Multi-dimensional evaluation of power battery safety risk of pure electric bus based on big data
YU Jiangbin
ZHANG Xin
ZHANG Yongtao
CHANG liang
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.
Keywords：pure electric buspower batterybig datasafety risk evaluation
Publication Date：2023-10-28
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：9( 98-106 )