粒子群优化
颗粒过滤器
混乱的
电池(电)
控制理论(社会学)
稳健性(进化)
锂离子电池
卡尔曼滤波器
可靠性(半导体)
扩展卡尔曼滤波器
计算机科学
物理
算法
人工智能
化学
基因
控制(管理)
生物化学
功率(物理)
量子力学
作者
Lihua Ye,Sijian Chen,Yefan Shi,Dinghan Peng,Aiping Shi
出处
期刊:International Journal of Electrochemical Science
[ESG]
日期:2023-05-01
卷期号:18 (5): 100122-100122
被引量:9
标识
DOI:10.1016/j.ijoes.2023.100122
摘要
The remaining useful life (RUL) prediction of lithium-ion batteries is crucial to ensure the safety and reliability of electric vehicles. Due to the complexity of the battery aging mechanism, the accurate prediction of RUL by traditional methods is difficult to guarantee. To improve the prediction performance of the particle filter (PF), an improved particle filter based on the chaotic particle swarm optimization algorithm (CPSO-PF) is presented. Then it is applied to predict the RUL of lithium-ion batteries. First, for a better posterior estimate in the PF, CPSO is used to drive the prior distribution of the particles toward a high likelihood probability to obtain a better-proposed distribution, which helps overcome the problem of degeneracy and impoverishment of particles. Then, Three models were employed to track the degradation trajectory of the batteries, including PF、the extended Kalman particle filter (EKPF), and CPSO-PF. Finally, the RUL of lithium-ion batteries was predicted with the three models. The experimental results demonstrate that CPSO-PF has higher prediction accuracy and strong robustness.
科研通智能强力驱动
Strongly Powered by AbleSci AI