Accuracy comparison and improvement for state of health estimation of lithium-ion battery based on random partial recharges and feature engineering

作     者：Xingjun Li Dan Yu Søren Byg Vilsen Daniel Ioan Stroe 

作者机构：Department of EnergyAalborg UniversityAalborg 9220Denmark Department of Mathematical SciencesAalborg UniversityAalborg 9220Denmark Walker Department of Mechanical EngineeringThe University of Texas at AustinAustinTX 78712USA 

出 版 物：《Journal of Energy Chemistry》 (能源化学（英文版）)

年 卷 期：2024年第92卷第5期

页      面：591-604页

核心收录：

学科分类：0820[工学-石油与天然气工程] 0808[工学-电气工程] 0817[工学-化学工程与技术] 08[工学] 0703[理学-化学] 

基　　金：funded by China Scholarship Council.The fund number is 202108320111 and 202208320055 

主　　题：Feature engineering Dynamic forklift aging profile State of health comparison Machine learning Lithium-ion batteries 

摘      要：State of health(SOH)estimation of e-mobilities operated in real and dynamic conditions is essential and *** of existing estimations are based on a fixed constant current charging and discharging aging profiles,which overlooked the fact that the charging and discharging profiles are random and not complete in real *** work investigates the influence of feature engineering on the accuracy of different machine learning(ML)-based SOH estimations acting on different recharging sub-profiles where a realistic battery mission profile is *** features were extracted from the battery partial recharging profiles,considering different factors such as starting voltage values,charge amount,and charging sliding ***,features were selected based on a feature selection pipeline consisting of filtering and supervised ML-based subset *** linear regression(MLR),Gaussian process regression(GPR),and support vector regression(SVR)were applied to estimate SOH,and root mean square error(RMSE)was used to evaluate and compare the estimation *** results showed that the feature selection pipeline can improve SOH estimation accuracy by 55.05%,2.57%,and 2.82%for MLR,GPR and SVR *** was demonstrated that the estimation based on partial charging profiles with lower starting voltage,large charge,and large sliding window size is more likely to achieve higher *** work hopes to give some insights into the supervised ML-based feature engineering acting on random partial recharges on SOH estimation performance and tries to fill the gap of effective SOH estimation between theoretical study and real dynamic application.