Article(id=1149781964531655633, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149781952959574654, articleNumber=null, orderNo=null, doi=10.12404/j.issn.1671-1815.2400770, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1706198400000, receivedDateStr=2024-01-26, revisedDate=1733241600000, revisedDateStr=2024-12-04, acceptedDate=null, acceptedDateStr=null, onlineDate=1752058982260, onlineDateStr=2025-07-09, pubDate=1743091200000, pubDateStr=2025-03-28, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1752058982260, onlineIssueDateStr=2025-07-09, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1752058982260, creator=13701087609, updateTime=1752058982260, 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=3938, endPage=3944, ext={EN=ArticleExt(id=1149781964976251862, articleId=1149781964531655633, tenantId=1146029695717560320, journalId=1146123166801305609, language=EN, title=Prediction Model of Aviation Spare Parts Demand Based on PCA-IPSO-LSSVM, columnId=1156262731079607234, journalTitle=Science Technology and Engineering, columnName=Papers·Aeronautics and Astronautics, runingTitle=null, highlight=null, articleAbstract=

In order to solve the problem of poor forecasting effect due to the large number of influencing factors of aviation material consumption and small amount of sample data. A prediction model for aircraft spare parts demand based on principal component analysis (PCA), improved particle swarm optimization (IPSO), and least squares support vector machine (LSSVM) was proposed. Firstly, the principal component analysis method was used to screen the main influencing factors of aviation spare parts, and then the improved particle swarm optimization algorithm was used to optimize the least square support vector machine parameter combination, and finally the selection results and optimization parameter combination were used to complete the PCA-IPSO-LSSVM aviation spare parts demand prediction model training. The results show that compared with the other four prediction models, the PCA-IPSO-LSSVM model has the highest prediction accuracy, and the RMSE and MRE of the test set are 3.24 and 4.23%, respectively, indicating that the model has good prediction precision and fitting effect.

, correspAuthors=Hao XU, 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=Hao XU, Cai-yan TIAN, Rui-ke MAO), CN=ArticleExt(id=1149781976825159906, articleId=1149781964531655633, tenantId=1146029695717560320, journalId=1146123166801305609, language=CN, title=基于PCA-IPSO-LSSVM的航材备件需求预测模型, columnId=1156262731373208516, journalTitle=科学技术与工程, columnName=论文·航空、航天, runingTitle=null, highlight=null, articleAbstract=

为解决航材备件需求预测中,因航材消耗影响因素多,样本数据量少从而造成预测效果差等问题。提出一种基于主成分分析(principal component analysis,PCA)与改进粒子群算法(improved particle swarm optimization,IPSO)及最小二乘支持向量机(least square support vector machine,LSSVM)的航材备件需求预测模型,首先利用主成分分析法筛选出航材备件主要影响因素,然后使用改进粒子群算法优化最小二乘支持向量机参数组合,最后使用筛选结果及优化参数组合完成PCA-IPSO-LSSVM航材备件需求预测模型训练。与其他4个预测模型相比,PCA-IPSO-LSSVM模型预测精度最高,测试集的均方根误差(root mean squared error,RMSE)和平均相对误差(mean relative error,MRE)分别为3.24和4.23%,表明模型具有较好的预测精度和拟合效果。

, correspAuthors=许浩, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=BPpOxht/hFnODbcNFMSnyA==, magXml=x3UXujr7woAbd3CF19XT5w==, pdfUrl=null, pdf=ClLPK7rA351CfXhRlsyZzQ==, pdfFileSize=2378537, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=C71UyOB9bZjA1+u64nPQvA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=8rPmiOuHW+ewpHu5lbSV3A==, mapNumber=null, authorCompany=null, fund=null, authors=

许浩(1996—),男,汉族,四川德阳人,硕士,助理工程师。研究方向:人工智能模式识别、通航维修技术等。E-mail:

, authorsList=许浩, 田才艳, 毛瑞柯)}, authors=[Author(id=1251249361028596466, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=xh1714257525@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1251249361125065473, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, authorId=1251249361028596466, language=EN, stringName=Hao XU, firstName=Hao, middleName=null, lastName=XU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Aircraft Repair & Overhaul Plant, Civil Aviation Flight University of China, Guanghan 618307, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1251249361288643356, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, authorId=1251249361028596466, language=CN, stringName=许浩, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 中国民用航空飞行学院飞机修理厂, 广汉 618307, bio={"content":"

许浩(1996—),男,汉族,四川德阳人,硕士,助理工程师。研究方向:人工智能模式识别、通航维修技术等。E-mail:

"}, bioImg=null, bioContent=

许浩(1996—),男,汉族,四川德阳人,硕士,助理工程师。研究方向:人工智能模式识别、通航维修技术等。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1251249360806298321, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, xref=1, ext=[AuthorCompanyExt(id=1251249360814686931, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, companyId=1251249360806298321, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Aircraft Repair & Overhaul Plant, Civil Aviation Flight University of China, Guanghan 618307, China), AuthorCompanyExt(id=1251249360823075541, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, companyId=1251249360806298321, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国民用航空飞行学院飞机修理厂, 广汉 618307)])]), Author(id=1251249361389306665, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, 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=1251249361523524411, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, authorId=1251249361389306665, language=EN, stringName=Cai-yan TIAN, firstName=Cai-yan, middleName=null, lastName=TIAN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 Guanghan Branch, Civil Aviation Flight University of China, Guanghan 618307, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1251249361674519372, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, authorId=1251249361389306665, language=CN, stringName=田才艳, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 中国民用航空飞行学院广汉分院, 广汉 618307, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1251249360919544547, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, xref=2, ext=[AuthorCompanyExt(id=1251249360927933157, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, companyId=1251249360919544547, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Guanghan Branch, Civil Aviation Flight University of China, Guanghan 618307, China), AuthorCompanyExt(id=1251249360932127462, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, companyId=1251249360919544547, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 中国民用航空飞行学院广汉分院, 广汉 618307)])]), Author(id=1251249361796154204, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, 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=1251249361905206122, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, authorId=1251249361796154204, language=EN, stringName=Rui-ke MAO, firstName=Rui-ke, middleName=null, lastName=MAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Aircraft Repair & Overhaul Plant, Civil Aviation Flight University of China, Guanghan 618307, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1251249361980703608, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, authorId=1251249361796154204, language=CN, stringName=毛瑞柯, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 中国民用航空飞行学院飞机修理厂, 广汉 618307, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1251249360806298321, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, xref=1, ext=[AuthorCompanyExt(id=1251249360814686931, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, companyId=1251249360806298321, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Aircraft Repair & Overhaul Plant, Civil Aviation Flight University of China, Guanghan 618307, China), AuthorCompanyExt(id=1251249360823075541, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, companyId=1251249360806298321, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国民用航空飞行学院飞机修理厂, 广汉 618307)])])], keywords=[Keyword(id=1251249362194613140, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, language=EN, orderNo=1, keyword=aviation material demand prediction), Keyword(id=1251249362299470750, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, language=EN, orderNo=2, keyword=principal component analysis), Keyword(id=1251249362500797359, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, language=EN, orderNo=3, keyword=improved particle swarm optimization), Keyword(id=1251249362626626491, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, language=EN, orderNo=4, keyword=least square support vector machine), Keyword(id=1251249362744067012, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, language=CN, orderNo=1, keyword=航材需求预测), Keyword(id=1251249362865701848, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, language=CN, orderNo=2, keyword=主成分分析), Keyword(id=1251249362978948068, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, language=CN, orderNo=3, keyword=改进粒子群算法), Keyword(id=1251249363058639853, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, language=CN, orderNo=4, keyword=最小二乘支持向量机)], refs=[Reference(id=1251249369798885670, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=柏林, journalName=航材保障学, refType=null, unstructuredReference=柏林. 航材保障学[M]. 徐州: 空军勤务学院, 2020., articleTitle=null, refAbstract=null), Reference(id=1251249369941492017, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=Bo Lin, journalName=Aviation material support, refType=null, unstructuredReference=Bo Lin. Aviation material support[M]. Xuzhou: Air Force Service College, 2020., articleTitle=null, refAbstract=null), Reference(id=1251249370071515451, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, doi=null, pmid=null, pmcid=null, year=2012, volume=null, issue=8, pageStart=179, pageEnd=182, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=李连, 孙聪, 苏涛, journalName=计算机与现代化, refType=null, unstructuredReference=李连, 孙聪, 苏涛. 改进BP网络在航材需求预测中的应用[J]. 计算机与现代化, 2012(8): 179-182, 186., articleTitle=改进BP网络在航材需求预测中的应用, refAbstract=null), Reference(id=1251249370197344579, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, doi=null, pmid=null, pmcid=null, year=2012, volume=null, issue=8, pageStart=179, pageEnd=182, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=Li Lian, Sun Cong, Su Tao, journalName=Computer and Modernization, refType=null, unstructuredReference=Li Lian, Sun Cong, Su Tao. Application of improvable back-propagation network in air material requirement forecast[J]. Computer and Modernization, 2012(8): 179-182, 186., articleTitle=Application of improvable back-propagation network in air material requirement forecast, refAbstract=null), Reference(id=1251249370356728143, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, doi=null, pmid=null, pmcid=null, year=2019, volume=38, issue=15, pageStart=151, pageEnd=154, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=毕钊, 侯胜利, journalName=价值工程, refType=null, unstructuredReference=毕钊, 侯胜利. 基于R语言SARIMA模型的航材需求预测分析[J]. 价值工程, 2019, 38(15): 151-154., articleTitle=基于R语言SARIMA模型的航材需求预测分析, refAbstract=null), Reference(id=1251249370503528796, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, doi=null, pmid=null, pmcid=null, year=2019, volume=38, issue=15, pageStart=151, pageEnd=154, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=Bi Zhao, Hou Shengli, journalName=Value Engineering, refType=null, unstructuredReference=Bi Zhao, Hou Shengli. Aircraft spare parts demand forecasting based on R language and SARIMA model[J]. Value Engineering, 2019, 38(15): 151-154., articleTitle=Aircraft spare parts demand forecasting based on R language and SARIMA model, refAbstract=null), Reference(id=1251249370616775019, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, doi=null, pmid=null, pmcid=null, year=2011, volume=214, issue=3, pageStart=606, pageEnd=615, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=Teunter R H, Syntetos A A, Babai M Z, journalName=European Journal of Operational Research, refType=null, unstructuredReference=Teunter R H, Syntetos A A, Babai M Z. Inter-mittent demand: linking forecasting to inventory obsoles-cence[J]. European Journal of Operational Research, 2011, 214(3): 606-615., articleTitle=Inter-mittent demand: linking forecasting to inventory obsoles-cence, refAbstract=null), Reference(id=1251249370742604148, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, doi=null, pmid=null, pmcid=null, year=2021, volume=12, issue=5, pageStart=75, pageEnd=79, url=null, language=null, rfNumber=[5], rfOrder=7, authorNames=曾浩然, 冯蕴雯, 路成, journalName=航空工程进展, refType=null, unstructuredReference=曾浩然, 冯蕴雯, 路成, . 基于支持向量机回归的民用飞机航材消耗预测研究[J]. 航空工程进展, 2021, 12(5): 75-79., articleTitle=基于支持向量机回归的民用飞机航材消耗预测研究, refAbstract=null), Reference(id=1251249370876821892, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, doi=null, pmid=null, pmcid=null, year=2021, volume=12, issue=5, pageStart=75, pageEnd=79, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=Zeng Haoran, Feng Yunwen, Lu Cheng, journalName=Advances in Aeronautical Engineering, refType=null, unstructuredReference=Zeng Haoran, Feng Yunwen, Lu Cheng, et al. Forecast study on civil aviation material consumption based on support vector machine regression[J]. Advances in Aeronautical Engineering, 2021, 12(5): 75-79., articleTitle=Forecast study on civil aviation material consumption based on support vector machine regression, refAbstract=null), Reference(id=1251249370994262415, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=11, pageStart=4609, pageEnd=4617, url=null, language=null, rfNumber=[6], rfOrder=9, authorNames=付维方, 穆彩虹, 刘英杰, journalName=科学技术与工程, refType=null, unstructuredReference=付维方, 穆彩虹, 刘英杰. 基于机器学习方法的航空消耗件需求自适应预测[J]. 科学技术与工程, 2022, 22(11): 4609-4617., articleTitle=基于机器学习方法的航空消耗件需求自适应预测, refAbstract=null), Reference(id=1251249371086537113, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=11, pageStart=4609, pageEnd=4617, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=Fu Weifang, Mu Caihong, Liu Yingjie, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Fu Weifang, Mu Caihong, Liu Yingjie. Adaptive demand prediction of aviation consumable spare parts based on machine learning method[J]. Science Technology and Engineering, 2022, 22(11): 4609-4617., articleTitle=Adaptive demand prediction of aviation consumable spare parts based on machine learning method, refAbstract=null), Reference(id=1251249371191394721, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, doi=null, pmid=null, pmcid=null, year=2017, volume=37, issue=7, pageStart=105, pageEnd=109, url=null, language=null, rfNumber=[7], rfOrder=11, authorNames=刘旭, 周丽华, 朱臣, journalName=舰船电子工程, refType=null, unstructuredReference=刘旭, 周丽华, 朱臣. 基于PCA-SVM的航材需求预测方法研究[J]. 舰船电子工程, 2017, 37(7): 105-109., articleTitle=基于PCA-SVM的航材需求预测方法研究, refAbstract=null), Reference(id=1251249371455635885, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, doi=null, pmid=null, pmcid=null, year=2017, volume=37, issue=7, pageStart=105, pageEnd=109, url=null, language=null, rfNumber=[7], rfOrder=12, authorNames=Liu Xu, Zhou Lihua, Zhu Chen, journalName=Ship Electronic Engineering, refType=null, unstructuredReference=Liu Xu, Zhou Lihua, Zhu Chen. Prediction of air material requirement based on PCA-SVM[J]. Ship Electronic Engineering, 2017, 37(7): 105-109., articleTitle=Prediction of air material requirement based on PCA-SVM, refAbstract=null), Reference(id=1251249371564687794, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=1, pageStart=281, pageEnd=288, url=null, language=null, rfNumber=[8], rfOrder=13, authorNames=李晓娟, 张芳媛, 喻玲, journalName=科学技术与工程, refType=null, unstructuredReference=李晓娟, 张芳媛, 喻玲. 基于主成分分析-BP神经网络的风电备件需求预测[J]. 科学技术与工程, 2024, 24(1): 281-288., articleTitle=基于主成分分析-BP神经网络的风电备件需求预测, refAbstract=null), Reference(id=1251249371694711228, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=1, pageStart=281, pageEnd=288, url=null, language=null, rfNumber=[8], rfOrder=14, authorNames=Li Xiaojuan, Zhang Fangyuan, Yu Ling, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Li Xiaojuan, Zhang Fangyuan, Yu Ling. Wind power spare parts demand forecasting based on PCA-BP neural network[J]. Science Technology and Engineering, 2024, 24(1): 281-288., articleTitle=Wind power spare parts demand forecasting based on PCA-BP neural network, refAbstract=null), Reference(id=1251249371833123268, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, doi=null, pmid=null, pmcid=null, year=2022, volume=13, issue=6, pageStart=166, pageEnd=172, url=null, language=null, rfNumber=[9], rfOrder=15, authorNames=李黄琪, 蔡开龙, 郝明, journalName=航空工程进展, refType=null, unstructuredReference=李黄琪, 蔡开龙, 郝明, . 基于GRA-IPSO-SVM的航材携行需求预测研究[J]. 航空工程进展, 2022, 13(6): 166-172., articleTitle=基于GRA-IPSO-SVM的航材携行需求预测研究, refAbstract=null), Reference(id=1251249371937980877, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, doi=null, pmid=null, pmcid=null, year=2022, volume=13, issue=6, pageStart=166, pageEnd=172, url=null, language=null, rfNumber=[9], rfOrder=16, authorNames=Li Huangqi, Cai Kailong, Hao Ming, journalName=Advances in Aeronautical Engineering, refType=null, unstructuredReference=Li Huangqi, Cai Kailong, Hao Ming, et al. Research on forecasting of aviation material carrying demand based on GRA-IPSO-SVM[J]. Advances in Aeronautical Engineering, 2022, 13(6): 166-172., articleTitle=Research on forecasting of aviation material carrying demand based on GRA-IPSO-SVM, refAbstract=null), Reference(id=1251249372026061269, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=35, pageStart=15697, pageEnd=15707, url=null, language=null, rfNumber=[10], rfOrder=17, authorNames=李长云, 李亭立, 何频捷, journalName=科学技术与工程, refType=null, unstructuredReference=李长云, 李亭立, 何频捷, . 基于关联规则及组合模型的面料需求预测[J]. 科学技术与工程, 2022, 22(35): 15697-15707., articleTitle=基于关联规则及组合模型的面料需求预测, refAbstract=null), Reference(id=1251249373213049307, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=35, pageStart=15697, pageEnd=15707, url=null, language=null, rfNumber=[10], rfOrder=18, authorNames=Li Changyun, Li Tingli, He Pinjie, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Li Changyun, Li Tingli, He Pinjie, et al. Fabric demand prediction based on association rule and combination model[J]. Science Technology and Engineering, 2022, 22(35): 15697-15707., articleTitle=Fabric demand prediction based on association rule and combination model, refAbstract=null), Reference(id=1251249373364044263, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, doi=null, pmid=null, pmcid=null, year=2021, volume=53, issue=6, pageStart=881, pageEnd=887, url=null, language=null, rfNumber=[11], rfOrder=19, authorNames=孙绳山, 徐常凯, 何亚群, journalName=南京航空航天大学学报, refType=null, unstructuredReference=孙绳山, 徐常凯, 何亚群. 基于RS-PSO-SVM的航材消耗预测模型[J]. 南京航空航天大学学报, 2021, 53(6): 881-887., articleTitle=基于RS-PSO-SVM的航材消耗预测模型, refAbstract=null), Reference(id=1251249373502456310, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, doi=null, pmid=null, pmcid=null, year=2021, volume=53, issue=6, pageStart=881, pageEnd=887, url=null, language=null, rfNumber=[11], rfOrder=20, authorNames=Sun Shengshan, Xu Changkai, He Yaqun, journalName=Journal of Nanjing University of Aeronautics and Astronautics, refType=null, unstructuredReference=Sun Shengshan, Xu Changkai, He Yaqun. Prediction model of air material consumption based on RS-PSO-SVM[J]. Journal of Nanjing University of Aeronautics and Astronautics, 2021, 53(6): 881-887., articleTitle=Prediction model of air material consumption based on RS-PSO-SVM, refAbstract=null), Reference(id=1251249373687005694, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=8, pageStart=68, pageEnd=71, url=null, language=null, rfNumber=[12], rfOrder=21, authorNames=宋传洲, 王瑞奇, 刘战, journalName=航空维修与工程, refType=null, unstructuredReference=宋传洲, 王瑞奇, 刘战. 面向任务携行航材消耗影响因素研究[J]. 航空维修与工程, 2020(8): 68-71., articleTitle=面向任务携行航材消耗影响因素研究, refAbstract=null), Reference(id=1251249373800251913, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=8, pageStart=68, pageEnd=71, url=null, language=null, rfNumber=[12], rfOrder=22, authorNames=Song Chuanzhou, Wang Ruiqi, Liu Zhan, journalName=Aviation Maintenance and Engineering, refType=null, unstructuredReference=Song Chuanzhou, Wang Ruiqi, Liu Zhan. Research on the influencing factors of consumption for mission-oriented carrying aviation materials[J]. Aviation Maintenance and Engineering, 2020(8): 68-71., articleTitle=Research on the influencing factors of consumption for mission-oriented carrying aviation materials, refAbstract=null), Reference(id=1251249373930275344, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, doi=null, pmid=null, pmcid=null, year=2021, volume=28, issue=4, pageStart=88, pageEnd=96, url=null, language=null, rfNumber=[13], rfOrder=23, authorNames=宋传洲, 王瑞奇, 刘天庆, journalName=航空兵器, refType=null, unstructuredReference=宋传洲, 王瑞奇, 刘天庆, . 基于XGBoost-GRA-DEMATEL面向任务携行航材消耗预测方法[J]. 航空兵器, 2021, 28(4): 88-96., articleTitle=基于XGBoost-GRA-DEMATEL面向任务携行航材消耗预测方法, refAbstract=null), Reference(id=1251249374047715863, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, doi=null, pmid=null, pmcid=null, year=2021, volume=28, issue=4, pageStart=88, pageEnd=96, url=null, language=null, rfNumber=[13], rfOrder=24, authorNames=Song Chuanzhou, Wang Ruiqi, Liu Tianqing, journalName=Aviation Weapons, refType=null, unstructuredReference=Song Chuanzhou, Wang Ruiqi, Liu Tianqing, et al. A mission-oriented aircraft spare parts carried consumption prediction method based on XGBoost-GRA-DEMATEL[J]. Aviation Weapons, 2021, 28(4): 88-96., articleTitle=A mission-oriented aircraft spare parts carried consumption prediction method based on XGBoost-GRA-DEMATEL, refAbstract=null), Reference(id=1251249374198710816, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, doi=null, pmid=null, pmcid=null, year=2011, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=25, authorNames=吴先慧, journalName=基于主成分分析和DEA方法的我国区域创新效率评价, refType=null, unstructuredReference=吴先慧. 基于主成分分析和DEA方法的我国区域创新效率评价[D]. 哈尔滨: 哈尔滨工业大学, 2011., articleTitle=null, refAbstract=null), Reference(id=1251249374345511468, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, doi=null, pmid=null, pmcid=null, year=2011, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=26, authorNames=Wu Xianhui, journalName=Harbin Institute of Technology, refType=null, unstructuredReference=Wu Xianhui. The evaluation of Chinese regional innovation efficiency based on principal component analysis and DATA envelopment analysis[D]. Harbin: Harbin Institute of Technology, 2011., articleTitle=null, refAbstract=null), Reference(id=1251249374471340595, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, doi=null, pmid=null, pmcid=null, year=2011, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=27, authorNames=岳斯玮, journalName=主成分分析在生态城市建设能力评价中的应用研究, refType=null, unstructuredReference=岳斯玮. 主成分分析在生态城市建设能力评价中的应用研究[D]. 成都: 成都理工大学, 2011., articleTitle=null, refAbstract=null), Reference(id=1251249374622335550, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, doi=null, pmid=null, pmcid=null, year=2011, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=28, authorNames=Yue Siwei, journalName=The Applied research on principal component analysis in the capacity-building evaluation of ecological city, refType=null, unstructuredReference=Yue Siwei. The Applied research on principal component analysis in the capacity-building evaluation of ecological city[D]. Chengdu: Chengdu University of Technology, 2011., articleTitle=null, refAbstract=null), Reference(id=1251249374748164679, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=1, pageStart=2, pageEnd=10, url=null, language=null, rfNumber=[16], rfOrder=29, authorNames=孙世政, 向洋, 党晓圆, journalName=仪器仪表学报, refType=null, unstructuredReference=孙世政, 向洋, 党晓圆, . 基于粒子群解耦算法的FBG流量温度复合传感研究[J]. 仪器仪表学报, 2022, 43(1): 2-10., articleTitle=基于粒子群解耦算法的FBG流量温度复合传感研究, refAbstract=null), Reference(id=1251249374840439371, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, doi=null, pmid=null, pmcid=null, year=null, volume=202, issue=1, pageStart=2, pageEnd=10, url=null, language=null, rfNumber=[16], rfOrder=30, authorNames=Sun Shizheng, Xiang Yang, Dang Xiaoyuan, journalName=Chinese Journal of Scientific Instrument, refType=null, unstructuredReference=Sun Shizheng, Xiang Yang, Dang Xiaoyuan, et al. Research on FBG flow temperature composite sensor based on PSO decoupling algorithm[J]. Chinese Journal of Scientific Instrument, 202, 43(1): 2-10., articleTitle=Research on FBG flow temperature composite sensor based on PSO decoupling algorithm, refAbstract=null), Reference(id=1251249374941102673, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=2, pageStart=122, pageEnd=127, url=null, language=null, rfNumber=[17], rfOrder=31, authorNames=张万胜, journalName=中国公共安全(学术版), refType=null, unstructuredReference=张万胜. 基于PCA-IPSO-GNN模型的铁路月度客运量预测模型研究[J]. 中国公共安全(学术版), 2018(2): 122-127., articleTitle=基于PCA-IPSO-GNN模型的铁路月度客运量预测模型研究, refAbstract=null), Reference(id=1251249375050154584, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=2, pageStart=122, pageEnd=127, url=null, language=null, rfNumber=[17], rfOrder=32, authorNames=Zhang Wansheng, journalName=China Public Security (Academic Edition), refType=null, unstructuredReference=Zhang Wansheng. Research of railway monthly volume forecast model based on PCA-IPSO-GNN model[J]. China Public Security (Academic Edition), 2018(2): 122-127., articleTitle=Research of railway monthly volume forecast model based on PCA-IPSO-GNN model, refAbstract=null), Reference(id=1251249375155012191, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, doi=null, pmid=null, pmcid=null, year=2023, volume=42, issue=1, pageStart=79, pageEnd=86, url=null, language=null, rfNumber=[18], rfOrder=33, authorNames=张平, 李亚民, 王冠霖, journalName=油气储运, refType=null, unstructuredReference=张平, 李亚民, 王冠霖, . 基于IPSO-LSSVM的离心式压缩机性能预测方法[J]. 油气储运, 2023, 42(1): 79-86., articleTitle=基于IPSO-LSSVM的离心式压缩机性能预测方法, refAbstract=null), Reference(id=1251249375268258405, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, doi=null, pmid=null, pmcid=null, year=2023, volume=42, issue=1, pageStart=79, pageEnd=86, url=null, language=null, rfNumber=[18], rfOrder=34, authorNames=Zhang Ping, Li Yamin, Wang Guanlin, journalName=Oil and Gas Storage and Transportation, refType=null, unstructuredReference=Zhang Ping, Li Yamin, Wang Guanlin, et al. Performance prediction method of centrifugal compressor based on IPSO-LSSVM[J]. Oil and Gas Storage and Transportation, 2023, 42(1): 79-86., articleTitle=Performance prediction method of centrifugal compressor based on IPSO-LSSVM, refAbstract=null), Reference(id=1251249375394087533, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, doi=null, pmid=null, pmcid=null, year=2021, volume=51, issue=7, pageStart=54, pageEnd=60, url=null, language=null, rfNumber=[19], rfOrder=35, authorNames=李文强, 刘颖, journalName=数学的实践与认识, refType=null, unstructuredReference=李文强, 刘颖. 基于灰色关联分析与PLS-LSSVM的航材备件需求预测模型[J]. 数学的实践与认识, 2021, 51(7): 54-60., articleTitle=基于灰色关联分析与PLS-LSSVM的航材备件需求预测模型, refAbstract=null), Reference(id=1251249375515722355, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, doi=null, pmid=null, pmcid=null, year=2021, volume=51, issue=7, pageStart=54, pageEnd=60, url=null, language=null, rfNumber=[19], rfOrder=36, authorNames=Li Wenqiang, Liu Ying, journalName=Mathematical Practice and Understanding, refType=null, unstructuredReference=Li Wenqiang, Liu Ying. The prediction model of airlines spare parts based on grey-relational analysis and PLS-LSSVM[J]. Mathematical Practice and Understanding, 2021, 51(7): 54-60., articleTitle=The prediction model of airlines spare parts based on grey-relational analysis and PLS-LSSVM, refAbstract=null)], funds=[Fund(id=1251249369522061591, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, awardId=QJ2023-006, language=CN, fundingSource=2023年度中央高校基本科研业务费资助项目-青年基金(QJ2023-006), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1251249360806298321, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, xref=1, ext=[AuthorCompanyExt(id=1251249360814686931, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, companyId=1251249360806298321, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Aircraft Repair & Overhaul Plant, Civil Aviation Flight University of China, Guanghan 618307, China), AuthorCompanyExt(id=1251249360823075541, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, companyId=1251249360806298321, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国民用航空飞行学院飞机修理厂, 广汉 618307)]), AuthorCompany(id=1251249360919544547, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, xref=2, ext=[AuthorCompanyExt(id=1251249360927933157, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, companyId=1251249360919544547, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Guanghan Branch, Civil Aviation Flight University of China, Guanghan 618307, China), AuthorCompanyExt(id=1251249360932127462, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, companyId=1251249360919544547, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 中国民用航空飞行学院广汉分院, 广汉 618307)])], figs=[ArticleFig(id=1251249364845412363, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, language=EN, label=Fig.1, caption=Flow chart, figureFileSmall=1d+eIpzaCb3wo4I62HGsPg==, figureFileBig=GNAM4VMOqXvPr3nUj2zUmA==, tableContent=null), ArticleFig(id=1251249365021573145, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, language=CN, label=图1, caption=流程图, figureFileSmall=1d+eIpzaCb3wo4I62HGsPg==, figureFileBig=GNAM4VMOqXvPr3nUj2zUmA==, tableContent=null), ArticleFig(id=1251249365193539626, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, language=EN, label=Fig.2, caption=Fitness curve, figureFileSmall=9fczljM4I8FXn0zLfyhSSw==, figureFileBig=ClyxFSAC5H9vuz/r4A3rTw==, tableContent=null), ArticleFig(id=1251249365336145973, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, language=CN, label=图2, caption=适应度曲线, figureFileSmall=9fczljM4I8FXn0zLfyhSSw==, figureFileBig=ClyxFSAC5H9vuz/r4A3rTw==, tableContent=null), ArticleFig(id=1251249365487140931, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, language=EN, label=Fig.3, caption=Comparison chart, figureFileSmall=IHIKxDqDz4c8B4xU/e3m3w==, figureFileBig=UmoK0REOoNwqhYNpH4C8pw==, tableContent=null), ArticleFig(id=1251249365612970064, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, language=CN, label=图3, caption=对比图, figureFileSmall=IHIKxDqDz4c8B4xU/e3m3w==, figureFileBig=UmoK0REOoNwqhYNpH4C8pw==, tableContent=null), ArticleFig(id=1251249365801713756, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, language=EN, label=Table 1, caption=

Factors affecting spare parts of aviation materials

, figureFileSmall=null, figureFileBig=null, tableContent=
编号 影响因素 数值单位或类型 取值
X1 飞行时间 h 飞机飞行总时长
X2 起落次数 飞机起落总架次
X3 异常温度 查阅资料
X4 异常湿度 湿度 查阅资料
X5 故障率 数值 相关记录
X6 人员熟练程度 数值 相关记录
X7 维修人员技术水平 数值 相关记录
), ArticleFig(id=1251249365956903015, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, language=CN, label=表1, caption=

航材备件影响因素

, figureFileSmall=null, figureFileBig=null, tableContent=
编号 影响因素 数值单位或类型 取值
X1 飞行时间 h 飞机飞行总时长
X2 起落次数 飞机起落总架次
X3 异常温度 查阅资料
X4 异常湿度 湿度 查阅资料
X5 故障率 数值 相关记录
X6 人员熟练程度 数值 相关记录
X7 维修人员技术水平 数值 相关记录
), ArticleFig(id=1251249366095315061, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, language=EN, label=Table 2, caption=

Data of aviation material demand and influencing factors from 2010 to 2017

, figureFileSmall=null, figureFileBig=null, tableContent=
序号 飞行时间 飞行起落 异常环境温度 异常环境湿度 故障率 人员熟练程度 人员技术水平 需求量
1 145 39 0.389 0.401 9.6 0.371 0.597 9
2 198 55 0.367 0.389 9.2 0.837 0.681 12
3 133 34 0.243 0.355 6.9 0.383 0.404 7
4 177 40 0.314 0.424 7.2 0.664 0.354 11
29 178 45 0.399 0.487 7.2 0.423 0.421 9
30 158 40 0.377 0.348 7.2 0.664 0.477 9
31 138 50 0.317 0.305 6.2 0.605 0.309 8
32 98 19 0.172 0.156 5.2 0.247 0.428 13
), ArticleFig(id=1251249366229532799, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, language=CN, label=表2, caption=

2010—2017年航材需求量及各影响因素的数据

, figureFileSmall=null, figureFileBig=null, tableContent=
序号 飞行时间 飞行起落 异常环境温度 异常环境湿度 故障率 人员熟练程度 人员技术水平 需求量
1 145 39 0.389 0.401 9.6 0.371 0.597 9
2 198 55 0.367 0.389 9.2 0.837 0.681 12
3 133 34 0.243 0.355 6.9 0.383 0.404 7
4 177 40 0.314 0.424 7.2 0.664 0.354 11
29 178 45 0.399 0.487 7.2 0.423 0.421 9
30 158 40 0.377 0.348 7.2 0.664 0.477 9
31 138 50 0.317 0.305 6.2 0.605 0.309 8
32 98 19 0.172 0.156 5.2 0.247 0.428 13
), ArticleFig(id=1251249366393110664, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, language=EN, label=Table 3, caption=

Standardized data

, figureFileSmall=null, figureFileBig=null, tableContent=
序号 飞行时间 飞行起落 异常环境温度 异常环境湿度 故障率 人员熟练程度 人员技术水平
1 -0.42 -0.23 0.43 -0.01 0.59 -0.90 0.86
2 0.79 1.08 0.24 -0.09 0.39 1.18 1.41
3 -0.69 -0.64 -0.85 -0.33 -0.73 -0.84 -0.40
4 0.31 -0.15 -0.22 0.16 -0.58 0.41 -0.73
29 0.33 0.26 0.52 0.60 -0.58 -0.67 -0.29
30 -0.12 -0.15 0.33 -0.38 -0.58 0.41 0.07
31 -0.58 0.67 -0.20 -0.68 -1.07 0.14 -1.03
32 -1.49 -1.86 -1.47 -1.72 -1.55 -1.45 -0.25
), ArticleFig(id=1251249366506356884, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, language=CN, label=表3, caption=

标准化数据

, figureFileSmall=null, figureFileBig=null, tableContent=
序号 飞行时间 飞行起落 异常环境温度 异常环境湿度 故障率 人员熟练程度 人员技术水平
1 -0.42 -0.23 0.43 -0.01 0.59 -0.90 0.86
2 0.79 1.08 0.24 -0.09 0.39 1.18 1.41
3 -0.69 -0.64 -0.85 -0.33 -0.73 -0.84 -0.40
4 0.31 -0.15 -0.22 0.16 -0.58 0.41 -0.73
29 0.33 0.26 0.52 0.60 -0.58 -0.67 -0.29
30 -0.12 -0.15 0.33 -0.38 -0.58 0.41 0.07
31 -0.58 0.67 -0.20 -0.68 -1.07 0.14 -1.03
32 -1.49 -1.86 -1.47 -1.72 -1.55 -1.45 -0.25
), ArticleFig(id=1251249366661546154, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, language=EN, label=Table 4, caption=

Correlation coefficient matrix R

, figureFileSmall=null, figureFileBig=null, tableContent=
rij
rji 1.000 0 0.804 8 0.820 5 0.830 0 0.790 0 0.762 7 0.646 3
0.804 8 1.000 0 0.680 7 0.753 9 0.678 5 0.814 9 0.576 0
0.820 5 0.680 7 1.000 0 0.573 9 0.607 9 0.504 9 0.695 3
0.830 0 0.753 9 0.573 9 1.000 0 0.765 3 0.707 4 0.480 8
0.790 0 0.678 5 0.607 9 0.765 3 1.000 0 0.599 9 0.528 0
0.762 7 0.814 9 0.504 9 0.707 4 0.599 9 1.000 0 0.416 3
0.646 3 0.576 0 0.695 3 0.480 8 0.528 0 0.416 3 1.000 0
), ArticleFig(id=1251249366808346808, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, language=CN, label=表4, caption=

相关系数矩阵R

, figureFileSmall=null, figureFileBig=null, tableContent=
rij
rji 1.000 0 0.804 8 0.820 5 0.830 0 0.790 0 0.762 7 0.646 3
0.804 8 1.000 0 0.680 7 0.753 9 0.678 5 0.814 9 0.576 0
0.820 5 0.680 7 1.000 0 0.573 9 0.607 9 0.504 9 0.695 3
0.830 0 0.753 9 0.573 9 1.000 0 0.765 3 0.707 4 0.480 8
0.790 0 0.678 5 0.607 9 0.765 3 1.000 0 0.599 9 0.528 0
0.762 7 0.814 9 0.504 9 0.707 4 0.599 9 1.000 0 0.416 3
0.646 3 0.576 0 0.695 3 0.480 8 0.528 0 0.416 3 1.000 0
), ArticleFig(id=1251249366976118983, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, language=EN, label=Table 5, caption=

Normalized data

, figureFileSmall=null, figureFileBig=null, tableContent=
序号 飞行
时间
飞行
起落
异常环
境温度
异常环
境湿度
需求量
1 0.301 6 0.416 7 0.564 0.385 8 0.285 7
2 0.582 0 0.750 0 0.520 0.366 9 0.714 3
3 0.238 1 0.312 5 0.272 0.313 4 0.000 0
4 0.470 9 0.437 5 0.414 0.422 0 0.571 4
29 0.476 2 0.541 7 0.584 0.521 3 0.285 7
30 0.370 4 0.437 5 0.540 0.302 4 0.285 7
31 0.264 6 0.645 8 0.420 0.234 6 0.142 9
32 0.052 9 0.000 0 0.130 0.000 0 0.857 1
), ArticleFig(id=1251249367118725332, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, language=CN, label=表5, caption=

归一化数据

, figureFileSmall=null, figureFileBig=null, tableContent=
序号 飞行
时间
飞行
起落
异常环
境温度
异常环
境湿度
需求量
1 0.301 6 0.416 7 0.564 0.385 8 0.285 7
2 0.582 0 0.750 0 0.520 0.366 9 0.714 3
3 0.238 1 0.312 5 0.272 0.313 4 0.000 0
4 0.470 9 0.437 5 0.414 0.422 0 0.571 4
29 0.476 2 0.541 7 0.584 0.521 3 0.285 7
30 0.370 4 0.437 5 0.540 0.302 4 0.285 7
31 0.264 6 0.645 8 0.420 0.234 6 0.142 9
32 0.052 9 0.000 0 0.130 0.000 0 0.857 1
), ArticleFig(id=1251249367223582938, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, language=EN, label=Table 6, caption=

IPSO parameter table

, figureFileSmall=null, figureFileBig=null, tableContent=
参数 数值
维数 2
规模 25
最大迭代次数 200
学习因子c1 2
学习因子c2 2
惯性权重最大值 0.9
惯性权重最小值 0.4
初始化位置 [100,1 000]
初始化速度 [0.001,0.01]
位置速度比 0.5
正则化系数 [0.01,300]
核函数系数 [0.01,200]
), ArticleFig(id=1251249367391355110, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, language=CN, label=表6, caption=

IPSO参数表

, figureFileSmall=null, figureFileBig=null, tableContent=
参数 数值
维数 2
规模 25
最大迭代次数 200
学习因子c1 2
学习因子c2 2
惯性权重最大值 0.9
惯性权重最小值 0.4
初始化位置 [100,1 000]
初始化速度 [0.001,0.01]
位置速度比 0.5
正则化系数 [0.01,300]
核函数系数 [0.01,200]
), ArticleFig(id=1251249367580098808, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, language=EN, label=Table 7, caption=

Comparison of predictive performance

, figureFileSmall=null, figureFileBig=null, tableContent=
模型名称 RMSE MRE/%
LSSVM 12.32 13.43
PSO-LSSVM 10.67 11.13
IPSO-LSSVM 9.56 9.32
文献[19] 8.09 5.98
PCA-IPSO-LSSVM 3.24 4.23
), ArticleFig(id=1251249369186517248, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149781964531655633, language=CN, label=表7, caption=

预测性能比较

, figureFileSmall=null, figureFileBig=null, tableContent=
模型名称 RMSE MRE/%
LSSVM 12.32 13.43
PSO-LSSVM 10.67 11.13
IPSO-LSSVM 9.56 9.32
文献[19] 8.09 5.98
PCA-IPSO-LSSVM 3.24 4.23
)], 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.1671-1815.2400770, detailUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2400770, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/PDF/10.12404/j.issn.1671-1815.2400770, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/PDF/10.12404/j.issn.1671-1815.2400770, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于PCA-IPSO-LSSVM的航材备件需求预测模型
收藏切换
PDF下载
许浩 1 , 田才艳 2 , 毛瑞柯 1
科学技术与工程 | 论文·航空、航天 2025,25(9): 3938-3944
收起
收藏切换
科学技术与工程 | 论文·航空、航天 2025, 25(9): 3938-3944
基于PCA-IPSO-LSSVM的航材备件需求预测模型
全屏
许浩1 , 田才艳2, 毛瑞柯1
作者信息
  • 1 中国民用航空飞行学院飞机修理厂, 广汉 618307
  • 2 中国民用航空飞行学院广汉分院, 广汉 618307
  • 许浩(1996—),男,汉族,四川德阳人,硕士,助理工程师。研究方向:人工智能模式识别、通航维修技术等。E-mail:

Prediction Model of Aviation Spare Parts Demand Based on PCA-IPSO-LSSVM
Hao XU1 , Cai-yan TIAN2, Rui-ke MAO1
Affiliations
  • 1 Aircraft Repair & Overhaul Plant, Civil Aviation Flight University of China, Guanghan 618307, China
  • 2 Guanghan Branch, Civil Aviation Flight University of China, Guanghan 618307, China
出版时间: 2025-03-28 doi: 10.12404/j.issn.1671-1815.2400770
文章导航
收藏切换

为解决航材备件需求预测中,因航材消耗影响因素多,样本数据量少从而造成预测效果差等问题。提出一种基于主成分分析(principal component analysis,PCA)与改进粒子群算法(improved particle swarm optimization,IPSO)及最小二乘支持向量机(least square support vector machine,LSSVM)的航材备件需求预测模型,首先利用主成分分析法筛选出航材备件主要影响因素,然后使用改进粒子群算法优化最小二乘支持向量机参数组合,最后使用筛选结果及优化参数组合完成PCA-IPSO-LSSVM航材备件需求预测模型训练。与其他4个预测模型相比,PCA-IPSO-LSSVM模型预测精度最高,测试集的均方根误差(root mean squared error,RMSE)和平均相对误差(mean relative error,MRE)分别为3.24和4.23%,表明模型具有较好的预测精度和拟合效果。

航材需求预测  /  主成分分析  /  改进粒子群算法  /  最小二乘支持向量机

In order to solve the problem of poor forecasting effect due to the large number of influencing factors of aviation material consumption and small amount of sample data. A prediction model for aircraft spare parts demand based on principal component analysis (PCA), improved particle swarm optimization (IPSO), and least squares support vector machine (LSSVM) was proposed. Firstly, the principal component analysis method was used to screen the main influencing factors of aviation spare parts, and then the improved particle swarm optimization algorithm was used to optimize the least square support vector machine parameter combination, and finally the selection results and optimization parameter combination were used to complete the PCA-IPSO-LSSVM aviation spare parts demand prediction model training. The results show that compared with the other four prediction models, the PCA-IPSO-LSSVM model has the highest prediction accuracy, and the RMSE and MRE of the test set are 3.24 and 4.23%, respectively, indicating that the model has good prediction precision and fitting effect.

aviation material demand prediction  /  principal component analysis  /  improved particle swarm optimization  /  least square support vector machine
许浩, 田才艳, 毛瑞柯. 基于PCA-IPSO-LSSVM的航材备件需求预测模型. 科学技术与工程, 2025 , 25 (9) : 3938 -3944 . DOI: 10.12404/j.issn.1671-1815.2400770
Hao XU, Cai-yan TIAN, Rui-ke MAO. Prediction Model of Aviation Spare Parts Demand Based on PCA-IPSO-LSSVM[J]. Science Technology and Engineering, 2025 , 25 (9) : 3938 -3944 . DOI: 10.12404/j.issn.1671-1815.2400770
近年来对民航业的重视程度越来越高,民航业随之发展加速,运输机场的数量和运输航空的旅客量日益增加,低空领域的开放也使得通用航空和无人机等行业蓬勃发展[1]。航材作为保障飞机安全的重要环节,其保障压力也随之增加。提高航材利用率、减少其库存量可以大幅度减少运输航空公司的经济压力,而航材及时到位能够提高通用航空飞行效率以及减少航校飞行训练的停场率,所以对航材备件需求进行预测具有重要意义[2]。航材备件需求预测发展较早且现已有很多预测方法,最早出现的是时间序列预测法。毕钊等[3]通过观察时间变化、长期改变及干扰等情况互相影响,提升了时间序列法预测精度,不过涉及要素较少且后期误差较大。Teunter等[4]使用Bootstrap法推算非连续性航材的需求量,该方法应用在小样本数据时准确率较低。随着智能算法的兴起,曾浩然等[5]使用支持向量机模型进行航材消耗量预测,支持向量机处理小样本数据时拟合效果不错,不过支持向量机的参数组合对其分类精确度有较大影响。付维方等[6]提出不同聚类模式和预测方法映射关系并实现数据与方法动态自适应的消耗备件需求预测。刘旭等[7]使用支持向量机(support vector machine,SVM)和主成分分析(principal component analysis,PCA)相结合的方法完成航材需求预测,PCA能够筛选出主要影响因素,但是SVM完成大规模样本训练速度慢且受核函数参数影响较大。李晓娟等[8]提出一种主成分分析-反向传播的风电备件需求预测模型,实验表明该模型预测结果可靠。李黄琪等[9]使用灰色关联度与改进的粒子群算法及支持向量机相结合的方法进行航材预测,但支持向量机在预测大样本数据时训练时间过长、准确率较低。李长云等[10]提出基于关联规则及组合模型的面料需求预测方法,该方法需求预测精度更高。孙绳山等[11]提出粗糙集与粒子群算法(particle swarm optimization,PSO)及支持向量机相结合的航材消耗预测方法,粒子群算法具有收敛快、参数少等优点,但PSO算法存在后期搜索能力低、易产生局部最优解等问题,造成预测精度不足。类似的预测方法在处理小样本数据时具有优势,但是对数据完整度要求较高,在处理不完整数据时预测精度都偏低。
综上,航材备件需求预测需要解决影响因素冗杂、算法速度慢及预测分类精度低等问题。针对以上问题,现提出PCA-IPSO-LSSVM的方法进行航材备件需求预测,PCA与IPSO和LSSVM的组合方法能去除影响航材消耗的多余因素,也能满足小样本航材备件预测的需求,处理不完整数据时效果好,IPSO算法极大地减少了核函数参数对LSSVM模型的影响,经过IPSO优化后的LSSVM模型进行分类预测的精度较高。
影响航材备件数量的因素很多[12],如航材自身质量、飞机飞行时长以及飞行环境等。飞行小时数越多,航空器零部件的使用寿命越长,就会加剧其老化和疲劳程度,飞机起落次数越多对飞机起落架等零部件冲击越大,也会加速其损坏。航材自身因素为航材故障率,即航材出厂后因设计或者制造原因在仓库自然损坏的平均概率[13]。飞行环境主要包括航空器运行的平均温湿度,温度变化将导致某些紧固件失效,湿度改变将导致结构金属件失效。还有人员因素,如飞行员和机务维修人员操作熟练度越高,业务能力水平越高,因人为原因导致的更换航材将减少,这些可以通过平时记录、工作时间及查阅相关资料得到。航材备件影响因素分析如表1所示。
在多指标统计分析中,每个独立指标和中心目标信息的相关度都能通过该指标自身表示,但是每个指标之间或多或少重叠部分信息,在后续研究中指标过多会增加计算复杂度,所以在对数据进行下一步处理之前,需要将数据尽可能地减少,不过其包含的信息量要够多。主成分分析法就是将原始数据通过计算简化为少数几个综合指标[14-15],得到的简化指标包括原始数据大部分信息,其运算步骤如下。
步骤1 建立指标变量矩阵。
假如有m个指标${X}_{1},{X}_{2},\dots,{X}_{m},$分别代表某个对象的各种特性,又有N个对象,则可用N×m矩阵表示其所有指标,即

${x}_{\mathrm{N}\times \mathrm{m}}$=$\left[\begin{array}{llll}{x}_{11}& {x}_{12}& \dots & {x}_{1m}\\ {x}_{21}& {x}_{22}& \dots & {x}_{2m}\\ ︙& ︙& \mathrm{ }& ︙\\ {x}_{N1}& {x}_{N2}& \dots & {x}_{Nm}\end{array}\right]。$

步骤2 标准化处理。
按式(1)对数据进行标准化处理,生成标准化矩阵Y
${Y}_{ij}=\frac{{x}_{ij}-{\overline{x}}_{j}}{{s}_{j}}$
式(1)中:$i=\mathrm{1,2},\dots,N;j=\mathrm{1,2},\dots,m$;${\overline{x}}_{j}$sj分别为变量xj的均值和方差。
步骤3 计算相关系数矩阵。

${R}_{\mathrm{N}\times \mathrm{m}}$=$\left[\begin{array}{llll}{r}_{11}& {r}_{12}& \dots & {r}_{1m}\\ {r}_{21}& {r}_{22}& \dots & {r}_{2m}\\ ︙& ︙& \mathrm{ }& ︙\\ {r}_{N1}& {r}_{N2}& \dots & {r}_{Nm}\end{array}\right]$

标准化矩阵Yyiyj的相关系数用rij表示,rij=rji,其运算公式为
${r}_{ij}=\frac{\stackrel{m}{\sum _{k=1}}({y}_{ki}-{\overline{y}}_{i})({y}_{kj}-{\overline{y}}_{j})}{\sqrt{\stackrel{m}{\sum _{k=1}}({y}_{ki}-{\overline{y}}_{i}{)}^{2}\stackrel{m}{\sum _{k=1}}({y}_{kj}-{\overline{y}}_{j}{)}^{2}}}$
步骤4 求特征值与特征向量。
先对特征方程$\left|\lambda I-R\right|=0$求解,求出特征值,然后按从大到小顺序进行排列为

${\lambda }_{1}\ge {\lambda }_{2}\ge {\lambda }_{3}\dots \ge {\lambda }_{m}\ge 0。$

分别求出与特征值${\lambda }_{i}$相对应的特征向量${e}_{\mathrm{i}}(i=\mathrm{1,2},\dots,m)$,要求‖ei‖=1,即$\stackrel{m}{\sum _{j=1}}{e}_{ij}^{2}=1$,eij代表向量ei的第j个分量。
步骤5 求出主成分贡献率和累计贡献率。
贡献率的计算方法为
${g}_{i}=\frac{{\lambda }_{i}}{\stackrel{m}{\sum _{k=1}}{\lambda }_{k}},\mathrm{ }i=\mathrm{1,2},\dots,m$
累计贡献率的计算方法为
$G=\frac{\stackrel{i}{\sum _{k=1}}{\lambda }_{k}}{\stackrel{m}{\sum _{k=1}}{\lambda }_{k}},\mathrm{ }i=\mathrm{1,2},\dots,m$
筛选累计贡献率达到85%~95%的特征值为${\lambda }_{1},{\lambda }_{2},\dots,{\lambda }_{n},$对应第1、第2、…、第$n(n\le m$)个主成分。
粒子群算法是一种有效的仿生算法,其通过模仿鸟来不断迭代更新参数以找到最优解[16]。每个粒子具备两个参数,分别代表方向和速度,每个粒子独立地在定义域求解,将其记为当前最优解,所有粒子反复地在定义域内求解并共享当前最优解,直到迭代稳定后得到的极值则记为粒子群的最优解。
PSO的基本公式为
$\left\{\begin{array}{l}{X}_{it}^{h+1}={X}_{it}^{h}+{V}_{it}^{h+1}\\ {V}_{it}^{h+1}=\mu {V}_{it}^{h}+{c}_{1}{r}_{1}({p}_{it}^{h}-{X}_{it}^{h})+{c}_{2}{r}_{2}({p}_{gt}^{h}-{X}_{it}^{h})\end{array}\right.$
式(5)中:$\mu $为惯性权重;${V}_{it}^{h}$为第h次迭代粒子i速度矢量第t维分量;${X}_{it}^{h}$为第h次迭代粒子i位置矢量第t维分量;${P}_{it}^{h}$为粒子h在迭代中的最优位置;c1c2为学习因子。粒子群算法具有收敛快、参数少等优点,但PSO算法存在后期搜索能力低、易产生局部最优解等问题。为解决该问题,张万胜[17]对惯性权重进行调整,调整公式为
$\mu =\gamma +\sigma N\left(\mathrm{0,1}\right)$
$\gamma ={\gamma }_{\mathrm{m}\mathrm{i}\mathrm{n}}+({\gamma }_{\mathrm{m}\mathrm{a}\mathrm{x}}-{\gamma }_{\mathrm{m}\mathrm{i}\mathrm{n}})\mathrm{r}\mathrm{a}\mathrm{n}\mathrm{d}\left(\mathrm{0,1}\right)$
式中:N(0,1)为正态分布的随机数;rand(0,1)为0~1的随机数;$\sigma $为随机权重方差;${\gamma }_{\mathrm{m}\mathrm{a}\mathrm{x}}、{\gamma }_{\mathrm{m}\mathrm{i}\mathrm{n}}$分别为随机权均值的最大值和最小值。改进PSO算法收敛速度更快,避免了后期迭代过程中全局搜索能力下降和种群多样性降低的问题。
最小二乘支持向量机是在SVM基础上演变而来的分类算法,由于支持向量机算法在求解凸优化问题时,其矩阵规模受样本数量的影响较大,且存在超平面参数选择问题,所以可以改动损失函数,进行问题优化的目标函数采用二范数,将原本SVM算法中的不等式约束条件改为等式约束,将优化问题变为对线性规划问题进行求解,这样就将求解Lagrange乘子完成简化,极大程度降低了算法空间复杂性,提高了算法的收敛速度及准确度[18],其原理如下:定义训练样本集为:$S=\left\{\right({x}_{k},{y}_{k}),k=\mathrm{1,2},\dots,N\}$,其中xk为输入样本,yk为输出样本,优化的目标函数为
$\mathrm{m}\mathrm{i}\mathrm{n}\left[\frac{1}{2}({w}^{\mathrm{*}}+C\stackrel{N}{\sum _{k=1}}{\xi }_{k}^{2})\right]$
其约束条件为
${y}_{k}={w}^{\mathrm{*}T}\varphi \left({x}_{k}\right)+{b}_{k}+{\xi }_{k}$
式中:${\xi }_{\mathrm{k}}$为误差变量;w*为权向量;bk为偏差量;C为可调正则参数。
然后引入拉格朗日因子${\alpha }_{k}$,根据KKT(Karush-Kuhn-Tucker)条件和Mercer定理得到线性约束条件,并采用最小二乘法求解。最终构建的LSSVM预测模型可表示为
$f\left(x\right)=\stackrel{N}{\sum _{k=1}}{\alpha }_{k}K({x}_{k},x)+b$
式(10)中:核函数K(xk,x)为径向基核函数RBF,其表达式为
$K(x,{x}_{i})=\mathrm{e}\mathrm{x}\mathrm{p}\left(-\frac{{\left|x-{x}_{i}\right|}^{2}}{{\sigma }^{2}}\right)$
式(11)中:x为支持向量;${\sigma }^{2}$为核函数参数。
因为LSSVM模型的分类预测精度和其参数组合$(C,{\sigma }^{2})$的选值紧密相关,为了提高其分类预测精度,使用IPSO算法对参数组合进行优化。
首先通过主成分分析法筛选出主要航材备件影响因素,然后利用IPSO算法寻优最小二乘支持向量机关键参数组合,再将筛选出的因素作为最小二乘支持向量机输入数据结合寻优得到的参数组合训练得到航材备件需求预测模型,基于PCA-IPSO-SSVM的航材需求预测模型计算流程如图1所示,主要步骤如下。
(1)收集航材消耗历史数据。
(2)对航材历史消耗数据进行主成分分析,筛选主要影响因素,并划分训练集和测试集。
(3)初始化设置IPSO模型的参数,运用IPSO 算法结合LSSVM模型对划分的训练集反复迭代运算,得到LSSVM模型的参数组合惩罚因子C和核函数参数${\sigma }^{2}$
(4)将训练集结合寻优得到的参数组合训练得到IPSO-LSSVM模型。
(5)将测试集输入PCA-IPSO-LSSVM模型得到预测值,分析模型预测性能。
选取文献[19]中部分数据,某无人机一种航材备件从2010年第1季度到2017年第4季度期间,每季度的航材消耗及影响因素相关数据,共32项数据。选取表1中影响航材备件的相关因素共7项,具体数据如表2所示。
根据式(1)计算标准化矩阵Y,将其转化为如表3所示数据。
根据式(2)计算相关系数矩阵R表4所示。
通过计算得到7个因素的特征值为: λ1=5.042 0,λ2=0.766 2,λ3=0.441 1,λ4=0.311 0,λ5=0.210 9,λ6=0.168 1,λ7=0.060 7。
根据式(3)计算各因素贡献率为:ρ1=0.720 3,ρ2=0.109 5,ρ3=0.063 0,ρ4=0.044 4,ρ5=0.030 1, ρ6=0.024 0,ρ7=0.008 7。
根据式(4)得出前4个因素的累计贡献率为: G=93.71%,85%<G<95%。
因此选取前4个因素就可以包括原始数据绝大部分信息,对前4个因素处理可以减少运算复杂度,对其进行归一化处理,归一化处理公式为
${y}^{i}=\frac{{y}_{i}-{y}_{\mathrm{m}\mathrm{i}\mathrm{n}}}{{y}_{\mathrm{m}\mathrm{a}\mathrm{x}}-{y}_{\mathrm{m}\mathrm{i}\mathrm{n}}}$
式(12)中:yi为原始数据;ymaxymin分别为最大值、最小值。
归一化后数据如表5所示,将前24组数据划分为训练集,后8组数据划分为测试集。
IPSO参数设置影响其最后运算结果。为使IPSO算法充分发挥其优势提升预测精度,先对其参数进行设计,如表6所示。将航材历史消耗数据拟合效果均方差作为粒子群的适应度函数,粒子群迭代结果如图2所示,可以看出,粒子群迭代到25次左右就寻到最优参数组合,此时最优参数组合为C=18.136,${\sigma }^{2}$=0.213。
将经过IPSO寻优得到参数组合结合训练集输入LSSVM模型完成PCA-IPSO-LSSVM航材备件需求预测模型的训练,将测试集输入模型中得到预测值,将均方根误差(root mean squared error,RMSE)和平均相对误差(mean relative error,MRE)作为模型预测性能评价标准,进行拟合效果和泛化能力验证。
$\mathrm{R}\mathrm{M}\mathrm{S}\mathrm{E}=\sqrt{\frac{1}{n}\stackrel{n}{\sum _{i=1}}({y}_{i}-{y}_{i}^{\mathrm{*}}{)}^{2}}$
$MRE=\frac{1}{n}\stackrel{n}{\sum _{i=1}}\left|\frac{{y}_{i}^{\mathrm{*}}-{y}_{i}}{{y}_{i}}\right|\times 100\mathrm{\%}$
式中:n为样本数;${y}_{i}^{\mathrm{*}}$为预测值;yi为实际值。
采用RMSE和MRE作为指标,评价模型预测值与实际测量值的变化趋势。为进行对比分析,分别使用文献[19]中的方法、LSSVM模型、PSO-LSSVM模型、IPSO-LSSVM模型进行预测及误差分析计算,得到的对比结果如图3所示,得到的RMSE和MRE指标如表7所示,可以看出,LSSVM模型的RMSE为12.32、MRE为17%,PSO-LSSVM模型的RMSE为10.67、MRE为15%,IPSO-SVM模型的RMSE为8.56、MRE为12%,PCA-IPSO-LSSVM模型的RMSE为3.24、MRE为4.23%,PCA-IPSO-LSSVM模型的RMSE、MRE比其他模型小,这表明PCA-IPSO-LSSVM 模型较其他预测模型具有更高的预测精度和更好的拟合效果,是一种更有效且更可靠的航材备件需求预测预测方法。
图3表7所示,PCA-IPSO-LSSVM组合预测模型相对误差较小预测精度较高,因为PCA能将原始数据中冗余因素去除,使得预测模型的输入值更加精简准确,同时IPSO算法收敛快寻优得到的参数组合提升了最小二乘支持向量机的分类性能,使得最小二乘支持向量机在分类预测时更快速精确。
建立了PCA-IPSO-LSSVM航材需求预测模型,并对模型进行了分析与评价,得到如下结论。
(1)提出PCA和IPSO及LSSVM相结合的航材备件需求预测模型,解决了提供的样本信息不完全和不确定以及复杂多变等导致航材备件需求预测精度低的问题,该模型展现了PCA理论筛选主要影响因素的能力,又体现了IPSO算法的强大搜索能力,避免了盲目选择LSSVM核函数参数,也展现了LSSVM模型的快速收敛能力,提高了航材备件需求的分类预测性能。
(2)采用主成分分析对原始数据初步筛选,能够准确把握强相关因素,减少非关键影响参数对模型的干扰,IPSO 算法收敛速度较快,寻优得到的模型最优正则参数C为18.136,最优核函数参数为0.213,测试集的RMSE和MRE分别为3.24和4.23%,优化后的LSSVM模型预测精度得到提升。
(3)结合PCA理论、IPSO算法和LSSVM模型,构建了PCA-IPSO-LSSVM航材备件需求预测模型,不仅为航材需求预测提供了不同的思路与方法,也对此类大样本、非线性和多维数据研究具有参考价值。
  • 2023年度中央高校基本科研业务费资助项目-青年基金(QJ2023-006)
参考文献 引证文献
排序方式:
[1]
柏林. 航材保障学[M]. 徐州: 空军勤务学院, 2020.
Bo Lin. Aviation material support[M]. Xuzhou: Air Force Service College, 2020.
[2]
李连, 孙聪, 苏涛. 改进BP网络在航材需求预测中的应用[J]. 计算机与现代化, 2012(8): 179-182, 186.
Li Lian, Sun Cong, Su Tao. Application of improvable back-propagation network in air material requirement forecast[J]. Computer and Modernization, 2012(8): 179-182, 186.
[3]
毕钊, 侯胜利. 基于R语言SARIMA模型的航材需求预测分析[J]. 价值工程, 2019, 38(15): 151-154.
Bi Zhao, Hou Shengli. Aircraft spare parts demand forecasting based on R language and SARIMA model[J]. Value Engineering, 2019, 38(15): 151-154.
[4]
Teunter R H, Syntetos A A, Babai M Z. Inter-mittent demand: linking forecasting to inventory obsoles-cence[J]. European Journal of Operational Research, 2011, 214(3): 606-615.
[5]
曾浩然, 冯蕴雯, 路成, . 基于支持向量机回归的民用飞机航材消耗预测研究[J]. 航空工程进展, 2021, 12(5): 75-79.
Zeng Haoran, Feng Yunwen, Lu Cheng, et al. Forecast study on civil aviation material consumption based on support vector machine regression[J]. Advances in Aeronautical Engineering, 2021, 12(5): 75-79.
[6]
付维方, 穆彩虹, 刘英杰. 基于机器学习方法的航空消耗件需求自适应预测[J]. 科学技术与工程, 2022, 22(11): 4609-4617.
Fu Weifang, Mu Caihong, Liu Yingjie. Adaptive demand prediction of aviation consumable spare parts based on machine learning method[J]. Science Technology and Engineering, 2022, 22(11): 4609-4617.
[7]
刘旭, 周丽华, 朱臣. 基于PCA-SVM的航材需求预测方法研究[J]. 舰船电子工程, 2017, 37(7): 105-109.
Liu Xu, Zhou Lihua, Zhu Chen. Prediction of air material requirement based on PCA-SVM[J]. Ship Electronic Engineering, 2017, 37(7): 105-109.
[8]
李晓娟, 张芳媛, 喻玲. 基于主成分分析-BP神经网络的风电备件需求预测[J]. 科学技术与工程, 2024, 24(1): 281-288.
Li Xiaojuan, Zhang Fangyuan, Yu Ling. Wind power spare parts demand forecasting based on PCA-BP neural network[J]. Science Technology and Engineering, 2024, 24(1): 281-288.
[9]
李黄琪, 蔡开龙, 郝明, . 基于GRA-IPSO-SVM的航材携行需求预测研究[J]. 航空工程进展, 2022, 13(6): 166-172.
Li Huangqi, Cai Kailong, Hao Ming, et al. Research on forecasting of aviation material carrying demand based on GRA-IPSO-SVM[J]. Advances in Aeronautical Engineering, 2022, 13(6): 166-172.
[10]
李长云, 李亭立, 何频捷, . 基于关联规则及组合模型的面料需求预测[J]. 科学技术与工程, 2022, 22(35): 15697-15707.
Li Changyun, Li Tingli, He Pinjie, et al. Fabric demand prediction based on association rule and combination model[J]. Science Technology and Engineering, 2022, 22(35): 15697-15707.
[11]
孙绳山, 徐常凯, 何亚群. 基于RS-PSO-SVM的航材消耗预测模型[J]. 南京航空航天大学学报, 2021, 53(6): 881-887.
Sun Shengshan, Xu Changkai, He Yaqun. Prediction model of air material consumption based on RS-PSO-SVM[J]. Journal of Nanjing University of Aeronautics and Astronautics, 2021, 53(6): 881-887.
[12]
宋传洲, 王瑞奇, 刘战. 面向任务携行航材消耗影响因素研究[J]. 航空维修与工程, 2020(8): 68-71.
Song Chuanzhou, Wang Ruiqi, Liu Zhan. Research on the influencing factors of consumption for mission-oriented carrying aviation materials[J]. Aviation Maintenance and Engineering, 2020(8): 68-71.
[13]
宋传洲, 王瑞奇, 刘天庆, . 基于XGBoost-GRA-DEMATEL面向任务携行航材消耗预测方法[J]. 航空兵器, 2021, 28(4): 88-96.
Song Chuanzhou, Wang Ruiqi, Liu Tianqing, et al. A mission-oriented aircraft spare parts carried consumption prediction method based on XGBoost-GRA-DEMATEL[J]. Aviation Weapons, 2021, 28(4): 88-96.
[14]
吴先慧. 基于主成分分析和DEA方法的我国区域创新效率评价[D]. 哈尔滨: 哈尔滨工业大学, 2011.
Wu Xianhui. The evaluation of Chinese regional innovation efficiency based on principal component analysis and DATA envelopment analysis[D]. Harbin: Harbin Institute of Technology, 2011.
[15]
岳斯玮. 主成分分析在生态城市建设能力评价中的应用研究[D]. 成都: 成都理工大学, 2011.
Yue Siwei. The Applied research on principal component analysis in the capacity-building evaluation of ecological city[D]. Chengdu: Chengdu University of Technology, 2011.
[16]
孙世政, 向洋, 党晓圆, . 基于粒子群解耦算法的FBG流量温度复合传感研究[J]. 仪器仪表学报, 2022, 43(1): 2-10.
Sun Shizheng, Xiang Yang, Dang Xiaoyuan, et al. Research on FBG flow temperature composite sensor based on PSO decoupling algorithm[J]. Chinese Journal of Scientific Instrument, 202, 43(1): 2-10.
[17]
张万胜. 基于PCA-IPSO-GNN模型的铁路月度客运量预测模型研究[J]. 中国公共安全(学术版), 2018(2): 122-127.
Zhang Wansheng. Research of railway monthly volume forecast model based on PCA-IPSO-GNN model[J]. China Public Security (Academic Edition), 2018(2): 122-127.
[18]
张平, 李亚民, 王冠霖, . 基于IPSO-LSSVM的离心式压缩机性能预测方法[J]. 油气储运, 2023, 42(1): 79-86.
Zhang Ping, Li Yamin, Wang Guanlin, et al. Performance prediction method of centrifugal compressor based on IPSO-LSSVM[J]. Oil and Gas Storage and Transportation, 2023, 42(1): 79-86.
[19]
李文强, 刘颖. 基于灰色关联分析与PLS-LSSVM的航材备件需求预测模型[J]. 数学的实践与认识, 2021, 51(7): 54-60.
Li Wenqiang, Liu Ying. The prediction model of airlines spare parts based on grey-relational analysis and PLS-LSSVM[J]. Mathematical Practice and Understanding, 2021, 51(7): 54-60.
2025年第25卷第9期
PDF下载
399
166
引用本文
BibTeX
文章信息
doi: 10.12404/j.issn.1671-1815.2400770
  • 接收时间:2024-01-26
  • 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:2024-01-26
  • 修回日期:2024-12-04
基金
2023年度中央高校基本科研业务费资助项目-青年基金(QJ2023-006)
作者信息
    1 中国民用航空飞行学院飞机修理厂, 广汉 618307
    2 中国民用航空飞行学院广汉分院, 广汉 618307
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2400770
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