5], rfOrder=6, authorNames=Jiang R, Zheng Y, journalName=IEEE Transactions on Industrial Electronics, refType=null, unstructuredReference=Jiang R, Zheng Y. Series arc fault detection using regular signals and time-series reconstruction[J]. IEEE Transactions on Industrial Electronics, 2023, 70(2): 2026-2036., articleTitle=Series arc fault detection using regular signals and time-series reconstruction, refAbstract=null), Reference(id=1179433904537747634, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=3, pageStart=141, pageEnd=149, url=null, language=null, rfNumber=[6], rfOrder=7, authorNames=张婷, 王海淇, 张认成, journalName=仪器仪表学报, refType=null, unstructuredReference=张婷, 王海淇, 张认成, 等. 基于自归一化神经网络的电弧故障检测方法[J]. 仪器仪表学报, 2021, 42(3): 141-149., articleTitle=基于自归一化神经网络的电弧故障检测方法, refAbstract=null), Reference(id=1179433904600662195, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=3, pageStart=141, pageEnd=149, url=null, language=null, rfNumber=[6], rfOrder=8, authorNames=Zhang Ting, Wang Haiqi, Zhang Rencheng, journalName=Chinese Journal of Scientific Instrument, refType=null, unstructuredReference=Zhang Ting, Wang Haiqi, Zhang Rencheng, et al. Arc fault detection method based on self-normalizing neural network[J]. Chinese Journal of Scientific Instrument, 2021, 42(3): 141-149., articleTitle=Arc fault detection method based on self-normalizing neural network, refAbstract=null), Reference(id=1179433904676159668, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, doi=null, pmid=null, pmcid=null, year=2019, volume=15, issue=12, pageStart=6210, pageEnd=6219, url=null, language=null, rfNumber=[7], rfOrder=9, authorNames=Wang Y, Zhang F, Zhang X, journalName=IEEE Transactions on Industrial Informatics, refType=null, unstructuredReference=Wang Y, Zhang F, Zhang X, et al. Series AC arc fault detection method based on hybrid time and frequency analysis and fully connected neural network[J]. IEEE Transactions on Industrial Informatics, 2019, 15(12): 6210-6219., articleTitle=Series AC arc fault detection method based on hybrid time and frequency analysis and fully connected neural network, refAbstract=null), Reference(id=1179433904751657141, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, doi=null, pmid=null, pmcid=null, year=2023, volume=220, issue=null, pageStart=109286, pageEnd=null, url=null, language=null, rfNumber=[8], rfOrder=10, authorNames=Meng Y, Yang Q, Chen S L, journalName=Electrical Power System, refType=null, unstructuredReference=Meng Y, Yang Q, Chen S L, et al. Multi-branch AC arc fault detection based on ICEEMDAN and LightGBM algorithm[J]. Electrical Power System, 2023, 220: 109286., articleTitle=Multi-branch AC arc fault detection based on ICEEMDAN and LightGBM algorithm, refAbstract=null), Reference(id=1179433904806183094, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, doi=null, pmid=null, pmcid=null, year=2022, volume=18, issue=1, pageStart=77, pageEnd=86, url=null, language=null, rfNumber=[9], rfOrder=11, authorNames=Wang Y, Hou L, Paul K C, journalName=IEEE Transactions on Industrial Informatics, refType=null, unstructuredReference=Wang Y, Hou L, Paul K C, et al. ArcNet: series AC arc fault detection based on raw current and convolutional neural network[J]. IEEE Transactions on Industrial Informatics, 2022, 18(1): 77-86., articleTitle=ArcNet: series AC arc fault detection based on raw current and convolutional neural network, refAbstract=null), Reference(id=1179433904877486263, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=13, pageStart=5626, pageEnd=5633, url=null, language=null, rfNumber=[10], rfOrder=12, authorNames=戴洪德, 张志亮, 崔伟成, journalName=科学技术与工程, refType=null, unstructuredReference=戴洪德, 张志亮, 崔伟成, 等. 基于SSA-SVM的航空电弧故障检测[J]. 科学技术与工程, 2024, 24(13): 5626-5633., articleTitle=基于SSA-SVM的航空电弧故障检测, refAbstract=null), Reference(id=1179433904936206520, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=13, pageStart=5626, pageEnd=5633, url=null, language=null, rfNumber=[10], rfOrder=13, authorNames=Dai Hongde, Zhang Zhiliang, Cui Weicheng, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Dai Hongde, Zhang Zhiliang, Cui Weicheng, et al. Arc fault detection in aviation based on SSA-SVM[J]. Science Technology and Engineering, 2024, 24(13): 5626-5633., articleTitle=Arc fault detection in aviation based on SSA-SVM, refAbstract=null), Reference(id=1179433904999121081, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, doi=null, pmid=null, pmcid=null, year=2024, volume=43, issue=5, pageStart=58, pageEnd=67, url=null, language=null, rfNumber=[11], rfOrder=14, authorNames=李岩, 刘鑫月, 乔俊杰, journalName=电工电能新技术, refType=null, unstructuredReference=李岩, 刘鑫月, 乔俊杰, 等. 基于1DCNN和D-S多信息融合的光伏系统直流母线串联电弧故障检测[J]. 电工电能新技术, 2024, 43(5): 58-67., articleTitle=基于1DCNN和D-S多信息融合的光伏系统直流母线串联电弧故障检测, refAbstract=null), Reference(id=1179433905053647034, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, doi=null, pmid=null, pmcid=null, year=2024, volume=43, issue=5, pageStart=58, pageEnd=67, url=null, language=null, rfNumber=[11], rfOrder=15, authorNames=Li Yan, Liu Xinyue, Qiao Junjie, journalName=Advanced Technology of Electrical Engineering and Energy, refType=null, unstructuredReference=Li Yan, Liu Xinyue, Qiao Junjie, et al. Detection of series arc faults in dc bus of photovoltaic systems based on 1DCNN and D-S multi-information fusion[J]. Advanced Technology of Electrical Engineering and Energy, 2024, 43(5): 58-67., articleTitle=Detection of series arc faults in dc bus of photovoltaic systems based on 1DCNN and D-S multi-information fusion, refAbstract=null), Reference(id=1179433905116561595, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, doi=null, pmid=null, pmcid=null, year=2022, volume=10, issue=null, pageStart=106958, pageEnd=106971, url=null, language=null, rfNumber=[12], rfOrder=16, authorNames=Liu X, Huang D, Jing T, journalName=IEEE Access, refType=null, unstructuredReference=Liu X, Huang D, Jing T, et al. Detection of AC arc faults of aviation cables based on H-I-W three-dimensional features and CNN-LSTM neural network[J]. IEEE Access, 2022, 10: 106958-106971., articleTitle=Detection of AC arc faults of aviation cables based on H-I-W three-dimensional features and CNN-LSTM neural network, refAbstract=null), Reference(id=1179433905183670460, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, doi=null, pmid=null, pmcid=null, year=2022, volume=71, issue=null, pageStart=1, pageEnd=14, url=null, language=null, rfNumber=[13], rfOrder=17, authorNames=Riba J R, Moreno-Eguilaz M, Ortega J A, journalName=IEEE Transactions on Instrumentation and Measurement, refType=null, unstructuredReference=Riba J R, Moreno-Eguilaz M, Ortega J A. Arc fault protections for aeronautic applications: a review identifying the effects, detection methods, current progress, limitations, future challenges, and research needs[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 1-14., articleTitle=Arc fault protections for aeronautic applications: a review identifying the effects, detection methods, current progress, limitations, future challenges, and research needs, refAbstract=null), Reference(id=1179433905242390717, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, doi=null, pmid=null, pmcid=null, year=2025, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=18, authorNames=火久元, 李昕, 常琛, journalName=北京航空航天大学学报, refType=null, unstructuredReference=火久元, 李昕, 常琛, 等. 基于多尺度特征融合的滚动轴承寿命预测[J]. 北京航空航天大学学报, 2025.DOI: 10.13700/j.bh.1001-5965.2024.0161., articleTitle=基于多尺度特征融合的滚动轴承寿命预测, refAbstract=null), Reference(id=1179433905301110974, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, doi=null, pmid=null, pmcid=null, year=2025, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=19, authorNames=Huo Jiuyuan, Li Xin, Chang Chen, journalName=Journal of Beijing University of Aeronautics and Astronautics, refType=null, unstructuredReference=Huo Jiuyuan, Li Xin, Chang Chen, et al. Rolling bearing life prediction based on multi-scale feature fusion[J]. Journal of Beijing University of Aeronautics and Astronautics, 2025.DOI: 10.13700/j.bh.1001-5965.2024.0161., articleTitle=Rolling bearing life prediction based on multi-scale feature fusion, refAbstract=null), Reference(id=1179433905368219839, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, doi=null, pmid=null, pmcid=null, year=2023, volume=70, issue=5, pageStart=4875, pageEnd=4886, url=null, language=null, rfNumber=[15], rfOrder=20, authorNames=Miao W, Wang Z, Wang F, journalName=IEEE Transactions on Industrial Electronics, refType=null, unstructuredReference=Miao W, Wang Z, Wang F, et al. Multicharacteristics arc model and autocorrelation-algorithm based arc fault detector for DC microgrid[J]. IEEE Transactions on Industrial Electronics, 2023, 70(5): 4875-4886., articleTitle=Multicharacteristics arc model and autocorrelation-algorithm based arc fault detector for DC microgrid, refAbstract=null), Reference(id=1179433905443717312, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, doi=null, pmid=null, pmcid=null, year=2019, volume=15, issue=12, pageStart=6210, pageEnd=6219, url=null, language=null, rfNumber=[16], rfOrder=21, authorNames=Wang Y, Zhang F, Zhang X, journalName=IEEE Transactions on Industrial Informatics, refType=null, unstructuredReference=Wang Y, Zhang F, Zhang X, et al. Series AC arc fault detection method based on hybrid time and frequency analysis and fully connected neural network[J]. IEEE Transactions on Industrial Informatics, 2019, 15(12): 6210-6219., articleTitle=Series AC arc fault detection method based on hybrid time and frequency analysis and fully connected neural network, refAbstract=null), Reference(id=1179433905506631873, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=1, pageEnd=8, url=null, language=null, rfNumber=[17], rfOrder=22, authorNames=Liu C, Wang F, Zhuo F, journalName=22nd European Conference on Power Electronics and Applications (EPE’20 ECCE Europe), refType=null, unstructuredReference=Liu C, Wang F, Zhuo F, et al. Fault diagnosis of HVDC transmission system using wavelet energy entropy and the wavelet neural network[C]// 22nd European Conference on Power Electronics and Applications (EPE’20 ECCE Europe). New York: IEEE, 2020: 1-8., articleTitle=Fault diagnosis of HVDC transmission system using wavelet energy entropy and the wavelet neural network, refAbstract=null), Reference(id=1179433905565352130, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, doi=null, pmid=null, pmcid=null, year=2021, volume=9, issue=null, pageStart=68985, pageEnd=69001, url=null, language=null, rfNumber=[18], rfOrder=23, authorNames=Ronald M, Poulose A, Han D S, journalName=IEEE Access, refType=null, unstructuredReference=Ronald M, Poulose A, Han D S. iSPLInception: an inception-ResNet deep learning architecture for human activity recognition[J]. IEEE Access, 2021, 9: 68985-69001., articleTitle=iSPLInception: an inception-ResNet deep learning architecture for human activity recognition, refAbstract=null), Reference(id=1179433905619878083, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=216, pageEnd=null, url=null, language=null, rfNumber=[19], rfOrder=24, authorNames=Mim T R, Amatullah M, Afreen S, journalName=Expert Systems with Applications, refType=null, unstructuredReference=Mim T R, Amatullah M, Afreen S, et al. GRU-INC: an inception-attention based approach using GRU for human activityrecognition[J]. Expert Systems with Applications, 2023, 216.DOI: 10.1016/j.eswa.2022.119419., articleTitle=GRU-INC: an inception-attention based approach using GRU for human activityrecognition, refAbstract=null), Reference(id=1179433905695375556, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, doi=null, pmid=null, pmcid=null, year=2025, volume=null, issue=null, pageStart=null, pageEnd=null, url=http://kns.cnki.net/kcms/detail/11.2107.TM.20231213.1111.002.html, language=null, rfNumber=[20], rfOrder=25, authorNames=孟宏宇, 张建良, 蔡兆龙, journalName=中国电机工程学报, refType=null, unstructuredReference=孟宏宇, 张建良, 蔡兆龙, 等. 基于CNN-BiLSTM-Attention的直流微电网故障诊断研究[J/OL]. [2025-02-25]. 中国电机工程学报. http://kns.cnki.net/kcms/detail/11.2107.TM.20231213.1111.002.html, articleTitle=基于CNN-BiLSTM-Attention的直流微电网故障诊断研究, refAbstract=null), Reference(id=1179433905770873029, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, doi=null, pmid=null, pmcid=null, year=2025, volume=null, issue=null, pageStart=null, pageEnd=null, url=http://kns.cnki.net/kcms/detail/11.2107.TM.20231213.1111.002.html, language=null, rfNumber=[20], rfOrder=26, authorNames=Meng Hongyu, Zhang Jianliang, Cai Zhaolong, journalName=Proceedings of the Chinese Society for Electrical Engineering, refType=null, unstructuredReference=Meng Hongyu, Zhang Jianliang, Cai Zhaolong, et al. Fault diagnosis of DC microgrid based on CNN-BiLSTM-attention[J/OL]. [2025-02-25]. Proceedings of the Chinese Society for Electrical Engineering. http://kns.cnki.net/kcms/detail/11.2107.TM.20231213.1111.002.html, articleTitle=Fault diagnosis of DC microgrid based on CNN-BiLSTM-attention, refAbstract=null), Reference(id=1179433905871536326, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, doi=null, pmid=null, pmcid=null, year=2024, volume=41, issue=11, pageStart=1977, pageEnd=1985, url=null, language=null, rfNumber=[21], rfOrder=27, authorNames=张印文, 王琳霖, 薛文科, journalName=机电工程, refType=null, unstructuredReference=张印文, 王琳霖, 薛文科, 等. ConvNeXt网络及Stacked BiLSTM-Self-Attention在轴承剩余寿命预测中的应用[J]. 机电工程, 2024, 41(11): 1977-1985, 1994., articleTitle=ConvNeXt网络及Stacked BiLSTM-Self-Attention在轴承剩余寿命预测中的应用, refAbstract=null), Reference(id=1179433905963811015, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, doi=null, pmid=null, pmcid=null, year=2024, volume=41, issue=11, pageStart=1977, pageEnd=1985, url=null, language=null, rfNumber=[21], rfOrder=28, authorNames=Zhang Yinwen, Wang Linlin, Xue Wenke, journalName=Mechanical and Electrical Engineering, refType=null, unstructuredReference=Zhang Yinwen, Wang Linlin, Xue Wenke, et al. Application of ConvNeXt network and stacked BiLSTM-Self-Attention in remaining life prediction of bearings[J]. Mechanical and Electrical Engineering, 2024, 41(11): 1977-1985, 1994., articleTitle=Application of ConvNeXt network and stacked BiLSTM-Self-Attention in remaining life prediction of bearings, refAbstract=null), Reference(id=1179433906026725576, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, doi=null, pmid=null, pmcid=null, year=2021, volume=11, issue=null, pageStart=1, pageEnd=8, url=null, language=null, rfNumber=[22], rfOrder=29, authorNames=Chahal H, Toner H, Rahkovsky I, journalName=Center for Security and Emerging Technology, refType=null, unstructuredReference=Chahal H, Toner H, Rahkovsky I. Small data's big AIpotential[J]. Center for Security and Emerging Technology, 2021, 11: 1-8., articleTitle=Small data's big AIpotential, refAbstract=null), Reference(id=1179433906093834441, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=1, pageEnd=4, url=null, language=null, rfNumber=[23], rfOrder=30, authorNames=Emrani A, Pourhomayoun M, journalName=IEEE 18th Workshop on Control and Modeling for Power Electro-nics (COMPEL), refType=null, unstructuredReference=Emrani A, Pourhomayoun M. Applying machine learning techniques to recognize arc in vehicle 48 electrical systems[C]// IEEE 18th Workshop on Control and Modeling for Power Electro-nics (COMPEL). New York: IEEE, 2017: 1-4., articleTitle=Applying machine learning techniques to recognize arc in vehicle 48 electrical systems, refAbstract=null)], funds=[Fund(id=1179433903816327338, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, awardId=3122018D009, language=CN, fundingSource=中央高校基本科研业务中国民航大学专项基金(3122018D009), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1179433899793989739, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, xref=null, ext=[AuthorCompanyExt(id=1179433899798184044, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, companyId=1179433899793989739, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. Emgineer Techniques Training Center,Civil Aviation University of China, Tianjin 300300, China), AuthorCompanyExt(id=1179433899806572653, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, companyId=1179433899793989739, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. 中国民航大学工程技术训练中心, 天津 300300)]), AuthorCompany(id=1179433899869487214, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, xref=null, ext=[AuthorCompanyExt(id=1179433899877875823, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, companyId=1179433899869487214, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2. College of Electronic Information and Automation,Civil Aviation University of China, Tianjin 300300, China), AuthorCompanyExt(id=1179433899886264432, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, companyId=1179433899869487214, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2. 中国民航大学电子信息与自动化学院, 天津 300300)])], figs=[ArticleFig(id=1179433900976783492, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=EN, label=Fig.1, caption=Vibration test circuit, figureFileSmall=AuR/V3ytFji+eoeN5i4xww==, figureFileBig=Aa9Ocg8e3Du3W3LbVjyviA==, tableContent=null), ArticleFig(id=1179433901060669573, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=CN, label=图1, caption=振动试验电路, figureFileSmall=AuR/V3ytFji+eoeN5i4xww==, figureFileBig=Aa9Ocg8e3Du3W3LbVjyviA==, tableContent=null), ArticleFig(id=1179433901111001222, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=EN, label=Fig.2, caption=Stress test circuit, figureFileSmall=iytNaACq66hsZZBXfxyOlg==, figureFileBig=Eq5LRkuSTXlokHCXYU2SGQ==, tableContent=null), ArticleFig(id=1179433901165527175, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=CN, label=图2, caption=应力实验电路, figureFileSmall=iytNaACq66hsZZBXfxyOlg==, figureFileBig=Eq5LRkuSTXlokHCXYU2SGQ==, tableContent=null), ArticleFig(id=1179433901236830344, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=EN, label=Fig.3, caption=Wet cable test circuit, figureFileSmall=Y8SvGO4LMJ6SI6aJdEj35g==, figureFileBig=p3CRZv3464HUP2Cvd7e6tw==, tableContent=null), ArticleFig(id=1179433901295550601, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=CN, label=图3, caption=潮湿电缆实验电路, figureFileSmall=Y8SvGO4LMJ6SI6aJdEj35g==, figureFileBig=p3CRZv3464HUP2Cvd7e6tw==, tableContent=null), ArticleFig(id=1179433901383630986, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=EN, label=Fig.4, caption=Partial sampling current, figureFileSmall=r649fWiRjgZp559wUoAHBQ==, figureFileBig=tCosBkLRoqOITn6auWzqmA==, tableContent=null), ArticleFig(id=1179433901459128459, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=CN, label=图4, caption=部分采样电流, figureFileSmall=r649fWiRjgZp559wUoAHBQ==, figureFileBig=tCosBkLRoqOITn6auWzqmA==, tableContent=null), ArticleFig(id=1179433901534625932, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=EN, label=Fig.5, caption=Inception structure, figureFileSmall=RvEoNcPvDPjjeZRYoNIMcw==, figureFileBig=JJI/hUnbuYYB2uoQ4cA4RA==, tableContent=null), ArticleFig(id=1179433901622706317, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=CN, label=图5, caption=Inception结构, figureFileSmall=RvEoNcPvDPjjeZRYoNIMcw==, figureFileBig=JJI/hUnbuYYB2uoQ4cA4RA==, tableContent=null), ArticleFig(id=1179433901681426574, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=EN, label=Fig.6, caption=BiLSTM structure, figureFileSmall=ngi4VQD4s0Gk08cfMXeSGA==, figureFileBig=lDRQ3Zfr2K3DPKtLeXXMiw==, tableContent=null), ArticleFig(id=1179433901740146831, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=CN, label=图6, caption=BiLSTM结构, figureFileSmall=ngi4VQD4s0Gk08cfMXeSGA==, figureFileBig=lDRQ3Zfr2K3DPKtLeXXMiw==, tableContent=null), ArticleFig(id=1179433901803061392, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=EN, label=Fig.7, caption=Inception-BiLSTM diagnostics network, figureFileSmall=5hTqiEmZA1QGJ5gcu0QtGg==, figureFileBig=7Ljp1nEcvwq6bqYYraTuUQ==, tableContent=null), ArticleFig(id=1179433901874364561, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=CN, label=图7, caption=Inception-BiLSTM诊断网络, figureFileSmall=5hTqiEmZA1QGJ5gcu0QtGg==, figureFileBig=7Ljp1nEcvwq6bqYYraTuUQ==, tableContent=null), ArticleFig(id=1179433901945667730, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=EN, label=Fig.8, caption=Arc fault diagnosis model, figureFileSmall=qELw91Jimu7HSMDybSOjqw==, figureFileBig=kPPl4KJnHXBaU8x54OikYA==, tableContent=null), ArticleFig(id=1179433902008582291, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=CN, label=图8, caption=电弧故障诊断模型, figureFileSmall=qELw91Jimu7HSMDybSOjqw==, figureFileBig=kPPl4KJnHXBaU8x54OikYA==, tableContent=null), ArticleFig(id=1179433902071496852, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=EN, label=Fig.9, caption=Scatter plot of discrete sum of squares of the autocorrelation coefficients, figureFileSmall=6BEe6CywsJnm+uQKnX/BsQ==, figureFileBig=alwZW3fM0DF5ERdKf3iQQA==, tableContent=null), ArticleFig(id=1179433902138605717, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=CN, label=图9, caption=自相关系数的离散平方和散点图, figureFileSmall=6BEe6CywsJnm+uQKnX/BsQ==, figureFileBig=alwZW3fM0DF5ERdKf3iQQA==, tableContent=null), ArticleFig(id=1179433902209908886, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=EN, label=Fig.10, caption=Scatter plot of Shannon entropy, figureFileSmall=ta9nuxWjxaNoj5WgE+9CSA==, figureFileBig=Sd+v7qyVRGWiKH5wfSN2Fg==, tableContent=null), ArticleFig(id=1179433902260240535, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=CN, label=图10, caption=香农熵特征散点图, figureFileSmall=ta9nuxWjxaNoj5WgE+9CSA==, figureFileBig=Sd+v7qyVRGWiKH5wfSN2Fg==, tableContent=null), ArticleFig(id=1179433902314766488, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=EN, label=Fig.11, caption=Scatter plot of wavelet energy entropy, figureFileSmall=AwZ4xHAF22sJy/MBRdXQuA==, figureFileBig=YHeMdFfHJYbPPpeNP3YL8Q==, tableContent=null), ArticleFig(id=1179433902377681049, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=CN, label=图11, caption=小波能量熵特征散点图, figureFileSmall=AwZ4xHAF22sJy/MBRdXQuA==, figureFileBig=YHeMdFfHJYbPPpeNP3YL8Q==, tableContent=null), ArticleFig(id=1179433902432207002, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=EN, label=Fig.12, caption=Arc fault diagnosis model flow chart, figureFileSmall=hyX2a1oH7HltrByxBZu2LQ==, figureFileBig=Yn+hXxKQk7jMsVUN47ULnw==, tableContent=null), ArticleFig(id=1179433902495121563, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=CN, label=图12, caption=电弧故障诊断模型流程图, figureFileSmall=hyX2a1oH7HltrByxBZu2LQ==, figureFileBig=Yn+hXxKQk7jMsVUN47ULnw==, tableContent=null), ArticleFig(id=1179433902545453212, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=EN, label=Fig.13, caption=Accuracy and loss of training set, figureFileSmall=g0dPyIXtN6X3oGdjTb4V5w==, figureFileBig=zVZN6SKdW2DcxqEycF5UDQ==, tableContent=null), ArticleFig(id=1179433902604173469, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=CN, label=图13, caption=训练集准确率和损失, figureFileSmall=g0dPyIXtN6X3oGdjTb4V5w==, figureFileBig=zVZN6SKdW2DcxqEycF5UDQ==, tableContent=null), ArticleFig(id=1179433902667088030, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=EN, label=Fig.14, caption=Confusion matrix of predicted results, figureFileSmall=6w/jDAIUwQ5A3RwVlKxXYw==, figureFileBig=KYdFltp7GRLVpb6281vMNg==, tableContent=null), ArticleFig(id=1179433902721613983, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=CN, label=图14, caption=预测结果的混淆矩阵, figureFileSmall=6w/jDAIUwQ5A3RwVlKxXYw==, figureFileBig=KYdFltp7GRLVpb6281vMNg==, tableContent=null), ArticleFig(id=1179433902788722848, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=EN, label=Fig.15, caption=Training curves for different models, figureFileSmall=e4pOZY+zd3Z+e2W/V4w4dQ==, figureFileBig=htRbgLPoUga3KFrDJRTbBA==, tableContent=null), ArticleFig(id=1179433902855831713, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=CN, label=图15, caption=不同模型的训练曲线, figureFileSmall=e4pOZY+zd3Z+e2W/V4w4dQ==, figureFileBig=htRbgLPoUga3KFrDJRTbBA==, tableContent=null), ArticleFig(id=1179433902914551970, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=EN, label=Table 1, caption=

Inception-BiLSTM network parameters

, figureFileSmall=null, figureFileBig=null, tableContent=
网络机构 参数 网络机构 参数
卷积层1 1×1 BiLSTM 128
卷积层2 1×3 全连接层1 64
卷积层3 1×5 全连接层2 32
卷积层4 1×4 全连接层3 16
池化层 1×1
), ArticleFig(id=1179433902985855139, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=CN, label=表1, caption=

Inception-BiLSTM网络参数

, figureFileSmall=null, figureFileBig=null, tableContent=
网络机构 参数 网络机构 参数
卷积层1 1×1 BiLSTM 128
卷积层2 1×3 全连接层1 64
卷积层3 1×5 全连接层2 32
卷积层4 1×4 全连接层3 16
池化层 1×1
), ArticleFig(id=1179433903107489956, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=EN, label=Table 2, caption=

The predictions of different models

, figureFileSmall=null, figureFileBig=null, tableContent=
检测模型 模型损失 准确率
CNN 0.256 2 0.917 2
CNN-LSTM 0.270 3 0.908 1
CNN-LSTM-BiLSTM 0.014 1 0.994 6
CNN-BiLSTM 0.038 9 0.990 6
Inception-BiLSTM 0.014 8 0.996 9
), ArticleFig(id=1179433903182987429, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=CN, label=表2, caption=

不同模型的预测结果

, figureFileSmall=null, figureFileBig=null, tableContent=
检测模型 模型损失 准确率
CNN 0.256 2 0.917 2
CNN-LSTM 0.270 3 0.908 1
CNN-LSTM-BiLSTM 0.014 1 0.994 6
CNN-BiLSTM 0.038 9 0.990 6
Inception-BiLSTM 0.014 8 0.996 9
), ArticleFig(id=1179433903254290598, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=EN, label=Table 3, caption=

The diagnostic results of the model under different data

, figureFileSmall=null, figureFileBig=null, tableContent=
训练集∶
测试集
检测时间/ms 模型损失 准确率
特征
数据
原始
数据
特征数据 原始数据 特征数据 原始数据
5∶5 4 12 0.011 5 0.427 2 0.995 0 0.847 5
6∶4 4 12 0.010 7 0.069 8 0.996 9 0.990 1
7∶3 4 12 0.014 6 0.061 5 0.995 8 0.989 6
8∶2 4 13 0.014 8 0.190 3 0.997 2 0.987 5
9∶1 5 13 0.053 0 0.356 8 0.995 7 0.887 5
), ArticleFig(id=1179433903333982375, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=CN, label=表3, caption=

不同数据下模型的诊断结果

, figureFileSmall=null, figureFileBig=null, tableContent=
训练集∶
测试集
检测时间/ms 模型损失 准确率
特征
数据
原始
数据
特征数据 原始数据 特征数据 原始数据
5∶5 4 12 0.011 5 0.427 2 0.995 0 0.847 5
6∶4 4 12 0.010 7 0.069 8 0.996 9 0.990 1
7∶3 4 12 0.014 6 0.061 5 0.995 8 0.989 6
8∶2 4 13 0.014 8 0.190 3 0.997 2 0.987 5
9∶1 5 13 0.053 0 0.356 8 0.995 7 0.887 5
), ArticleFig(id=1179433903484977320, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=EN, label=Table 4, caption=

Performance results of different diagnosis models

, figureFileSmall=null, figureFileBig=null, tableContent=
诊断模型 准确率 召回率 检测时间/ms
本文模型 0.996 9 0.978 6 5
PCA-SVM(PSO) 0.938 0 0.938 0 2 135
特征提取+随机森林[23] 0.982 9 0.982 9 390
), ArticleFig(id=1179433903564669097, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769466151612831, language=CN, label=表4, caption=

不同诊断模型的性能结果

, figureFileSmall=null, figureFileBig=null, tableContent=
诊断模型 准确率 召回率 检测时间/ms
本文模型 0.996 9 0.978 6 5
PCA-SVM(PSO) 0.938 0 0.938 0 2 135
特征提取+随机森林[23] 0.982 9 0.982 9 390
)], 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.1671-1815.2404712, detailUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2404712, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/PDF/10.12404/j.issn.1671-1815.2404712, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/PDF/10.12404/j.issn.1671-1815.2404712, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于Inception-BiLSTM的航空电缆电弧故障检测
收藏切换
PDF下载
刘岱 1 , 李晨辉 2
科学技术与工程 | 论文·航空、航天 2025,25(14): 6100-6108
收起
收藏切换
科学技术与工程 | 论文·航空、航天 2025, 25(14): 6100-6108
基于Inception-BiLSTM的航空电缆电弧故障检测
全屏
刘岱1 , 李晨辉2
作者信息
  • 1. 中国民航大学工程技术训练中心, 天津 300300
  • 2. 中国民航大学电子信息与自动化学院, 天津 300300
  • 刘岱(1981—),男,汉族,天津人,硕士,讲师。研究方向:航空器维修及适航审定技术。E-mail:

Aviation Cable Arc Fault Detection Based on Inception-BiLSTM
Dai LIU1 , Chen-hui LI2
Affiliations
  • 1. Emgineer Techniques Training Center,Civil Aviation University of China, Tianjin 300300, China
  • 2. College of Electronic Information and Automation,Civil Aviation University of China, Tianjin 300300, China
出版时间: 2025-05-18 doi: 10.12404/j.issn.1671-1815.2404712
文章导航
收藏切换

针对航空电缆电弧故障引起的微小电流变化难以识别的问题,提出了一种基于Inception模块和双向长短期记忆网络(bidirectional long short-term memory,BiLSTM)的交流串联电弧故障诊断方法。首先通过计算自相关系数的离散平方和(discrete sum of squares of the atocorrelation coefficient)、信息熵(Shannon entropy)以及小波能量熵(wavelet energy entropy)提取原始电流数据的特征,将特征合并形成新的特征矩阵,对原始数据实现特征增强。之后Inception-BiLSTM网络利用特征矩阵进行学习,最后完成对电弧故障的诊断。为了验证模型在实际环境中的诊断性能,在充分考虑实际情况下,基于航空电缆电弧模拟实验平台进行了振动试验、应力实验以及潮湿电缆实验,并将实验数据整合作为检测样本。实验结果表明,本文方法对于识别电弧故障有着较高的准确度,可以达到99.69%。

Inception模块  /  双向长短期记忆网络  /  航空电缆电弧故障  /  特征提取

A method for diagnosing AC series arc faults based on the Inception module and BiLSTM (bidirectional long short-term memory) was proposed to address the challenge of identifying small current changes caused by arc faults in aviation cables. First, features of the raw current data were extracted by calculating the discrete sum of squares of the autocorrelation coefficient, Shannon entropy, and wavelet energy entropy. These features are then combined to form a new feature matrix, enhancing the original data's feature representation. Subsequently, the Inception-BiLSTM network learns from the feature matrix and ultimately completes the arc fault diagnosis. To validate the diagnostic performance of the model in practical environments, a series of experiments were conducted, including vibration tests, stress tests, and wet cable tests, based on an aviation cable arc fault simulation platform, with the experimental data being integrated as detection samples. The experimental results show that the proposed method achieves a high accuracy rate of 99.69% in identifying arc faults.

inception module  /  BiLSTM  /  aviation cable arc fault  /  features extraction
刘岱, 李晨辉. 基于Inception-BiLSTM的航空电缆电弧故障检测. 科学技术与工程, 2025 , 25 (14) : 6100 -6108 . DOI: 10.12404/j.issn.1671-1815.2404712
Dai LIU, Chen-hui LI. Aviation Cable Arc Fault Detection Based on Inception-BiLSTM[J]. Science Technology and Engineering, 2025 , 25 (14) : 6100 -6108 . DOI: 10.12404/j.issn.1671-1815.2404712
随着飞机机龄的增加,电气系统线缆长期负载或过载工作,易导致线缆绝缘老化或故障,出现局部放电或电弧放电[1]。飞机中线缆故障引发的故障电弧通常伴随着高温与强闪光现象,当电弧接触到电缆的绝缘层或护套时,使得线缆局部电阻和能量增加,造成机舱电气火灾,给飞机安全运行造成极大的隐患。
到目前为止,中外学者对电弧故障检测问题展开了一系列的研究。从应用层面进行分析,电弧故障检测方法大致分为两类:一种是基于物理现象的方法,这种方法通常涉及电弧产生的声、光、电等[2]。对光伏直流系统中的电弧电磁辐射脉冲信号进行分析,发现其波形幅值与电弧电流的变化率近似成正比关系,通过实验验证其有效频率范围为210~800 MHz。文献[3]提出了另一种利用光谱分析进行弧闪故障检测的新方法。研究表明,通过分析电弧事故期间铜导体和铝导体的光谱,能够提高弧闪故障检测操作的准确性和可靠性。
另一种则是在电弧故障发生的情况下,分析电流和电压的时域、频域和时频域的特征变化。当发生电弧故障时,线路的电压电流波形会产生畸变,出现波形不对称、幅值变化、并伴随着高频噪声信号产生等情况。基于耦合信号高频脉冲分量的方法被用于识别住宅建筑中的交流串联电弧故障,文献[4-5]在此方法的基础上,提出短观察窗奇异值分解法和重构算法。
近年来,随着人工智能技术的发展,机器学习和深度学习等技术因其对复杂信号的优异处理能力也逐渐被引入电弧检测研究中。文献[6]通过对故障电弧的时域分析,引用归一化卷积神经网络,优化了传统神经网络在电弧故障识别上的不足,提高了一定的检测精度,但仍有不小提升空间。文献[7]利用电弧电流的高频特性以及全连接神经网络,设计了精细化区分不同负载对应的电弧故障的方法,减低了计算成本。文献[8]利用改进的经验模态分解方法分析电弧电流,并通过Boruta和LightGBM(light gradient boosting machine)算法来降低特征维数,利用决策树完成了对电弧故障的分类和检测。文献[9]设计了一种基于卷积神经网络的电弧检测模型,通过调整卷积网络的结构平衡了计算时间和精度,可以利用原始电流数据对电弧故障进行较高准确率的检测。文献[10]提出一种基于麻雀优化算法(sparrow search algorithm, SSA)优化支持向量机(support vector machine, SVM)的航空电弧故障检测方法,从信号无序度角度提取能量熵、模糊熵与近似熵构造特征向量,利用构造的特征向量完成了对航空电弧的故障诊断。文献[11]则提出基于一维卷积神经网络(convolutional neural network, CNN)和D-S(dempster-shafer)证据理论的故障检测方法,该方法使用1DCNN对并联电容器电流和电压信号进行电弧识别,并将基于单个传感数据的识别结果作为证据,运用D-S理论计算信度分配最终利用决策规则判断是否发生串联电弧故障。
综上所述,现提出一种inception-BiLSTM模型,对含有电弧故障的航空电缆电流检测数据进行故障诊断。利用自相关系数的离散平方和、小波能量熵以及信息熵三种特征对原始电流进行特征增强,利用Inception-BiLSTM网络捕捉特征数据中的时空信息,实现航空电缆电弧故障的诊断。
航空电缆作为民航飞机系统中的重要组成部分,负责传输电力、信号和数据等。由于其应用环境的恶劣和复杂,传统的点接触实验很难模拟电弧出现的真实环境,在考虑了电弧出现的各种原因,包括机械损伤、环境因素和电气等原因[12]。在相同的电源电压和负载类型下,本次实验基于航空电缆电弧模拟实验平台进行试验,最终选择了振动试验、应力实验以及潮湿电缆实验。具体电路设计如下。振动实验电路如图1所示,振动装置不断振动接线端子使得线路处在间接性接触的情况。应力实验电路如图2所示,其中利用金属块来对电缆进行挤压。潮湿电缆实验的电路如图3所示,实验电缆部分被切除部分外部胶皮,由滴水装置向电缆裸露处滴水。
该实验基于电弧故障断路器标准UL1699和航空标准SAE AS5692A[13]搭建,具体的模拟环境如下。
(1)试验台和振动控制装置一起振动,来模拟电缆的间接性接触,模拟连接器松动。
(2)切割实验利用金属块挤压电缆模拟电缆被外部坚硬物体挤压的情况。
(3)潮湿电缆实验以一定的速度向裸漏的电缆处滴加水滴来模拟电缆因温度变化而凝结水滴的情况。
(4)电源选择115 V/400 Hz的驱动电压和电源电压模拟飞机的电源电压。
(5)负载选用线性负载和非线性负载模拟飞机电缆连接的电器设备,其中线性负载选择灯泡,非线性负载使用电机。
最终采用电流探头采集电弧故障试验电流,每次试验截取30个周期电流,包括正常电流和故障电流,每周期6 250个采样点,最终总和采集到的三种场景下的电流数据。如图4所示是采集到的部分电流数据。
以三种电弧故障的电流数据的总和作为训练样本,以此来保证模型的泛化性。确保模型在面对不同种类的电流数据时仍可以精确的检测出故障的电流。
由于航空电缆电弧故障所引起的电流变化微小,需要大规模的电流数据进行检测。而直接利用原始信号进行检测会导致较高的计算成本的同时花费更多的时间。因此,本文研究从三个维度对原始电流信号进行特征提取。其中,利用自相关系数的离散平方和来描述信号在时域的特征,以香农熵来描述信号的混乱程度,最后以小波能量熵来描述信号的时频域特征。并将获取的特征值进行合并形成新的输入信号,从三个维度对原始电流信号进行特征从而提高模型的检测效率和泛化性[14]
相关性是信号之间的统计关系,而自相关性可以表示信号与其自身的滞后版本在连续时间间隔内的相似程度。当信号具有周期性时,自相关系数为1。对于非周期随机信号,其自相关系数为0。自相关系数的计算式为
R e ( τ ) = c o v ( X t , X t + τ ) σ X τ σ X t + τ
cov ( X t , X t + τ ) = E [ ( X t μ X t ) ( X t + τ μ X t + τ ) ]
式中:Re为自相关系数;Xtt时间内的电弧电流信号;τ为时间间隔;E为数学期望;μσ分别为X的期望值和标准差。
μ X = E ( X ) σ X 2 = E ( X 2 ) - E 2 ( X )可以推出式(3)和式(4)。
R e ( τ ) = E ( X t X t + τ ) - E ( X t ) ( X t + τ ) E ( X t 2 ) - E 2 ( X t ) E ( X t + τ 2 ) - E 2 ( X t + τ )
D = t = 1 n R e ( τ ) 2
式中:D为自相关系数的离散平方和。
与现有的故障检测方法中常用的快速傅里叶变化相比[15],自相关算法具有较低的时间复杂度,此外自相关算法可以区分粉红噪声和白噪声,通过计算D来更准确地区分正常电流和故障电流。由于航空电缆电流为交流电,其电流具有周期性,故障电流的变化在周期内可能微小但显著。通过对电流信号进行周期划分,可以将每个周期内的电流变化单独提取出来,有助于分析周期内的细微变化。而自相关系数能够捕捉到周期内电流的特征变化。对于故障电流,由于其在周期内的变化与正常电流不同,自相关函数将会显示出明显的差异。而通过对自相关函数进行平方求和,可以增强周期内电流变化的特征,使得故障特征更加显著。以此来有效地区分正常电流和故障电流。
由于航空电缆电弧故障发生时,电流信号的复杂度和不确定性通常会显著增加。而使用香农熵作为特征,则可以充分利用其度量信号复杂度和不确定性的特性[16]。其具体定义式为
S ( X ) = - i = 1 n p ( x i ) l o g 2 p ( x i )
式(5)中:S(X)为随机变量X的熵;p(xi)为随机变量X取值为xi的概率。
小波变换通过将信号分解成不同频率的分量来分析信号的时频特性。与传统的傅里叶变换不同,小波变换不仅能够提供频率信息,还能够提供时间信息。而小波能量熵则结合了小波变换的多分辨率分析能力和熵在度量信号复杂度方面的优势,对于分析电流信号的局部特征和整体特征有着极佳的效果[17]。其具体定义如下。
假设有一组小波系数cj,k,其中j表示尺度,k表示时间或空间坐标。
首先计算小波系数的能量Ej,k
E j , k = c j , k 2
将小波系数的能量作为概率分布,计算每个尺度下j的能量分布概率pj,k
p j , k = E j , k k = 1 N E j , k
式(7)中:N为系数个数。基于式(6)和式(7)所得使用信息熵的计算公式,计算小波能量熵W
W = - j = 1 M k = 1 N p j , k l o g 2 p j , k
其中:M为分解的子带总数。
传统的CNN网络在面对大规模的数据时为了更好地学习特征会增加网络的深度,但是其反向传播过程可能会随着层数的变化而出现梯度爆炸或梯度消失的问题,所以在处理航空电缆电流的大规模数据时选择Inception网络[18]
Inception网络本质上是将多个不同卷积核大小的卷积层进行并行运算,将并行运算的结果在通道维度上合并成新的特征图,相比于传统CNN的简单堆叠,该结构可有效解决CNN在计算大规模数据时易过拟合以及计算量大容易导致梯度爆炸或梯度消失的问题,并且从多个尺度学习数据,可以更好地挖掘出数据的特征[19]。相关的计算公式如下。
CNN的特征提取过程即卷积过程具体过程为
a j k = f ( i M j k a i k - 1 W i j k + b j k )
式(9)中: a j kj特征图神经网络第k个卷积层对应的输出; f为激活函数; b j k为偏置。
Inception网络结构相当于将不同尺度的卷积层输出拼接,其表达式为
A c o n c a t e n a t e = c o n c a t e n a t e [ k = 1 n a j k , M a x p o o l ( j ) ]
式(10)中:concatenate为通道拼接函数。
本文所使用的Inception结构如图5所示。
双向长短期记忆网络是LSTM网络的一种变体[20],它是由前向LSTM和后向LSTM组合而成。相比于LSTM网络,增强了网络的表示能力,使其能够更好地发现输入序列的特征和结构。BiLSTM网络结构如图6所示。
图6中的BiLSTM网络的计算过程为
h = L S T M ( x t , h t - 1 ) h = L S T M ( x t , h t - 1 ) y t = σ ( W y [ h , h ] ) + b y )
式(11)中:LSTM单元为传统LSTM网络计算过程; h 为时刻前向隐藏层状态; h 为后向隐藏层状态;yt为当前时间步的输出;σ为Sigmoid激活函数;Wyby分别为权重矩阵和偏置项。
BiLSTM网络结构首先利用前向的LSTM层,以正向顺序逐步读取输入序列的信息,并根据每个时间步以及前一个时间步的隐藏状态来更新当前时间步的隐藏状态。同时利用反向的LSTM层以逆向的顺序处理输入序列,从最后一个时间步开始,依次向前处理序列。最后将每个时间步的正向和逆向的隐藏状态整理连接起来形成一个综合的表示,以捕获两个方向信息的隐藏特征[21]
综合Inception模块多尺度卷积的空间特征挖掘能力以及BiLSTM网络的时间特征发掘能力。Inception-BiLSTM诊断网络可以更好地捕捉输入数据的时空特征从而提高诊断的准确度以及诊断效率。Inception-BiLSTM诊断网络的具体结构如图7所示。
网络中共使用了4种不同尺度的卷积层,其中三种用于组成Inception模块,一种用于提取Inception模块输出特征图的特征,同时对输入数据进行批归一化来提高网络的泛化能力减少过拟合的风险[22]。具体参数由表1给出,其中卷积层1×1表示卷积核的大小。
基于三维特征提取和Inception-BiLSTM的航空电缆电弧故障诊断模型如图8所示。
具体原理为:首先对输入信号进行测试集和训练集的划分,计算选择的三种特征值并合并成新的特征矩阵输入Inception网络。该网络会进行特征的多尺度提取和特征融合,之后将特征图输入BiLSTM网络进行训练最后利用Sigmod函数进行故障样本和正常样本的区分。
将获得的原始电流数据进行特征提取。利用式(4)计算电流原始数据每一个时间序列样本的自相关系数的离散平方和。同时,为了解决数据之间的差异以及加快网络收敛,同时保证能最大限度保留原始数据的特征,对处理后的数据采用数据归一化的方式来去除量纲,处理后的结果如图9所示。
通过式(5)计算计算电流原始数据每一个时间序列样本的香农熵。同样进行归一化以去除量纲,加快网络的计算速度。具体结果如图10所示。
通过式(8)计算计算电流原始数据每一个时间序列样本的小波能量熵。同样进行归一化以去除量纲。具体结果如图11所示。
图9~图11中可以看出,三种特征值在三个维度上,对原始电流数据中正常样本和故障样本进行了不同程度的区分。
本文研究基于Tensorflow框架建立组合网络模型,设置的超参数包括学习率为lr=0.001,迭代次数为W=250,使用Adam优化函数。此外,为了更好地分析电弧检测模型效果,需选择更有表达力的评估指标。故障检测问题本质上为一个二分类问题,选用交叉熵作为网络的损失函数来观测模型的预测准确度。评价指标选用准确度来对整个模型的分类能力进行性能评估。
为了确保模型能够更高的泛化性,避免过拟合,并提高模型的稳定性,将原始样本的顺序打乱,并划分为训练集以及测试集,训练集占原始数据的80%,测试集则为剩余的20%。模型训练的流程如图12所示。
基于Inception-BiLSTM电弧故障诊断模型的训练曲线如图13所示,训练后的模型在测试集上进行检验所得的混淆矩阵如图14所示。
为了进一步说明Inception-BiLSTM网络的性能,在相同的训练参数、网络结构参数和训练数据的设置下,对CNN网络、CNN-LSTM网络,CNN-BiLSTN,和CNN-LSTM-BiLSTM网络进行训练。图15所示为不同网络训练过程中准确率的变化曲线。
图15中可以看出,Inception-BiLSTM网络的训练效率显著优于其他模型,在第15轮训练后即达到较高的分类精度。同时,其训练曲线的波动幅度也显著低于其他4种模型,进一步证明了该模型在诊断效率和精度方面的优势。此外,表2中记录了训练后的5种模型在测试集上的最终预测性能。
表2中的数据可知,BiLSTM网络的引入显著提高了模型的性能。结合特征提取能力更强的Inception模块后,基于Inception-BiLSTM的模型在特征提取能力和时序特征捕捉能力方面,相比于单独的CNN和简单的堆叠模型有了显著提升。因此,综合来看,基于Inception-BiLSTM架构的故障诊断模型的性能优于其他模型。
此外,为了验证本文提出的三种特征值对模型性能的提升,采用不同的训练集和测试集比例,比较了将原始数据集直接用于模型训练和使用三种特征值合并的特征矩阵进行训练所得到的模型在验证集上的诊断结果。具体结果如表3所示。
表3中的数据可以看出,通过提取原始电流数据中的三维特征值作为Inception-BiLSTM网络的输入,相较于直接使用原始电流数据,能够获得更高的准确率和更快的训练速度,对诊断模型性能有显著提升。此外,随着训练集和测试集比例的变化,直接利用原始数据进行训练的模型准确率波动较大,最高可达0.990 1,最低可至0.847 5,表明单独使用网络结构对数据的依赖程度较大,想要获得较好的诊断性能必须选择合适的数据比例,这也导致其故障诊断性能不稳定。而利用所提出的三种特征进行预处理后所获得的输入数据能够帮助提升和稳定模型的训练效果,面对不同比例的训练样本,其最终在测试集上均表现出极高的诊断准确率,且所需训练时间更短。
综合来看,本文研究中提出的三种特征值不仅在降低了输入信号维度的同时保留了正常电流样本和故障样本之间的关键特征,还进一步提升了模型的鲁棒性和泛化能力。
针对电弧故障诊断问题,深度学习方法因其卓越的特征提取能力而受到广泛关注。然而,传统机器学习方法在某些应用场景中依然展现出良好的性能。在本文研究中,选取了两种常见的传统机器学习算法构建故障诊断模型,并与本文模型进行对比实验。以测试集上的检测结果为依据,综合记录召回率、准确率和检测时间三个指标,以更全面地评估所提模型的有效性,具体结果如表4所示。
表4中其他两种诊断模型包括PCA-SVM(PSO)模型和与参考文献[23]的随机森林模型。PCA-SVM模型首先利用PCA算法对数据进行降维,随后通过SVM进行分类,其中SVM由粒子群算法(particle swarm optimization,PSO)算法进行超参数的优化。尽管该模型通过降维降低了检测时间,并利用智能优化算法提升了SVM的性能,但在处理大规模数据时,其能力明显不及本文所采用的诊断模型。
而参考文献[23]中提出的基于随机森林的故障诊断模型则是提取了包括标注差、平均电流、最大电流等在内的12类特征值,随后采用随机森林算法进行故障识别。尽管该模型在诊断准确率和召回率上有较大的提升,但其特征提取过程需要人工干预,大量特征的提取显著增加了特征选择和数据处理的时间成本。相比之下,本文模型仅使用三类特征,特征维度更为精简。此外,实验结果表明,本文模型的检测时间也明显优于该模型,也证明了本文模型特征的选取和网络的搭建都有助于减少诊断的时间成本。
综上所述,本文模型在综合评估准确性与效率方面,相较于传统机器学习算法,展现出了更卓越的性能。
针对航空电缆电弧故障中微小电流变化无法有效识别的问题,提出了一种基于三维特征提取和Inception-BiLSTM网络的故障诊断模型。该模型有效利用大规模电缆电流数据学习电弧故障的电流特征,实现了高效的电弧故障诊断。通过研究得出以下结论。
(1)本文提出的三种特征值能够有效利用大规模电流数据区分故障样本和正常样本。将这三种特征值合并为新的特征矩阵后,相比于直接使用原始电流数据进行训练,模型的训练速度提升了8 ms,准确率提升了5.5%。
(2)模型具有较好的可扩展性。由于Inception结构具备多尺度特征提取能力,在面对更大规模数据时,可以通过扩展模型的宽度或深度来适应不同的输入数据,展现出较高的适用性。
(3)本文模型在测试集上的最终诊断准确率可达到99.69%,相比于CNN、CNN-LSTM、CNN-BiLSTM以及CNN-LSTM-BiLSTM等简单堆叠模型,故障诊断准确率有显著提升。这表明,相较于单纯的CNN网络,本文模型不仅具有较强的特征提取能力,还兼顾了BiLSTM网络在处理时间序列数据方面的优势。
  • 中央高校基本科研业务中国民航大学专项基金(3122018D009)
参考文献 引证文献
排序方式:
[1]
刘苏德, 王子昕, 靖子洋, 等. 航空线缆电弧故障引发电气火灾研究综述[J]. 电气工程学报, 2023, 18(3): 18-34.
Liu Sude, Wang Zixin, Jing Ziyang, et al. Review of research on electrical fires caused by arc faults in aviation cables[J]. Journal of Electrical Engineering, 2023, 18(3): 18-34.
[2]
王尧, 张彦风, 牛峰, 等. 光伏直流电弧电磁辐射特性分析与量方法[J]. 电工技术学报, 2019, 34(14): 2913-2921.
Wang Yao, Zhang Yanfeng, Niu Feng, et al. Analysis and measurement methods of electromagnetic radiation characteristics of photovoltaic DC arc[J]. Transactions of China Electrotechnical Society, 2019, 34(14): 2913-2921.
[3]
Zhao L, Zhou Y, Chen K L, et al. High-speed arcing fault detection: using the light spectrum[J]. IEEE Industry Applications Magazine, 2022, 26(3): 29-36.
[4]
Jiang R, Bao G, Hong Q, et al. A coupling method for identifying arc faults based on short-observation-window SVDR[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 1-10.
[5]
Jiang R, Zheng Y. Series arc fault detection using regular signals and time-series reconstruction[J]. IEEE Transactions on Industrial Electronics, 2023, 70(2): 2026-2036.
[6]
张婷, 王海淇, 张认成, 等. 基于自归一化神经网络的电弧故障检测方法[J]. 仪器仪表学报, 2021, 42(3): 141-149.
Zhang Ting, Wang Haiqi, Zhang Rencheng, et al. Arc fault detection method based on self-normalizing neural network[J]. Chinese Journal of Scientific Instrument, 2021, 42(3): 141-149.
[7]
Wang Y, Zhang F, Zhang X, et al. Series AC arc fault detection method based on hybrid time and frequency analysis and fully connected neural network[J]. IEEE Transactions on Industrial Informatics, 2019, 15(12): 6210-6219.
[8]
Meng Y, Yang Q, Chen S L, et al. Multi-branch AC arc fault detection based on ICEEMDAN and LightGBM algorithm[J]. Electrical Power System, 2023, 220: 109286.
[9]
Wang Y, Hou L, Paul K C, et al. ArcNet: series AC arc fault detection based on raw current and convolutional neural network[J]. IEEE Transactions on Industrial Informatics, 2022, 18(1): 77-86.
[10]
戴洪德, 张志亮, 崔伟成, 等. 基于SSA-SVM的航空电弧故障检测[J]. 科学技术与工程, 2024, 24(13): 5626-5633.
Dai Hongde, Zhang Zhiliang, Cui Weicheng, et al. Arc fault detection in aviation based on SSA-SVM[J]. Science Technology and Engineering, 2024, 24(13): 5626-5633.
[11]
李岩, 刘鑫月, 乔俊杰, 等. 基于1DCNN和D-S多信息融合的光伏系统直流母线串联电弧故障检测[J]. 电工电能新技术, 2024, 43(5): 58-67.
Li Yan, Liu Xinyue, Qiao Junjie, et al. Detection of series arc faults in dc bus of photovoltaic systems based on 1DCNN and D-S multi-information fusion[J]. Advanced Technology of Electrical Engineering and Energy, 2024, 43(5): 58-67.
[12]
Liu X, Huang D, Jing T, et al. Detection of AC arc faults of aviation cables based on H-I-W three-dimensional features and CNN-LSTM neural network[J]. IEEE Access, 2022, 10: 106958-106971.
[13]
Riba J R, Moreno-Eguilaz M, Ortega J A. Arc fault protections for aeronautic applications: a review identifying the effects, detection methods, current progress, limitations, future challenges, and research needs[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 1-14.
[14]
火久元, 李昕, 常琛, 等. 基于多尺度特征融合的滚动轴承寿命预测[J]. 北京航空航天大学学报, 2025.DOI: 10.13700/j.bh.1001-5965.2024.0161.
Huo Jiuyuan, Li Xin, Chang Chen, et al. Rolling bearing life prediction based on multi-scale feature fusion[J]. Journal of Beijing University of Aeronautics and Astronautics, 2025.DOI: 10.13700/j.bh.1001-5965.2024.0161.
[15]
Miao W, Wang Z, Wang F, et al. Multicharacteristics arc model and autocorrelation-algorithm based arc fault detector for DC microgrid[J]. IEEE Transactions on Industrial Electronics, 2023, 70(5): 4875-4886.
[16]
Wang Y, Zhang F, Zhang X, et al. Series AC arc fault detection method based on hybrid time and frequency analysis and fully connected neural network[J]. IEEE Transactions on Industrial Informatics, 2019, 15(12): 6210-6219.
[17]
Liu C, Wang F, Zhuo F, et al. Fault diagnosis of HVDC transmission system using wavelet energy entropy and the wavelet neural network[C]// 22nd European Conference on Power Electronics and Applications (EPE’20 ECCE Europe). New York: IEEE, 2020: 1-8.
[18]
Ronald M, Poulose A, Han D S. iSPLInception: an inception-ResNet deep learning architecture for human activity recognition[J]. IEEE Access, 2021, 9: 68985-69001.
[19]
Mim T R, Amatullah M, Afreen S, et al. GRU-INC: an inception-attention based approach using GRU for human activityrecognition[J]. Expert Systems with Applications, 2023, 216.DOI: 10.1016/j.eswa.2022.119419.
[20]
孟宏宇, 张建良, 蔡兆龙, 等. 基于CNN-BiLSTM-Attention的直流微电网故障诊断研究[J/OL]. [2025-02-25]. 中国电机工程学报. http://kns.cnki.net/kcms/detail/11.2107.TM.20231213.1111.002.html http://kns.cnki.net/kcms/detail/11.2107.TM.20231213.1111.002.html
Meng Hongyu, Zhang Jianliang, Cai Zhaolong, et al. Fault diagnosis of DC microgrid based on CNN-BiLSTM-attention[J/OL]. [2025-02-25]. Proceedings of the Chinese Society for Electrical Engineering. http://kns.cnki.net/kcms/detail/11.2107.TM.20231213.1111.002.html http://kns.cnki.net/kcms/detail/11.2107.TM.20231213.1111.002.html
[21]
张印文, 王琳霖, 薛文科, 等. ConvNeXt网络及Stacked BiLSTM-Self-Attention在轴承剩余寿命预测中的应用[J]. 机电工程, 2024, 41(11): 1977-1985, 1994.
Zhang Yinwen, Wang Linlin, Xue Wenke, et al. Application of ConvNeXt network and stacked BiLSTM-Self-Attention in remaining life prediction of bearings[J]. Mechanical and Electrical Engineering, 2024, 41(11): 1977-1985, 1994.
[22]
Chahal H, Toner H, Rahkovsky I. Small data's big AIpotential[J]. Center for Security and Emerging Technology, 2021, 11: 1-8.
[23]
Emrani A, Pourhomayoun M. Applying machine learning techniques to recognize arc in vehicle 48 electrical systems[C]// IEEE 18th Workshop on Control and Modeling for Power Electro-nics (COMPEL). New York: IEEE, 2017: 1-4.
2025年第25卷第14期
PDF下载
415
163
引用本文
BibTeX
文章信息
doi: 10.12404/j.issn.1671-1815.2404712
  • 接收时间:2024-06-24
  • 首发时间:2025-07-09
  • 出版时间:2025-05-18
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-06-24
  • 修回日期:2025-02-25
基金
中央高校基本科研业务中国民航大学专项基金(3122018D009)
作者信息
    1. 中国民航大学工程技术训练中心, 天津 300300
    2. 中国民航大学电子信息与自动化学院, 天津 300300
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2404712
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