首页 期刊 论文 学科刊群 资讯 加盟 关于
EN
image
Article(id=1149773876458124104, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149773869357167407, articleNumber=null, orderNo=null, doi=10.12404/j.issn.1671-1815.2404534, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1718640000000, receivedDateStr=2024-06-18, revisedDate=1737648000000, revisedDateStr=2025-01-24, acceptedDate=null, acceptedDateStr=null, onlineDate=1752057053912, onlineDateStr=2025-07-09, pubDate=1746633600000, pubDateStr=2025-05-08, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1752057053912, onlineIssueDateStr=2025-07-09, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1752057053912, creator=13701087609, updateTime=1752057053912, updator=13701087609, issue=Issue{id=1149773869357167407, tenantId=1146029695717560320, journalId=1146123166801305609, year='2025', volume='25', issue='13', pageStart='5273', pageEnd='5704', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1752057052207, creator=13701087609, updateTime=1768456769392, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1218559268744253990, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149773869357167407, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1218559268744253991, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149773869357167407, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=5696, endPage=5704, ext={EN=ArticleExt(id=1149773876869165897, articleId=1149773876458124104, tenantId=1146029695717560320, journalId=1146123166801305609, language=EN, title=Comprehensive Evaluation of Aircraft Fire Risk Based on Random Forest Algorithm, columnId=1156262729993277777, journalTitle=Science Technology and Engineering, columnName=Papers·Environmental and Safe Science, runingTitle=null, highlight=null, articleAbstract=

In order to solve the problems of imperfect fire risk management system and subjective and one-sided risk assessment methods of civil aviation transport aircraft, a comprehensive risk assessment method based on random forest ensemble algorithm was proposed for the analysis and evaluation of risk factor indicators. Firstly, according to the man machine environment management(MMEM) theory, the risk index system was established based on the investigation of the causes of aircraft fire accidents in the past 20 years, and then the scores of scholars and experts in related fields on the correlation between the indicators were collected, and the subjective risk index weight results were obtained by using the analytic network process(ANP) method. The causes of major aircraft fire accidents in the database in the past 20 years were counted and their prior probabilities were calculated by classification, and the Bayesian network(BN) dynamic analysis method was used for reverse reasoning to obtain the probability distribution of each risk factor. The random forest regression model was established to obtain the predicted value and importance of the characteristic index, and put forward scientific and effective suggestions for the fire risk control of the operating unit. The results show that the five indicators of missing dangerous goods in security inspection, failure to eliminate hidden dangers in time, component failure, bird strike, and high surface temperature are the most critical risk factors in aircraft fire accidents.

, correspAuthors=Rong-ze ZHOU, 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=Yang SONG, Rong-ze ZHOU), CN=ArticleExt(id=1149773902219538937, articleId=1149773876458124104, tenantId=1146029695717560320, journalId=1146123166801305609, language=CN, title=基于随机森林算法的航空器火灾风险综合评价, columnId=1156262730140078420, journalTitle=科学技术与工程, columnName=论文·环境科学、安全科学, runingTitle=null, highlight=null, articleAbstract=

为解决民航运输航空器火灾风险管理体系不健全、风险评价方法较主观、片面的问题,针对风险因素指标的分析与评估提出一种基于随机森林集成算法的综合风险评价方法。首先,根据“人-机-环-管”系统(man machine environment management,MMEM)理论以近20年的航空器火灾事故原因调查情况建立风险指标体系;其次,采集相关领域研究学者专家对指标之间关联关系的评分,采用网络分析(analytic network process,ANP)进行评价分析获取主观性的风险指标权重结果;统计数据库内20年中重大航空器火灾事故的致因情况并分类计算其先验概率,采用贝叶斯网络(Bayesian network,BN)动态分析方法进行逆向推理,获得各风险因素的概率分布情况;最后,引入随机森林算法综合分析指标主客观赋权情况,建立随机森林回归模型得到特征指标预测值及重要度,为运行单位进行火灾风险控制提出科学有效的建议。研究结果表明,5项指标安检遗漏危险品、隐患未及时排除、零部件故障、鸟击、地表温度过高是航空器火灾事故中最关键的风险因素。

, correspAuthors=周融泽, authorNote=null, correspAuthorsNote=
* 周融泽(2000—),女,汉族,内蒙古巴彦淖尔人,硕士研究生。研究方向:航空器火灾风险研究与应急管理。E-mail:。
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=FNqWBWVSBOcfu6JmOgeFsg==, magXml=GyYtYucJZX0eLaeVN9zAPg==, pdfUrl=null, pdf=0tDABw6WMFZnnX9nUI78Lg==, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=YAh3pQXEFKtZ/DL0s9ssPw==, mapNumber=null, authorCompany=null, fund=null, authors=

宋洋(1977—),男,汉族,天津人,博士,教授。研究方向:民用机场建筑信息模型(BIM)、航站楼火灾精细化仿真及应急管理。E-mail:。

, authorsList=宋洋, 周融泽)}, authors=[Author(id=1175114485787407332, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=y-song@cauc.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1175114485896459239, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, authorId=1175114485787407332, language=EN, stringName=Yang SONG, firstName=Yang, middleName=null, lastName=SONG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Civil Aviation Key Laboratory of Thermal Disaster Prevention and Emergency Response, Civil Aviation University of China, Tianjin 300300, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1175114485980345320, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, authorId=1175114485787407332, language=CN, stringName=宋洋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 中国民航大学民航热灾害防控与应急重点实验室, 天津 300300, bio={"content":"

宋洋(1977—),男,汉族,天津人,博士,教授。研究方向:民用机场建筑信息模型(BIM)、航站楼火灾精细化仿真及应急管理。E-mail:。

"}, bioImg=null, bioContent=

宋洋(1977—),男,汉族,天津人,博士,教授。研究方向:民用机场建筑信息模型(BIM)、航站楼火灾精细化仿真及应急管理。E-mail:。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1175114485523166173, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, xref=1, ext=[AuthorCompanyExt(id=1175114485527360478, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, companyId=1175114485523166173, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Civil Aviation Key Laboratory of Thermal Disaster Prevention and Emergency Response, Civil Aviation University of China, Tianjin 300300, China), AuthorCompanyExt(id=1175114485535749087, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, companyId=1175114485523166173, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国民航大学民航热灾害防控与应急重点实验室, 天津 300300)])]), Author(id=1175114486051648490, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=rongzez2000@163.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1175114486110368748, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, authorId=1175114486051648490, language=EN, stringName=Rong-ze ZHOU, firstName=Rong-ze, middleName=null, lastName=ZHOU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, *, address=2 School of Safety Science and Engineering, Civil Aviation University of China, Tianjin 300300, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1175114486164894701, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, authorId=1175114486051648490, language=CN, stringName=周融泽, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, *, address=2 中国民航大学安全科学与工程学院, 天津 300300, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1175114485665772512, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, xref=2, ext=[AuthorCompanyExt(id=1175114485669966817, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, companyId=1175114485665772512, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 School of Safety Science and Engineering, Civil Aviation University of China, Tianjin 300300, China), AuthorCompanyExt(id=1175114485678355426, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, companyId=1175114485665772512, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 中国民航大学安全科学与工程学院, 天津 300300)])])], keywords=[Keyword(id=1175114486311695342, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, language=EN, orderNo=1, keyword=aircraft fires), Keyword(id=1175114486378804207, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, language=EN, orderNo=2, keyword=analytic hierarchy process), Keyword(id=1175114486454301680, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, language=EN, orderNo=3, keyword=Bayesian networks), Keyword(id=1175114486529799153, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, language=EN, orderNo=4, keyword=random forests), Keyword(id=1175114486605296626, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, language=EN, orderNo=5, keyword=risk assessment), Keyword(id=1175114486659822579, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, language=CN, orderNo=1, keyword=航空器火灾), Keyword(id=1175114486747902964, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, language=CN, orderNo=2, keyword=网络层次分析), Keyword(id=1175114486810817525, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, language=CN, orderNo=3, keyword=贝叶斯网络), Keyword(id=1175114486865343478, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, language=CN, orderNo=4, keyword=随机森林), Keyword(id=1175114486915675127, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, language=CN, orderNo=5, keyword=风险评价)], refs=[Reference(id=1175114489012826124, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=柏羽珊, journalName=大型客机火灾风险评估, refType=null, unstructuredReference=柏羽珊. 大型客机火灾风险评估[D]. 沈阳: 沈阳航空航天大学, 2021., articleTitle=null, refAbstract=null), Reference(id=1175114489071546381, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=Bai Yushan, journalName=Fire risk assessment of large passenger aircraft, refType=null, unstructuredReference=Bai Yushan. Fire risk assessment of large passenger aircraft[D]. Shenyang: Shenyang University of Aeronautics and Astronautics, 2021., articleTitle=null, refAbstract=null), Reference(id=1175114489188986894, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, doi=null, pmid=null, pmcid=null, year=2022, volume=10, issue=11, pageStart=1685, pageEnd=null, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=Zhang H Y, Li C F, Zhao N, journalName=Journal of Marine Science and Engineering, refType=null, unstructuredReference=Zhang H Y, Li C F, Zhao N, et al. Fire risk assessment in engine rooms considering the fire-induced domino effects[J]. Journal of Marine Science and Engineering, 2022, 10(11): 1685., articleTitle=Fire risk assessment in engine rooms considering the fire-induced domino effects, refAbstract=null), Reference(id=1175114489247707151, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, doi=null, pmid=null, pmcid=null, year=2022, volume=10, issue=20, pageStart=3799, pageEnd=null, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=Chen J H, Li K, Yang S, journalName=Mathematics, refType=null, unstructuredReference=Chen J H, Li K, Yang S. Electric vehicle fire risk assessment based on WBS-RBS and fuzzy BN coupling[J]. Mathematics, 2022, 10(20): 3799., articleTitle=Electric vehicle fire risk assessment based on WBS-RBS and fuzzy BN coupling, refAbstract=null), Reference(id=1175114489306427408, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://aviation-safety.net, language=null, rfNumber=[4], rfOrder=4, authorNames=Harro R, journalName=null, refType=null, unstructuredReference=Harro R. ASN aviation safety database(safety issue list-fire)[DB/OL]. (2021-01-24) [2024-06-18]. https://aviation-safety.net., articleTitle=ASN aviation safety database(safety issue list-fire), refAbstract=null), Reference(id=1175114489377730577, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://skybrary.aero, language=null, rfNumber=[5], rfOrder=5, authorNames=EUROCONTROL, ICAO, journalName=null, refType=null, unstructuredReference=EUROCONTROL, ICAO. Accident and serious incident reports fire[DB/OL]. (2021-01-24)[2024-06-18]. https://skybrary.aero., articleTitle=Accident and serious incident reports fire, refAbstract=null), Reference(id=1175114489432256530, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=10, pageStart=29, pageEnd=35, url=null, language=null, rfNumber=[6], rfOrder=6, authorNames=黄鑫, 白荟琳, 周晓猛, journalName=安全, refType=null, unstructuredReference=黄鑫, 白荟琳, 周晓猛. 民用飞机火灾应急处置现状及发展趋势[J]. 安全, 2022, 43(10): 29-35., articleTitle=民用飞机火灾应急处置现状及发展趋势, refAbstract=null), Reference(id=1175114489503559699, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=10, pageStart=29, pageEnd=35, url=null, language=null, rfNumber=[6], rfOrder=7, authorNames=Huang Xin, Bai Huilin, Zhou Xiaomeng, journalName=Safety, refType=null, unstructuredReference=Huang Xin, Bai Huilin, Zhou Xiaomeng. Present situation and development trend of aircraft fire emergency disposal in China[J]. Safety, 2022, 43(10): 29-35., articleTitle=Present situation and development trend of aircraft fire emergency disposal in China, refAbstract=null), Reference(id=1175114489595834388, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=25, pageStart=10946, pageEnd=10955, url=null, language=null, rfNumber=[7], rfOrder=8, authorNames=吴波, 李雅婷, 徐世祥, journalName=科学技术与工程, refType=null, unstructuredReference=吴波, 李雅婷, 徐世祥, 等. 基于博弈论组合赋权-灰关联投影法的山岭隧道突涌水风险评价[J]. 科学技术与工程, 2024, 24(25): 10946-10955., articleTitle=基于博弈论组合赋权-灰关联投影法的山岭隧道突涌水风险评价, refAbstract=null), Reference(id=1175114489704886293, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=25, pageStart=10946, pageEnd=10955, url=null, language=null, rfNumber=[7], rfOrder=9, authorNames=Wu Bo, Li Yating, Xu Shixiang, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Wu Bo, Li Yating, Xu Shixiang, et al. Risk assessment of water inrush in mountain tunnels based on game theory combinatorial weighting-gray correlation projection method[J]. Science Technology and Engineering, 2024, 24(25): 10946-10955., articleTitle=Risk assessment of water inrush in mountain tunnels based on game theory combinatorial weighting-gray correlation projection method, refAbstract=null), Reference(id=1175114489767800854, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, doi=null, pmid=null, pmcid=null, year=2024, volume=50, issue=3, pageStart=82, pageEnd=87, url=null, language=null, rfNumber=[8], rfOrder=10, authorNames=刘立萍, 刘海明, 王雅歌, journalName=水力发电, refType=null, unstructuredReference=刘立萍, 刘海明, 王雅歌, 等. 基于G1-熵权-可拓理论的边坡风险评价[J]. 水力发电, 2024, 50(3): 82-87., articleTitle=基于G1-熵权-可拓理论的边坡风险评价, refAbstract=null), Reference(id=1175114489902018583, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, doi=null, pmid=null, pmcid=null, year=2024, volume=50, issue=3, pageStart=82, pageEnd=87, url=null, language=null, rfNumber=[8], rfOrder=11, authorNames=Liu Liping, Liu Haiming, Wang Yage, journalName=Hydroelectric Engineering, refType=null, unstructuredReference=Liu Liping, Liu Haiming, Wang Yage, et al. Slope risk assessment based on G1-entropy weight-extensibility theory[J]. Hydroelectric Engineering, 2024, 50(3): 82-87., articleTitle=Slope risk assessment based on G1-entropy weight-extensibility theory, refAbstract=null), Reference(id=1175114490002681880, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, doi=null, pmid=null, pmcid=null, year=2023, volume=14, issue=1, pageStart=2240943, pageEnd=null, url=null, language=null, rfNumber=[9], rfOrder=12, authorNames=Sun N, Li C L, Guo B Y, journalName=Geomatics, Natural Hazards and Risk, refType=null, unstructuredReference=Sun N, Li C L, Guo B Y, et al. Urban flooding risk assessment based on FAHP-EWM combination weighting: a case study of Beijing[J]. Geomatics, Natural Hazards and Risk, 2023, 14(1): 2240943., articleTitle=Urban flooding risk assessment based on FAHP-EWM combination weighting: a case study of Beijing, refAbstract=null), Reference(id=1175114490053013529, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, doi=null, pmid=null, pmcid=null, year=2020, volume=20, issue=4, pageStart=1228, pageEnd=1235, url=null, language=null, rfNumber=[10], rfOrder=13, authorNames=贾进章, 陈怡诺, journalName=安全与环境学报, refType=null, unstructuredReference=贾进章, 陈怡诺. 基于网络层次分析-灰色聚类法的高层建筑火灾风险分析[J]. 安全与环境学报, 2020, 20(4): 1228-1235., articleTitle=基于网络层次分析-灰色聚类法的高层建筑火灾风险分析, refAbstract=null), Reference(id=1175114490120122394, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, doi=null, pmid=null, pmcid=null, year=2020, volume=20, issue=4, pageStart=1228, pageEnd=1235, url=null, language=null, rfNumber=[10], rfOrder=14, authorNames=Jia Jinzhang, Chen Yinuo, journalName=Journal of Safety and Environment, refType=null, unstructuredReference=Jia Jinzhang, Chen Yinuo. Fire risk analysis of high-rise buildings based on network analytic hierarchy process-grey clustering method[J]. Journal of Safety and Environment, 2020, 20(4): 1228-1235., articleTitle=Fire risk analysis of high-rise buildings based on network analytic hierarchy process-grey clustering method, refAbstract=null), Reference(id=1175114490174648347, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, doi=null, pmid=null, pmcid=null, year=2023, volume=43, issue=22, pageStart=5596, pageEnd=5600, url=null, language=null, rfNumber=[11], rfOrder=15, authorNames=陈玲, 郝志梅, 魏霞霞, journalName=中国老年学杂志, refType=null, unstructuredReference=陈玲, 郝志梅, 魏霞霞, 等. 基于贝叶斯网络的老年人失能风险预测模型构建[J]. 中国老年学杂志, 2023, 43(22): 5596-5600., articleTitle=基于贝叶斯网络的老年人失能风险预测模型构建, refAbstract=null), Reference(id=1175114490258534428, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, doi=null, pmid=null, pmcid=null, year=2023, volume=43, issue=22, pageStart=5596, pageEnd=5600, url=null, language=null, rfNumber=[11], rfOrder=16, authorNames=Chen Ling, Hao Zhimei, Wei Xiaxia, journalName=Chinese Journal of Gerontology, refType=null, unstructuredReference=Chen Ling, Hao Zhimei, Wei Xiaxia, et al. Construction of disability risk prediction model for the elderly based on Bayesian network[J]. Chinese Journal of Gerontology, 2023, 43(22): 5596-5600., articleTitle=Construction of disability risk prediction model for the elderly based on Bayesian network, refAbstract=null), Reference(id=1175114490329837597, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=15, pageStart=6700, pageEnd=6706, url=null, language=null, rfNumber=[12], rfOrder=17, authorNames=李航, 聂芳艺, journalName=科学技术与工程, refType=null, unstructuredReference=李航, 聂芳艺. 基于贝叶斯网络的物流无人机碰撞风险评估[J]. 科学技术与工程, 2023, 23(15): 6700-6706., articleTitle=基于贝叶斯网络的物流无人机碰撞风险评估, refAbstract=null), Reference(id=1175114490396946462, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=15, pageStart=6700, pageEnd=6706, url=null, language=null, rfNumber=[12], rfOrder=18, authorNames=Li Hang, Nie Fangyi, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Li Hang, Nie Fangyi. Collision risk assessment of logistics UAV based on Bayesian network[J]. Science Technology and Engineering, 2023, 23(15): 6700-6706., articleTitle=Collision risk assessment of logistics UAV based on Bayesian network, refAbstract=null), Reference(id=1175114490464055327, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, doi=null, pmid=null, pmcid=null, year=2023, volume=30, issue=6, pageStart=40, pageEnd=47, url=null, language=null, rfNumber=[13], rfOrder=19, authorNames=陈星霖, 林卫东, 黄晓冬, journalName=安全与环境工程, refType=null, unstructuredReference=陈星霖, 林卫东, 黄晓冬, 等. 基于模糊贝叶斯网络的超高层建筑火灾风险评估[J]. 安全与环境工程, 2023, 30(6): 40-47., articleTitle=基于模糊贝叶斯网络的超高层建筑火灾风险评估, refAbstract=null), Reference(id=1175114490602467360, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, doi=null, pmid=null, pmcid=null, year=2023, volume=30, issue=6, pageStart=40, pageEnd=47, url=null, language=null, rfNumber=[13], rfOrder=20, authorNames=Chen Xinglin, Lin Weidong, Huang Xiaodong, journalName=Safety and Environmental Engineering, refType=null, unstructuredReference=Chen Xinglin, Lin Weidong, Huang Xiaodong, et al. Fire risk assessment of super high-rise buildings based on fuzzy Bayesian network[J]. Safety and Environmental Engineering, 2023, 30(6): 40-47., articleTitle=Fire risk assessment of super high-rise buildings based on fuzzy Bayesian network, refAbstract=null), Reference(id=1175114490707324961, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, doi=null, pmid=null, pmcid=null, year=2024, volume=26, issue=2, pageStart=318, pageEnd=331, url=null, language=null, rfNumber=[14], rfOrder=21, authorNames=谭翠, 黄钦, 杨波, journalName=地球信息科学学报, refType=null, unstructuredReference=谭翠, 黄钦, 杨波, 等. 随机森林算法在区域生态旅游适宜性评价中的应用研究[J]. 地球信息科学学报, 2024, 26(2): 318-331., articleTitle=随机森林算法在区域生态旅游适宜性评价中的应用研究, refAbstract=null), Reference(id=1175114490770239522, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, doi=null, pmid=null, pmcid=null, year=2024, volume=26, issue=2, pageStart=318, pageEnd=331, url=null, language=null, rfNumber=[14], rfOrder=22, authorNames=Tan Cui, Huang Qin, Yang Bo, journalName=Journal of Geo-information Science, refType=null, unstructuredReference=Tan Cui, Huang Qin, Yang Bo, et al. Application of random forest algorithm in regional ecotourism suitability evaluation[J]. Journal of Geo-information Science, 2024, 26(2): 318-331., articleTitle=Application of random forest algorithm in regional ecotourism suitability evaluation, refAbstract=null), Reference(id=1175114490917040163, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, doi=null, pmid=null, pmcid=null, year=2024, volume=45, issue=8, pageStart=4802, pageEnd=4811, url=null, language=null, rfNumber=[15], rfOrder=23, authorNames=刘靖宇, 李若怡, 梁永春, journalName=环境科学, refType=null, unstructuredReference=刘靖宇, 李若怡, 梁永春, 等. 基于特征优选和机器学习的塔里木盆地东缘绿洲土壤镉元素含量预测及健康风险评价[J]. 环境科学, 2024, 45(8): 4802-4811., articleTitle=基于特征优选和机器学习的塔里木盆地东缘绿洲土壤镉元素含量预测及健康风险评价, refAbstract=null), Reference(id=1175114490992537636, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, doi=null, pmid=null, pmcid=null, year=2024, volume=45, issue=8, pageStart=4802, pageEnd=4811, url=null, language=null, rfNumber=[15], rfOrder=24, authorNames=Liu Jingyu, Li Ruoyi, Liang Yongchun, journalName=Environmental Science, refType=null, unstructuredReference=Liu Jingyu, Li Ruoyi, Liang Yongchun, et al. Prediction of cadmium content in soil oasis in the eastern margin of tarim basin based on feature optimization and machine learning and health risk assessment[J]. Environmental Science, 2024, 45(8): 4802-4811., articleTitle=Prediction of cadmium content in soil oasis in the eastern margin of tarim basin based on feature optimization and machine learning and health risk assessment, refAbstract=null), Reference(id=1175114491051257893, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=3, pageStart=717, pageEnd=null, url=null, language=null, rfNumber=[16], rfOrder=25, authorNames=Alexis P, L W M C, Yang C, journalName=Sensors, refType=null, unstructuredReference=Alexis P, L W M C, Yang C. Evaluation of random forests (RF) for regional and local-scale wheat yield prediction in southeast Australia[J]. Sensors, 2022, 22(3): 717., articleTitle=Evaluation of random forests (RF) for regional and local-scale wheat yield prediction in southeast Australia, refAbstract=null), Reference(id=1175114491101589542, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, doi=null, pmid=null, pmcid=null, year=2024, volume=33, issue=null, pageStart=101091, pageEnd=null, url=null, language=null, rfNumber=[17], rfOrder=26, authorNames=Sémanou K D, Abudu R K, Rikiatu H, journalName=Remote Sensing Applications: Society and Environment, refType=null, unstructuredReference=Sémanou K D, Abudu R K, Rikiatu H, et al. Analysis of the future potential impact of environmental and climate changes on wildfire spread in Ghana's ecological zones using a random forest (RF) machine learning approach[J]. Remote Sensing Applications: Society and Environment, 2024, 33: 101091., articleTitle=Analysis of the future potential impact of environmental and climate changes on wildfire spread in Ghana's ecological zones using a random forest (RF) machine learning approach, refAbstract=null), Reference(id=1175114491151921191, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, doi=null, pmid=null, pmcid=null, year=2022, volume=52, issue=6, pageStart=1957, pageEnd=1970, url=null, language=null, rfNumber=[18], rfOrder=27, authorNames=王雪冬, 张超彪, 王翠, journalName=吉林大学学报(地球科学版), refType=null, unstructuredReference=王雪冬, 张超彪, 王翠, 等. 基于Logistic回归与随机森林的和龙市地质灾害易发性评价[J]. 吉林大学学报(地球科学版), 2022, 52(6): 1957-1970., articleTitle=基于Logistic回归与随机森林的和龙市地质灾害易发性评价, refAbstract=null), Reference(id=1175114491202252840, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, doi=null, pmid=null, pmcid=null, year=2022, volume=52, issue=6, pageStart=1957, pageEnd=1970, url=null, language=null, rfNumber=[18], rfOrder=28, authorNames=Wang Xuedong, Zhang Chaobiao, Wang Cui, journalName=Journal of Jilin University (Earth Science Edition), refType=null, unstructuredReference=Wang Xuedong, Zhang Chaobiao, Wang Cui, et al. Geological hazard susceptibility evaluation of Helong City based on Logistic regression and random forest[J]. Journal of Jilin University (Earth Science Edition), 2022, 52(6): 1957-1970., articleTitle=Geological hazard susceptibility evaluation of Helong City based on Logistic regression and random forest, refAbstract=null), Reference(id=1175114491269361705, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, doi=null, pmid=null, pmcid=null, year=2021, volume=28, issue=5, pageStart=36, pageEnd=42, url=null, language=null, rfNumber=[19], rfOrder=29, authorNames=张建荣, 张伟, 薛楠楠, journalName=安全与环境工程, refType=null, unstructuredReference=张建荣, 张伟, 薛楠楠, 等. 基于随机森林算法的塔式起重机安全事故预测及致因分析[J]. 安全与环境工程, 2021, 28(5): 36-42., articleTitle=基于随机森林算法的塔式起重机安全事故预测及致因分析, refAbstract=null), Reference(id=1175114491319693354, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, doi=null, pmid=null, pmcid=null, year=2021, volume=28, issue=5, pageStart=36, pageEnd=42, url=null, language=null, rfNumber=[19], rfOrder=30, authorNames=Zhang Jianrong, Zhang Wei, Xue Nannan, journalName=Safety and Environmental Engineering, refType=null, unstructuredReference=Zhang Jianrong, Zhang Wei, Xue Nannan, et al. Prediction and causal analysis of tower crane safety accident based on random forest algorithm[J]. Safety and Environmental Engineering, 2021, 28(5): 36-42., articleTitle=Prediction and causal analysis of tower crane safety accident based on random forest algorithm, refAbstract=null)], funds=[Fund(id=1175114488870219787, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, awardId=RZH2022-KF-04, language=CN, fundingSource=中国民航大学民航热灾害防控与应急重点实验室开放基金(RZH2022-KF-04), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1175114485523166173, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, xref=1, ext=[AuthorCompanyExt(id=1175114485527360478, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, companyId=1175114485523166173, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Civil Aviation Key Laboratory of Thermal Disaster Prevention and Emergency Response, Civil Aviation University of China, Tianjin 300300, China), AuthorCompanyExt(id=1175114485535749087, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, companyId=1175114485523166173, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国民航大学民航热灾害防控与应急重点实验室, 天津 300300)]), AuthorCompany(id=1175114485665772512, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, xref=2, ext=[AuthorCompanyExt(id=1175114485669966817, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, companyId=1175114485665772512, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 School of Safety Science and Engineering, Civil Aviation University of China, Tianjin 300300, China), AuthorCompanyExt(id=1175114485678355426, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, companyId=1175114485665772512, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 中国民航大学安全科学与工程学院, 天津 300300)])], figs=[ArticleFig(id=1175114487150556152, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, language=EN, label=Fig.1, caption=ANP model for aircraft fire risk management, figureFileSmall=0EsB4oaCiNX98W0+voQKJw==, figureFileBig=RlK+CKhV2fkg/od2DbPlSQ==, tableContent=null), ArticleFig(id=1175114487247025145, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, language=CN, label=图1, caption=航空器火灾风险管理ANP模型, figureFileSmall=0EsB4oaCiNX98W0+voQKJw==, figureFileBig=RlK+CKhV2fkg/od2DbPlSQ==, tableContent=null), ArticleFig(id=1175114487343494138, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, language=EN, label=Fig.2, caption=Bayesian network model of aircraft fire risk, figureFileSmall=JR0eVlI+pPegmmmAZM9o6A==, figureFileBig=vBmntETH+W4UkjG4+Oc9ow==, tableContent=null), ArticleFig(id=1175114487414797307, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, language=CN, label=图2, caption=航空器火灾风险贝叶斯网络模型

叶节点T表示发生航空器火灾事故的总体风险概率,中间节点C1~C4表示四大类引发航空器火灾事故的风险因素,根节点C11~C44表示引发航空器火灾事故的具体风险因素指标

, figureFileSmall=JR0eVlI+pPegmmmAZM9o6A==, figureFileBig=vBmntETH+W4UkjG4+Oc9ow==, tableContent=null), ArticleFig(id=1175114487502877692, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, language=EN, label=Fig.3, caption=Random forest inteqration method, figureFileSmall=Od57qbTbTUkVYf2d80T36w==, figureFileBig=3jRSJKq+Pdj0VqTL7CH+yg==, tableContent=null), ArticleFig(id=1175114487561597949, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, language=CN, label=图3, caption=随机森林集成方式, figureFileSmall=Od57qbTbTUkVYf2d80T36w==, figureFileBig=3jRSJKq+Pdj0VqTL7CH+yg==, tableContent=null), ArticleFig(id=1175114487695815678, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, language=EN, label=Fig.4, caption=Decision tree instance, figureFileSmall=ai12z6mVMqPbBdwYW7n1qg==, figureFileBig=Wxef/Z7f5NqqM5owTWONrA==, tableContent=null), ArticleFig(id=1175114487813256191, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, language=CN, label=图4, caption=决策树示例, figureFileSmall=ai12z6mVMqPbBdwYW7n1qg==, figureFileBig=Wxef/Z7f5NqqM5owTWONrA==, tableContent=null), ArticleFig(id=1175114487892947968, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, language=EN, label=Fig.5, caption=Bayesian network parameter results, figureFileSmall=mKfnWXGXJRnfOfpIjkxoNw==, figureFileBig=WIPKcWjDZ/r4YVihj5Fl9A==, tableContent=null), ArticleFig(id=1175114487993610240, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, language=CN, label=图5, caption=贝叶斯网络参数学习结果

yes表示该事件发生的概率;no表示该事件不发生的概率

, figureFileSmall=mKfnWXGXJRnfOfpIjkxoNw==, figureFileBig=WIPKcWjDZ/r4YVihj5Fl9A==, tableContent=null), ArticleFig(id=1175114488102662145, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, language=EN, label=Fig.6, caption=Random forest decision tree, figureFileSmall=lAbP0kDTNqW9rRDDyviOSg==, figureFileBig=jr4fNTyIedLcJELY8VMQng==, tableContent=null), ArticleFig(id=1175114488199131138, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, language=CN, label=图6, caption=随机森林决策树

x[ ]表示节点分类时使用的特征值及其阈值;squared error表示当前节点的均方误差,用于衡量节点中样本的预测误差;samples表示当前节点中包含的样本数量;value表示当前节点的预测值

, figureFileSmall=lAbP0kDTNqW9rRDDyviOSg==, figureFileBig=jr4fNTyIedLcJELY8VMQng==, tableContent=null), ArticleFig(id=1175114488266240003, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, language=EN, label=Fig.7, caption=Random forest feature importance, figureFileSmall=rnpTaPWPYx42veRI/dsSMg==, figureFileBig=8woZH30V/QSGEQCXtXIOig==, tableContent=null), ArticleFig(id=1175114488316571652, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, language=CN, label=图7, caption=随机森林特征重要性, figureFileSmall=rnpTaPWPYx42veRI/dsSMg==, figureFileBig=8woZH30V/QSGEQCXtXIOig==, tableContent=null), ArticleFig(id=1175114488366903301, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, language=EN, label=Table 1, caption=

Statistics of aircraft fire accidents from 2000 to 2021

, figureFileSmall=null, figureFileBig=null, tableContent=
年份 火灾事故数量/件 年份 火灾事故数量/件
2000 5 2011 9
2001 1 2012 2
2002 4 2013 10
2003 0 2014 0
2004 1 2015 3
2005 0 2016 6
2006 3 2017 5
2007 3 2018 7
2008 1 2019 10
2009 0 2020 1
2010 3 2021 2
), ArticleFig(id=1175114488450789382, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, language=CN, label=表1, caption=

2000—2021年航空器火灾事故统计

, figureFileSmall=null, figureFileBig=null, tableContent=
年份 火灾事故数量/件 年份 火灾事故数量/件
2000 5 2011 9
2001 1 2012 2
2002 4 2013 10
2003 0 2014 0
2004 1 2015 3
2005 0 2016 6
2006 3 2017 5
2007 3 2018 7
2008 1 2019 10
2009 0 2020 1
2010 3 2021 2
), ArticleFig(id=1175114488505315335, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, language=EN, label=Table 2, caption=

Indicators of risk factors for aircraft fire accidents

, figureFileSmall=null, figureFileBig=null, tableContent=
安全管理目标 控制层要素 风险因素指标
航空器
火灾事故		 人为因素
P1		 相关人员操作失误C11
操作人员安全意识薄弱C12
设备维护存在问题C13
安全隐患未及时排除C14
机械因素
P2
静电起火C21
过度摩擦产生火花C22
发动机故障C23
燃油泄漏C24
其他零部件故障C25
机油泄漏C26
电气故障C27
机械因素
P2
火灾探测系统故障C28
锂电池燃烧C29
环境因素
P3
机体附近出现火源C31
鸟击C32
地表温度过高C33
恶劣天气C34
低空风切变C35
管理因素
P4
安全检查不到位C41
使用零部件不合规C42
危险品安置不合理C43
安检遗漏危险品C44
), ArticleFig(id=1175114488568229896, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, language=CN, label=表2, caption=

航空器火灾事故风险因素指标

, figureFileSmall=null, figureFileBig=null, tableContent=
安全管理目标 控制层要素 风险因素指标
航空器
火灾事故		 人为因素
P1		 相关人员操作失误C11
操作人员安全意识薄弱C12
设备维护存在问题C13
安全隐患未及时排除C14
机械因素
P2
静电起火C21
过度摩擦产生火花C22
发动机故障C23
燃油泄漏C24
其他零部件故障C25
机油泄漏C26
电气故障C27
机械因素
P2
火灾探测系统故障C28
锂电池燃烧C29
环境因素
P3
机体附近出现火源C31
鸟击C32
地表温度过高C33
恶劣天气C34
低空风切变C35
管理因素
P4
安全检查不到位C41
使用零部件不合规C42
危险品安置不合理C43
安检遗漏危险品C44
), ArticleFig(id=1175114488635338761, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, language=EN, label=Table 3, caption=

Risk actor indicator priority weight ranking

, figureFileSmall=null, figureFileBig=null, tableContent=
控制层 权重 网络层 权重 极限权重 排序
P1 0.204 68 C11 0.240 42 0.080 868 7
C12 0.251 30 0.084 529 5
C13 0 0 19
C14 0.508 29 0.170 971 1
P2 0.289 46 C21 0.133 41 0.066 177 12
C22 0.219 68 0.108 969 8
C23 0.078 73 0.039 053 15
C24 0.036 14 0.017 927 17
C25 0.034 09 0.016 910 18
C26 0.058 51 0.029 024 16
C27 0.149 59 0.074 201 11
C28 0.203 92 0.101 150 9
C29 0.085 93 0.042 626 14
P3 0.096 49 C31 0.5 0.004 078 3
C32 0 0 20
C33 0.5 0.004 078 4
C34 0 0 21
C35 0 0 22
P4 0.409 36 C41 0.162 12 0.025 849 10
C42 0.090 74 0.014 468 13
C43 0.505 13 0.080 537 2
C44 0.242 00 0.038 585 6
), ArticleFig(id=1175114488736002058, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773876458124104, language=CN, label=表3, caption=

风险因素指标优先度权重排序

, figureFileSmall=null, figureFileBig=null, tableContent=
控制层 权重 网络层 权重 极限权重 排序
P1 0.204 68 C11 0.240 42 0.080 868 7
C12 0.251 30 0.084 529 5
C13 0 0 19
C14 0.508 29 0.170 971 1
P2 0.289 46 C21 0.133 41 0.066 177 12
C22 0.219 68 0.108 969 8
C23 0.078 73 0.039 053 15
C24 0.036 14 0.017 927 17
C25 0.034 09 0.016 910 18
C26 0.058 51 0.029 024 16
C27 0.149 59 0.074 201 11
C28 0.203 92 0.101 150 9
C29 0.085 93 0.042 626 14
P3 0.096 49 C31 0.5 0.004 078 3
C32 0 0 20
C33 0.5 0.004 078 4
C34 0 0 21
C35 0 0 22
P4 0.409 36 C41 0.162 12 0.025 849 10
C42 0.090 74 0.014 468 13
C43 0.505 13 0.080 537 2
C44 0.242 00 0.038 585 6
)], attaches=null, journal=Journal(id=1146119176004939786, delFlag=0, nameCn=科学技术与工程, nameEn=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, issn=1671-1815, eissn=, cn=11-4688/T, coden=null, periodic=4, language=CN, oaType=是, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=UKU/O7GSka5polgCTkbIIw==, journalPrice=null, startedYear=null, abbrevIsoEn=Sci Technol Eng, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1754445529766, createdBy=null, updatedBy=13701087609, firstLetterCn=S, firstLetterEn=S, subjectCode=Natural Sciences, subjectName=自然科学, subjectCodeEn=Natural Sciences, subjectNameEn=null, picCn=UKU/O7GSka5polgCTkbIIw==, picEn=5hwlULoNwcbj3xUmVi9MAQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1159791870395564357, language=CN, name=科学技术与工程, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529793, updatedTime=1754445529793, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=http://www.stae.com.cn/jsygc/site/menus/20090429150146001, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1159791870441701702, language=EN, name=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529804, updatedTime=1754445529804, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1146123166801305609, websiteList=[Website(id=1148243202391400884, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/kxjsygc/CN, language=CN, createTime=1751692112777, createBy=18614031015, updateTime=1753520965431, updateBy=18614031015, name=科学技术与工程-中文站点, tplId=1146099689490845704, title=科学技术与工程, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148622798802673703, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=articleTextType, value=kx, createTime=1751782615614, updateTime=1751782615614, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798781702180, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=banner, value=null, createTime=1751782615609, updateTime=1751782615609, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798769119267, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1751782615606, updateTime=1751782615606, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798794285094, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751782615612, updateTime=1751782615612, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798790090789, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751782615611, updateTime=1751782615611, creator=18614031015, updator=18614031015)]), Website(id=1155914124811976731, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/kxjsygc/EN, language=EN, createTime=1753521003206, createBy=18614031015, updateTime=1753521003206, updateBy=18614031015, name=科学技术与工程-英文站点, tplId=1146101810881728533, title=Science Technology and Engineering, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155914371227308235, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=articleTextType, value=kx, createTime=1753521061952, updateTime=1753521061952, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371210531016, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=banner, value=null, createTime=1753521061947, updateTime=1753521061947, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371202142407, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1753521061945, updateTime=1753521061945, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371223113930, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753521061950, updateTime=1753521061950, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371218919625, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753521061949, updateTime=1753521061949, creator=18614031015, updator=18614031015)])], journalTitle=科学技术与工程, weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=Science Technology and Engineering, journalPhotoCn=UKU/O7GSka5polgCTkbIIw==, journalPhotoEn=5hwlULoNwcbj3xUmVi9MAQ==, journalFirstLetter=S, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=null, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2404534, detailUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2404534, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/PDF/10.12404/j.issn.1671-1815.2404534, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/PDF/10.12404/j.issn.1671-1815.2404534, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于随机森林算法的航空器火灾风险综合评价
收藏切换
PDF下载
宋洋 1 , 周融泽 2, *
科学技术与工程 | 论文·环境科学、安全科学 2025,25(13): 5696-5704
收起
收藏切换
科学技术与工程 | 论文·环境科学、安全科学 2025, 25(13): 5696-5704
基于随机森林算法的航空器火灾风险综合评价
全屏
宋洋1 , 周融泽2, *
作者信息
  • 1 中国民航大学民航热灾害防控与应急重点实验室, 天津 300300
  • 2 中国民航大学安全科学与工程学院, 天津 300300

    • 宋洋(1977—),男,汉族,天津人,博士,教授。研究方向:民用机场建筑信息模型(BIM)、航站楼火灾精细化仿真及应急管理。E-mail:。

通讯作者:

* 周融泽(2000—),女,汉族,内蒙古巴彦淖尔人,硕士研究生。研究方向:航空器火灾风险研究与应急管理。E-mail:。
Comprehensive Evaluation of Aircraft Fire Risk Based on Random Forest Algorithm
Yang SONG1 , Rong-ze ZHOU2, *
Affiliations
  • 1 Civil Aviation Key Laboratory of Thermal Disaster Prevention and Emergency Response, Civil Aviation University of China, Tianjin 300300, China
  • 2 School of Safety Science and Engineering, Civil Aviation University of China, Tianjin 300300, China
出版时间: 2025-05-08 doi: 10.12404/j.issn.1671-1815.2404534
文章导航
收藏切换
摘要
收起

为解决民航运输航空器火灾风险管理体系不健全、风险评价方法较主观、片面的问题,针对风险因素指标的分析与评估提出一种基于随机森林集成算法的综合风险评价方法。首先,根据“人-机-环-管”系统(man machine environment management,MMEM)理论以近20年的航空器火灾事故原因调查情况建立风险指标体系;其次,采集相关领域研究学者专家对指标之间关联关系的评分,采用网络分析(analytic network process,ANP)进行评价分析获取主观性的风险指标权重结果;统计数据库内20年中重大航空器火灾事故的致因情况并分类计算其先验概率,采用贝叶斯网络(Bayesian network,BN)动态分析方法进行逆向推理,获得各风险因素的概率分布情况;最后,引入随机森林算法综合分析指标主客观赋权情况,建立随机森林回归模型得到特征指标预测值及重要度,为运行单位进行火灾风险控制提出科学有效的建议。研究结果表明,5项指标安检遗漏危险品、隐患未及时排除、零部件故障、鸟击、地表温度过高是航空器火灾事故中最关键的风险因素。

航空器火灾  /  网络层次分析  /  贝叶斯网络  /  随机森林  /  风险评价

In order to solve the problems of imperfect fire risk management system and subjective and one-sided risk assessment methods of civil aviation transport aircraft, a comprehensive risk assessment method based on random forest ensemble algorithm was proposed for the analysis and evaluation of risk factor indicators. Firstly, according to the man machine environment management(MMEM) theory, the risk index system was established based on the investigation of the causes of aircraft fire accidents in the past 20 years, and then the scores of scholars and experts in related fields on the correlation between the indicators were collected, and the subjective risk index weight results were obtained by using the analytic network process(ANP) method. The causes of major aircraft fire accidents in the database in the past 20 years were counted and their prior probabilities were calculated by classification, and the Bayesian network(BN) dynamic analysis method was used for reverse reasoning to obtain the probability distribution of each risk factor. The random forest regression model was established to obtain the predicted value and importance of the characteristic index, and put forward scientific and effective suggestions for the fire risk control of the operating unit. The results show that the five indicators of missing dangerous goods in security inspection, failure to eliminate hidden dangers in time, component failure, bird strike, and high surface temperature are the most critical risk factors in aircraft fire accidents.

aircraft fires  /  analytic hierarchy process  /  Bayesian networks  /  random forests  /  risk assessment
宋洋, 周融泽. 基于随机森林算法的航空器火灾风险综合评价. 科学技术与工程, 2025 , 25 (13) : 5696 -5704 . DOI: 10.12404/j.issn.1671-1815.2404534
Yang SONG, Rong-ze ZHOU. Comprehensive Evaluation of Aircraft Fire Risk Based on Random Forest Algorithm[J]. Science Technology and Engineering, 2025 , 25 (13) : 5696 -5704 . DOI: 10.12404/j.issn.1671-1815.2404534
正文
收起
国际民航正随着科技的进步获得巨大的发展和进步,经过多年来的发展,民航运输体量逐渐增大,与此同时,影响运行安全的风险也越来越多,其中航空器火灾对民航运输业的发展影响巨大。特别是由于民用航空器载油量大,载客量多,机舱内部各种材料十分多样,而机舱内部空间狭小,航空器一旦出现火灾,将会引发不可预估的严重后果。因此航空器火灾的预防和治理在航空器设计制造、运行管理等领域也应当更加重视。近年来,许多国内外学者针对航空器火灾的风险进行深入研究,柏羽珊[1]通过故障树分析法对大型客机火灾事故进行分析,建立风险评估指标体系同时又采用层次分析法和熵权法结合计算指标权重进而对大型客机的火灾风险进行评估。Zhang等[2]提出逻辑与多米诺效应动态分析的机舱火灾风险评估方法,利用矩阵计算和蒙特卡洛仿真计算机舱火灾的动态概率模型,分别针对不同设备单元进行模拟极端,找到3个发生火灾概率最高危险性最高的初始火源位置,为精准控制火灾扩散做出科学的评估和测算。Chen等[3]通过构建工作分解结构模型,对火灾事故风险结构进行分解,构建WBS-RBS耦合矩阵进行风险识别,采用贝叶斯网络进行半定量的火灾风险评估。
综上所述,对于航空器火灾风险评估的研究中,学者们从不同的角度构建评价指标体系选择适合研究体系的评价模型,但由于航空器火灾事件的相关数据难以获取,各风险因素中的关联关系错综复杂,目前很少有能够有效兼顾客观数据和主观风险分析的综合性风险评价方法。因此,现提出一种基于随机森林算法的航空器火灾风险评价方法,不仅通过网络分析法对风险因素权重进行确定,还采用贝叶斯网络分析方法通过已统计得出的客观数据获取风险指标的客观权重,最后通过随机森林集成算法、主客观权重及逆行组合处理,以此实现对航空器火灾风险的有效评估。
1 风险评价指标体系
收起
“人-机-环-管”(man machine environment management,MMEM)系统理论,是在“人-机-环境系统工程学”中三要素之间相互作用相互影响的基础上加入“管理”这一发挥协调和控制作用的第四要素,构成完整的安全管理系统的四大要素,用以满足生产任务中对安全管理的需求。结合航空安全网(Aviation Safety Network)[4]和SKY Brary[5]中公布的事故数据,整理2000—2021年航空器火灾事故数据,如表1所示。
其中,2007年一架B737-809客机在地面区域放行滑出,滑行后油箱被刺破,燃料泄漏,引发火情,经调查由于维修时相应组件存在安全隐患而相关人员未上报,机组、运控等各部门认为航班符合放行要求,开车滑行,引发火灾;2016年一架B757-200由于燃料管错误安装使得发动机起火;2019年一架Cessa560XLS公务机在降落时与ILS信号天线发生撞击,燃油泄漏导致火灾等类似由于相关工组人员的操作或工作出现问题而导致事故,在研究中将此类事故的主要原因划分为人为因素;2007年一架B777-222ER客机在地面运行阶段发动机电缆产生电气故障,内部电弧短路起火,从机舱地板下方开始燃烧;2011年一架B767-300客机液压系统故障,飞机降落后起落架自动收回,飞机重着陆冲向跑道引发火灾;2021年一架B777-200飞机,高空飞行时发动机故障,单个风扇叶片内部疲劳开裂导致起火,类似航空器由于突发的设备设施故障相关原因而导致起火,在研究的数据中占很大一部分比重,此类事故的主要原因划分为机械因素;2011年一架B747-400F驾驶舱后部存储着锂电池等易燃危险品货物,使得飞机在空中发生起火;2019年一架B737-900客机乘客行李中充电宝在货舱存放,其内含的锂电池过热导致火灾,等等类似的由于航空器上危险品的存放或登机前携带物品安全检查不规范导致事故,在研究中此类事故的主要原因划分为管理因素;2018年一架B737-800进场降落阶段遇低空风切变导致航空器未能成功停止滑跑,冲出跑道引发火灾;2021年一架B737-200在降雪后滑行制动失败,冲出跑道,与物体撞击发生火灾;2021年一架A320neo航行过程中遭遇鸟击,导致发动机燃油泄漏,引发起火,由于客观环境中气温、天气等其他外部因素的变化导致航空器失火,在研究中此类事故原因划分为环境因素。
针对以上四大类主要要素,根据事故原因具体特征再进行进一步细化分类,排除其他主观外部因素和坠机导致整机起火事故,主要引发航空器火灾事故的重点部位包括发动机、油箱、电气电缆故障、货舱内危险品和制动系统[6]。依据以上统计数据及详细的事故原因分析,对航空器火灾事故风险按照风险因素的识别、分析评估以及提出风险控制应对措施的流程进行综合评价研究。
结合上述航空器火灾事故数据统计,依照MMEM理论,对其风险要素进行细分,构建航空器火灾事故风险因素指标体系如表2所示。
2 算法设计
收起
2.1 风险评价算法思路
基于指标的风险评价结果主要受风险指标权重的影响,因此风险指标权重的计算方法选择决定着最终结果是否真实科学有效。权重计算主要包括主观与客观赋权的方法,主观赋权法多依赖于专家评分,其结果受专家的主观意见影响程度高,评分倾向因专家对研究对象的认知程度及研究方向而异,且缺少数据支撑,评价结果稳定性低。客观赋权法依据数据之间的关系确定权重,但民航运输业发展时间较短、现行的事故数据库统计不能保证全面,且航空器火灾事故案例数据量较小,评价结果存在一定的随机性。
因此,将机器学习方法引入风险评价的研究,对风险指标的赋权法进行组合研究[7],通过集成学习算法将传统的赋权方法相互结合进行优化,提升评价结果的可靠性[8],算法设计思路如图1所示。
2.2 ANP主观赋权
网络分析法(analytic network process,ANP)最早由匹兹堡大学T L Saaty教授提出,网络层次分析法[9-10]在层次分析法(analytic hierarchy process,AHP)的基础上进行了改进,在决策中加入了对非独立层次间指标相互影响的考量,形成一个指标与层次相互依存的网络结构。
2.2.1 ANP模型构建
基于表2航空器火灾事故风险因素指标体系,确定ANP网络划分准则,结合火灾事故原因调查及相关专家意见,确定风险元素的划分并明确其相互影响关系,搭建ANP网络结构,以安全管理目标为网络的总目标;以MMEM理论划分的要素作为控制层要素,分别为人为因素P1、机械因素P2、环境因素P3、管理因素P4;以风险因素指标为网络层元素以Cij表示。共同组成表示相互影响关系的ANP结构模型,如图1所示。
2.2.2 ANP判断矩阵
根据以上网络中各元素之间的关联性,确定控制层中各元素之间的关联性,依次选择控制层元素作为主准则,以某一维度中具体元素为次准则,将其他具体元素与次准则进行两两比较,并结合事故调查以及相关专家意见,对该矩阵中两元素的相对重要性采用九分法进行标注,得到两两判断矩阵。
2.2.3 超矩阵计算
依照判断矩阵构建方式,选定控制层一元素作为主准则,选定网络层中某一维度组中一个元素为次准则,将次准则与其他元素进行两两比较,将已经构建的判断矩阵进行归一化处理,得到归一化特征向量,网络中所有元素的特征向量汇总得到未加权超矩阵W。
主准则依旧选择控制层元素,网络层中一维度组作为次准则,进行组与组之间的比较,并进行归一化处理将归一化特征向量汇总,根据式(1)进行计算,得到加权超矩阵W1。通过对超矩阵进行稳定处理,依照式(2)计算极限超矩阵W∞。
$\boldsymbol{W}_{1}=\boldsymbol{W} \boldsymbol{A}$
$\boldsymbol{W}_{\infty}=\lim _{x \rightarrow \infty} \boldsymbol{W}^{x}$
式中:W为该网络的未加权超矩阵;A为权矩阵,由加权因子aij组成。
最后得到各风险因素的优先度权重,并进行排序,如表3所示。该优先度权重结果则为航空器火灾风险主观评价结果,为了一定程度地避免个别专家主观思想对结果的影响程度过大,收集多位专家及相关学者的打分结果对该风险因素网络进行评分,对其优先度权重进行数据处理,作为主观赋权法的评价结果。
2.3 BN客观赋权
贝叶斯网络(Bayesian network,BN)是以贝叶斯概率公式为基础而构成的一个有向无环图,利用节点表示随机事件,有向边表示节点间的相互关系,采用对应的条件概率表达节点之间的关系强度[11-12]。
2.3.1 BN模型构建
基于表2的风险因素体系,确定网络的节点及拓扑结构,同时根据前期航空器重大事故数据的统计,以航空器火灾事故发生的频率表示火灾事故的概率,同时对各风险因素导致航空器发生事故的条件概率进行统计与计算,最后根据所确定的节点随机变量和其概率分布确定模型结构,如图2所示。
2.3.2 节点概率分布
(1)根节点先验概率。以风险因素发生的基本概率作为各根节点为“1”时的先验概率,按照“0”“1” 概率之和为1 的原则,确定各根节点的先验概率。
(2)非根节点的条件概率。条件概率又称后验概率,是指在A事件已经发生的情况下,B事件发生的概率,表示为P(B|A),通过式(3)进行计算。
P(B|A)= P ( A B ) P ( A )
式(3)中:P(AB)为A、B事件同时发生的概率;P(A)为A事件发生的概率。
2.3.3 模型推理预测
整理节点及其概率数据,利用GeNIe软件,搭建贝叶斯网络结构,并输入个节点的概率进行参数学习,输入结果则为贝叶斯网络动态分析基础。基于贝叶斯网络的推理学习功能,利用软件的逆向推理功能[13],对贝叶斯网络进行动态更新,将目标节点“航空器火灾事故”状态设为“1”,通过逆向推理,得到不同控制层因素导致事故发生条件下各节点的后验概率。记录每一类情况下火灾事故发生的风险因素逆向推理结果,作为客观赋权法的结果。
2.4 随机森林算法——组合分析
随机森林(random forest,RF)算法是Bagging集成学习算法[14],随机森林模型通过组合多个相互独立的分类归回决策树,将每一个决策树的预测结果进行均值处理得到最终组合决策树随机森林的回归预测结果。通俗来讲,是指通过构建若干个并联的决策树作为子模型,分别执行同样的目标任务,然后每个子模型各自执行自己的预测任务,输出相应的结果,最后对所有子模型的结果进行综合处理,因此最终的预测结果由全部子模型共同决定。该集成过程如图3所示。
2.4.1 组合赋权——主客观数据混合
将所有专家基于ANP法运算所得的风险指标权重数据归一化处理与贝叶斯网络动态分析所得的逆向推理概率分布情况归一化后,组合构建风险指标权重主客观数据集,利用Bagging集成算法在该数据集,通过有放回抽样发方式,分别选出K个新的数据集,对每一颗决策树分别进行独立训练,保证各决策树间不存在相互关联关系[15]。
充分混合的主客观权重数据通过完全随机的抽取方式进行组合不存在任何主观倾向,能够在一定程度上保证数据选择的科学性。
2.4.2 子模型——分类回归决策树
分类回归决策树(classification and regression tree,CART)把所有决策树分为二叉树,将每个特征的取值设置为“0”和“1”,依次将特征进行二分,在随机森林构建决策树时会将特征进行随机组合构成一定深度的决策树,进行回归预测,预测模型如图4所示。
2.4.3 集成实现——随机森林模型训练
通过有放回的抽取数据样本的方式,搭建不同特征样本训练模型的决策树,进行非线性拟合特征与样本数据之间的关系,得到不同的训练结果。进行预测时,选取多个模型中回归结果的平均值,作为该集成评估器的最终预测结果。
由于其每一个子模型的构成数据都在数据训练集中有放回的随机抽取,既保证了每棵树的训练模型都保留各自抽取部分数据的个性,不同模型训练的结果最后求均值才能充分考虑数据的多样性情况。
基于python语言搭建随机森林模型,利用训练集数据输入模型组成的进行训练,此时的主客观权重完全随机的混乱排列在随机森林中,训练模型从中随机选取,多次重复的进行抽取训练[16],该模型的测试结果逐渐趋向真实值。
2.4.4 指标评价——精确度验证及特征重要性计算
训练完成后,将测试集数据输入模型进行特征值预测计算,采用平均绝对百分比误差(mean absolute percentage error,MAPE)作为精确度验证指标[17],以确定该训练模型与真实情况的拟合情况。
由于集成算法采取随机放回抽取数据的方式,该过程使得特征重要性十分易得。得到的特征重要性则可以作为风险评价中最终对风险因素指标重要程度的评价结果。
3 案例分析
收起
以近期民航运输航空器运行现状算例,运用所建立风险因素指标体系及风险评价算法,对航空器火灾事故发生的特征分析,找到导致事故发生的关键因素指标。该算例共收集统计了20位专家学者的评分结果,民航运输航空器重大事故1 378件,其中火灾事故69件,并根据所建立的风险指标体系对事故原因进行对应分类统计。
3.1 主观赋权
(1)ANP模型。以航空器火灾风险为基准,确定指标层和网络层要素,如图1所示。
(2)判断矩阵确定。整理统计的专家对指标关系的九分法打分结果,并将该数据输入SD软件中进行分析计算。
(3)超矩阵及优先度计算。在SD软件中,基于网络中的元素指标关系进行计算得到该网络的超矩阵、加权超矩阵,极限化处理后得到极限超矩阵,最后提取各指标因素优先度,并对其进行排序,其中一名专家主观赋权结果输出如表3所示。
(4)误差消除处理。重复(1)~(3)步骤,将20次打分结果进行计算,统计计算结果并进行归一化处理。
3.2 客观赋权
3.2.1 BN模型
根据图2确定的贝叶斯分享网络拓扑结构,建立风险因素指标及研究事件的关系。根据统计的航空器重大事故数据对各节点进行条件概率计算,将计算结果统计输入软件,得到参数学习结果,如图5所示。
3.2.2 BN风险推理预测
通过软件调整叶节点和中间节点的状态进行反向推理,设置不同关键类别风险和事件的组合状态,输出多次一项推理结果,得到根节点事件在不同非根节点组合状态下引发叶节点事件发生的概率分布情况,记录动态分析所得所有概率分布结果,进行归一化处理。
3.3 随机森林组合分析
3.3.1 数据混合与抽样
以风险指标因素作为随机森林中特征值,对主客观指标权重结果进行归一化处理,集成打包利用python中的scikit-learn库进行相关测试实验[18]。首先,进行数据分离,通过有放回的方式从数据集中随机抽取样本,形成训练样本,并规定数据集中70%作为训练集,剩余数据为测试集。
3.3.2 模型集成训练
主客观赋权的风险因素指标权重数值导入随机森林算法模型中,风险因素指标作为特征值,在所有权重数据随机抽取70%进行模型训练,经过以往进行随机森林训练实验的经验,选择100个子模型进行训练既不会导致运算过于庞大也能达到预测值趋于稳定的效果,整体模型的结果也能具有较高的精确度和泛化能力。
模型中共构建了100棵如图6所示的决策树,分别基于不同的训练集数据进行训练学习,输出其预测结果,对这些预测结果进行均值处理,得到最终的随机森林模型预测结果[19],如图7所示。
3.3.3 评价结果输出
以剩余数据为测试集,采用MAPE指标进行预测精确度进行评估,输出误差值为极小值,证明该随机森林训练模型的预测结果具有极大的可信度。
在以上所有的子模型训练过程中,随机森林模型会选择出被利用最多的特征值,该特征值在大部分的基础子模型中都被利用同时又十分靠近根节点,则认为该特征值更重要,因此引入特征重要性的概念,以此作为风险指标对于火灾事故影响的重要程度指标。调用sklearn库中特征重要性函数对特征值的重要性进行计算,得到特征预测值及其重要性程度,并根据特征的重要性程度得分排序,如图7所示。
3.3.4 评价结果分析
根据随机森林组合赋权法计算得到的特征重要性排序,即为综合考虑主客观风险因素指标权重后的航空器火灾风险因素的重要度结果,其中安检遗漏危险品C44、隐患未及时排除C14、零部件故障C28、鸟击C32、地表温度过高C33共5项指标为航空器火灾事故中最关键的风险因素。
针对安检遗漏危险品带给航空器的风险主要是指乘客或机组人员误将携带锂电池的物品等易燃易爆物品带入机舱,航司、机场等相关运行部门应当加强对上机人员的随身物品、托运行李以及运输货物进行严格的筛查与管控,特别是安检人员的工作职责应当引起充足的重视与强调;针对隐患未及时排除的风险主要是指在航空器运行前后进行检查未查出或未重视机体组件存在安全隐患的情况,机场及机务维修公司应当明确航前、过站、航后检查以及定检过程中的正确程序并对相关工作人员的工作能力及职责进行严格的考核与强调;针对零部件故障的风险是指在航空器运行过程中突发的故障情况,此类情况对机组飞行人员及随机维修人员的抗压能力、工作能力以及工作经验都有极高的要求,相关职业培训学校及机构以及航司应对相关人员进行全面的应急处置方法及可能遇到的情况定期进行培训,同时对于跟随航空器参与民航运输工作的机组人员应当持续学习和提高自身的综合能力,才能更好地保障自身和他人的生命财产安全。对于鸟击和地面温度过高的环境因素的风险,所有民航运行单位都应当重视,例如驱鸟、极端天气下起降环境调节等相关工作的日常程序及核查检验标准的设定,最大程度上降低由于环境因素而引发航空器事故的可能性。
4 结论
收起
(1)基于MMEM模型选取22个风险因素,建立了航空器火灾风险因素指标体系。
(2)基于随机森林集成算法,将网络模型所得的风险指标主观权重与贝叶斯网络所得的风险指标客观权重进行组合分析,确定了风险因素指标的重要程度情况。
(3)根据风险指标的重要性,对最关键的5个风险因素提出实际运行过程中风险出现导致事故发生的原因,并提出了各运行单位针对关键风险因素的控制措施及缓解措施的制定与决策提供建议。
风险评价基础数据主要依赖专家评估及一部分航空器重大事故,随机森林集成算法的随机抽取方式一定程度上弥补了数据量较少的缺憾,但在更为丰富的数据基础上,该算法能发挥更加突出的优势,实现更加精确的回归预测。因此,在今后的研究中,有必要收集更全面的数据,以完善针对航空器风险评价的模型。
基金
收起
  • 中国民航大学民航热灾害防控与应急重点实验室开放基金(RZH2022-KF-04)
文献
收起
参考文献 引证文献
排序方式：
[1]
柏羽珊. 大型客机火灾风险评估[D]. 沈阳: 沈阳航空航天大学, 2021.
Bai Yushan. Fire risk assessment of large passenger aircraft[D]. Shenyang: Shenyang University of Aeronautics and Astronautics, 2021.
[2]
Zhang H Y, Li C F, Zhao N, et al. Fire risk assessment in engine rooms considering the fire-induced domino effects[J]. Journal of Marine Science and Engineering, 2022, 10(11): 1685.
[3]
Chen J H, Li K, Yang S. Electric vehicle fire risk assessment based on WBS-RBS and fuzzy BN coupling[J]. Mathematics, 2022, 10(20): 3799.
[4]
Harro R. ASN aviation safety database(safety issue list-fire)[DB/OL]. (2021-01-24) [2024-06-18]. https://aviation-safety.net. https://aviation-safety.net
[5]
EUROCONTROL, ICAO. Accident and serious incident reports fire[DB/OL]. (2021-01-24)[2024-06-18]. https://skybrary.aero. https://skybrary.aero
[6]
黄鑫, 白荟琳, 周晓猛. 民用飞机火灾应急处置现状及发展趋势[J]. 安全, 2022, 43(10): 29-35.
Huang Xin, Bai Huilin, Zhou Xiaomeng. Present situation and development trend of aircraft fire emergency disposal in China[J]. Safety, 2022, 43(10): 29-35.
[7]
吴波, 李雅婷, 徐世祥, 等. 基于博弈论组合赋权-灰关联投影法的山岭隧道突涌水风险评价[J]. 科学技术与工程, 2024, 24(25): 10946-10955.
Wu Bo, Li Yating, Xu Shixiang, et al. Risk assessment of water inrush in mountain tunnels based on game theory combinatorial weighting-gray correlation projection method[J]. Science Technology and Engineering, 2024, 24(25): 10946-10955.
[8]
刘立萍, 刘海明, 王雅歌, 等. 基于G1-熵权-可拓理论的边坡风险评价[J]. 水力发电, 2024, 50(3): 82-87.
Liu Liping, Liu Haiming, Wang Yage, et al. Slope risk assessment based on G1-entropy weight-extensibility theory[J]. Hydroelectric Engineering, 2024, 50(3): 82-87.
[9]
Sun N, Li C L, Guo B Y, et al. Urban flooding risk assessment based on FAHP-EWM combination weighting: a case study of Beijing[J]. Geomatics, Natural Hazards and Risk, 2023, 14(1): 2240943.
[10]
贾进章, 陈怡诺. 基于网络层次分析-灰色聚类法的高层建筑火灾风险分析[J]. 安全与环境学报, 2020, 20(4): 1228-1235.
Jia Jinzhang, Chen Yinuo. Fire risk analysis of high-rise buildings based on network analytic hierarchy process-grey clustering method[J]. Journal of Safety and Environment, 2020, 20(4): 1228-1235.
[11]
陈玲, 郝志梅, 魏霞霞, 等. 基于贝叶斯网络的老年人失能风险预测模型构建[J]. 中国老年学杂志, 2023, 43(22): 5596-5600.
Chen Ling, Hao Zhimei, Wei Xiaxia, et al. Construction of disability risk prediction model for the elderly based on Bayesian network[J]. Chinese Journal of Gerontology, 2023, 43(22): 5596-5600.
[12]
李航, 聂芳艺. 基于贝叶斯网络的物流无人机碰撞风险评估[J]. 科学技术与工程, 2023, 23(15): 6700-6706.
Li Hang, Nie Fangyi. Collision risk assessment of logistics UAV based on Bayesian network[J]. Science Technology and Engineering, 2023, 23(15): 6700-6706.
[13]
陈星霖, 林卫东, 黄晓冬, 等. 基于模糊贝叶斯网络的超高层建筑火灾风险评估[J]. 安全与环境工程, 2023, 30(6): 40-47.
Chen Xinglin, Lin Weidong, Huang Xiaodong, et al. Fire risk assessment of super high-rise buildings based on fuzzy Bayesian network[J]. Safety and Environmental Engineering, 2023, 30(6): 40-47.
[14]
谭翠, 黄钦, 杨波, 等. 随机森林算法在区域生态旅游适宜性评价中的应用研究[J]. 地球信息科学学报, 2024, 26(2): 318-331.
Tan Cui, Huang Qin, Yang Bo, et al. Application of random forest algorithm in regional ecotourism suitability evaluation[J]. Journal of Geo-information Science, 2024, 26(2): 318-331.
[15]
刘靖宇, 李若怡, 梁永春, 等. 基于特征优选和机器学习的塔里木盆地东缘绿洲土壤镉元素含量预测及健康风险评价[J]. 环境科学, 2024, 45(8): 4802-4811.
Liu Jingyu, Li Ruoyi, Liang Yongchun, et al. Prediction of cadmium content in soil oasis in the eastern margin of tarim basin based on feature optimization and machine learning and health risk assessment[J]. Environmental Science, 2024, 45(8): 4802-4811.
[16]
Alexis P, L W M C, Yang C. Evaluation of random forests (RF) for regional and local-scale wheat yield prediction in southeast Australia[J]. Sensors, 2022, 22(3): 717.
[17]
Sémanou K D, Abudu R K, Rikiatu H, et al. Analysis of the future potential impact of environmental and climate changes on wildfire spread in Ghana's ecological zones using a random forest (RF) machine learning approach[J]. Remote Sensing Applications: Society and Environment, 2024, 33: 101091.
[18]
王雪冬, 张超彪, 王翠, 等. 基于Logistic回归与随机森林的和龙市地质灾害易发性评价[J]. 吉林大学学报(地球科学版), 2022, 52(6): 1957-1970.
Wang Xuedong, Zhang Chaobiao, Wang Cui, et al. Geological hazard susceptibility evaluation of Helong City based on Logistic regression and random forest[J]. Journal of Jilin University (Earth Science Edition), 2022, 52(6): 1957-1970.
[19]
张建荣, 张伟, 薛楠楠, 等. 基于随机森林算法的塔式起重机安全事故预测及致因分析[J]. 安全与环境工程, 2021, 28(5): 36-42.
Zhang Jianrong, Zhang Wei, Xue Nannan, et al. Prediction and causal analysis of tower crane safety accident based on random forest algorithm[J]. Safety and Environmental Engineering, 2021, 28(5): 36-42.
2025年第25卷第13期
PDF下载
322
132
引用本文
BibTeX
文章信息
doi: 10.12404/j.issn.1671-1815.2404534
  • 接收时间：2024-06-18
  • 首发时间：2025-07-09
  • 出版时间：2025-05-08
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期：2024-06-18
  • 修回日期：2025-01-24
基金
中国民航大学民航热灾害防控与应急重点实验室开放基金(RZH2022-KF-04)
作者信息
    1 中国民航大学民航热灾害防控与应急重点实验室, 天津 300300
    2 中国民航大学安全科学与工程学院, 天津 300300

通讯作者:

* 周融泽(2000—),女,汉族,内蒙古巴彦淖尔人,硕士研究生。研究方向:航空器火灾风险研究与应急管理。E-mail:。
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2404534
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
科
Family		 属数
Number of
genus		 种数
Number of
species		 占总种数比例
Percentage of
total species (%)		 属
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
相关链接
论文
最新文章
热读文章
热点专题
内参
蓝皮书
产业发展报告
传播力报告
期刊分级目录
资讯
学术新闻
行业新闻
学术会议
行业会议
关于
关于我们
联系我们
北京市海淀区学院南路86号
100081
010-62199257
qkjq@cast.org.cn

中国科学技术协会版权所有 京ICP 备10216604号-4 海淀分局备案 1101084647
科技导报社主办 中国科协信息中心技术支持