计量学报2024，Vol.45Issue(8)：1222-1230,9.DOI:10.3969/j.issn.1000-1158.2024.08.19
基于无迹粒子滤波改进算法的电池容量衰退预测研究
Research on Battery Capacity Decline Prediction Based on Improved Algorithm of Traceless Particle Filtering
摘要
Abstract
In order to improve the accuracy and applicability of battery capacity prediction,an improved algorithm based on traceless particle filtering is proposed.In order to reduce the observation error of the filtering iteration process,a support vector regression algorithm is introduced to improve it.Since the kernel function and penalty factor in the support vector regression algorithm are difficult to determine,it is proposed to use the optimization ability of the genetic algorithm to solve it,forming a model improved by the genetic algorithm and support vector regression.The performance of this fusion model is evaluated and compared with UPF-SVR and UPF-RVR,and the experimental results show that the mean absolute error EMA and root mean square error SRMSE of the fusion model prediction results are lower than 2.0％and 2.5％,respectively,and the prediction accuracy is higher compared with the other models,and at the same time,the prediction level and convergence are significantly better than other models,which is more effective and feasible.关键词
电学计量/电池容量预测/无迹粒子滤波/遗传算法/支持向量回归/寻优能力Key words
electrical measurement/battery capacity prediction/traceless particle filtering/genetic algorithm/support vector regression/optimization ability分类
通用工业技术引用本文复制引用
郭芮君,辛永强,杨剑锋..基于无迹粒子滤波改进算法的电池容量衰退预测研究[J].计量学报,2024,45(8):1222-1230,9.基金项目
甘肃省自然科学基金(23JRRA868) （23JRRA868）
