中北大学学报（自然科学版）2025，Vol.46Issue(3)：293-305,13.DOI:10.62756/jnuc.issn.1673-3193.2024.11.0018
基于数据驱动的电动汽车动力电池故障预测算法
Real Vehicle Fault Prediction Algorithm of Electric Vehicle Based on Data Drive
摘要
Abstract
To solve the problem of real vehicle fault prediction of electric vehicle battery system,a new algorithm for predicting real vehicle fault using Bayesian algorithm to optimize Long Short-Term Memory neural network(LSTM)was proposed.Firstly,the input and output features of LSTM were determined by Pearson correlation coefficient method,which effectively solved the problem of overfitting or underfit-ting of deep learning model caused by large amount of existing engineering data and excessive input and output features.Then,Bayes algorithm was used to optimize the hyperparameters of LSTM,it focused on solving the problem of difficult setting of LSTM hyperparameters,which led to false positives.The final combination of hyperparameters was determined after optimization by Bayes algorithm,and the method of establishing a single battery voltage prediction model to predict the vehicle battery voltage was proposed,which saved the model training time.The median of all single battery voltages under each frame time was determined as a new single battery voltage to train the model,and then the single battery voltage prediction model was established.Through the verification of real vehicle data,RMSE,MAE and MRE of the single unit voltage prediction model based on LSTM decreased by 61.59%,61.31%and 60.94%,respectively,compared with the vehicle voltage prediction model based on LSTM,effec-tively improving the accuracy of real vehicle voltage prediction.Finally,the superiority,reliability and robustness of the proposed voltage prediction model were verified.关键词
电动汽车/故障预测/皮尔逊相关系数/贝叶斯算法/单体预测模型Key words
electric vehicle/fault prediction/pearson correlation coefficient/Bayesian algorithm/cell pre-diction model分类
信息技术与安全科学引用本文复制引用
李晓杰,苏振洋,丁技峰..基于数据驱动的电动汽车动力电池故障预测算法[J].中北大学学报（自然科学版）,2025,46(3):293-305,13.基金项目
山西省重点实验室建设项目(GDZBKKX-10) （GDZBKKX-10）
