北京交通大学学报2023，Vol.47Issue(5)：98-106,9.DOI:10.11860/j.issn.1673-0291.20230054
基于大数据的纯电动客车动力电池安全风险多维度评价
Multi-dimensional evaluation of power battery safety risk of pure electric bus based on big data
摘要
Abstract
Based on big data technology,the safety risk of pure electric bus power battery is evaluated in multiple dimensions,aiming at the power battery fault phenomenon caused by multi-factor coupling under real working conditions of pure electric bus.A multi-dimensional safety risk evaluation system of power battery based on analytic hierarchy process and entropy weight method is established.Multi-dimensional quantifiable evaluation indexes are obtained through multi-source data fusion.A random forest model of fault grade prediction is established by machine learning method.Finally,the scheme is verified by data sets provided by digital vehicle competition.The results show that this scheme can predict the fault grade and type of power battery 30 min in advance,and the average accuracy of prediction reaches 97.25%.At the same time,with the 2.59 GHz CPU,it takes 5.6 ms to calculate each set of data,offering excellent real-time performance,which is conducive to technicians and drivers to make timely response measures.关键词
纯电动客车/动力电池/大数据/安全风险评价Key words
pure electric bus/power battery/big data/safety risk evaluation分类
交通工程引用本文复制引用
俞蒋彬,张欣,张永涛,常亮..基于大数据的纯电动客车动力电池安全风险多维度评价[J].北京交通大学学报,2023,47(5):98-106,9.基金项目
国家重点研发计划(2021YFB2501303) National Key R&D Plan(2021YFB2501303) （2021YFB2501303）
