湖北汽车工业学院学报2023，Vol.37Issue(4)：22-26,31,6.DOI:10.3969/j.issn.1008-5483.2023.04.005
基于LSTM的电池组工作状态预测
Working State Prediction of Battery Pack Based on LSTM
摘要
Abstract
The long short-term memory(LSTM)neural network was used to predict the voltage,current,and state of charge(SOC)of the battery.A multi-parameter LSTM model containing acceleration,vehi-cle speed,voltage,current,and SOC was determined by considering the influence of driving behavior on the working state of the battery pack.Then,the LSTM model was trained,tested,and predicted by using the Adam optimization algorithm based on the data of China Yiwei new energy vehicle cloud platform.The experimental results show that the multi-parameter LSTM model can effectively predict the SOC and voltage change state of the battery,and the mean square error of current can be reduced from 14.848%to 3.192%.关键词
锂离子电池/长短期记忆神经网络/电池参数预测/驾驶行为Key words
lithium-ion batteries/long short-term memory neural network/battery parameter predic-tion/driving behavior分类
交通工程引用本文复制引用
李轩谊,赵慧勇..基于LSTM的电池组工作状态预测[J].湖北汽车工业学院学报,2023,37(4):22-26,31,6.基金项目
汽车零部件技术湖北省协同创新项目(2015XTZX0403) （2015XTZX0403）
