基于改进支持向量回归机的锂离子电池剩余寿命预测

Prediction for Lithium-ion Battery Remaining Useful Life Based on Improved SVR

为提高电动汽车锂离子电池剩余循环寿命预测的准确性,提出了一种基于改进支持向量回归机的预测算法,利用免疫完全学习型粒子群优化算法对支持向量回归机的惩罚系数和超参数进行优化,增强其预测能力,基于NASA PCoE研究中心提供的锂电池测量数据,与完全学习型粒子群优化的支持向量回归机预测算法进行对比分析,仿真结果显示,本文提出的算法预测相对误差低于6%,容量预测平均相对误差低于0.4%,具有更好的预测性能。

In order to improve the prediction accuracy of the remaining useful life of lithium ion batteries in electric vehicles, a prediction algorithm based on Support Vector Regression(SVR) machine was proposed, the Complete Learning Particle Swarm Optimization(CLPSO) algorithm based on Artificial Immune System(AIS) was utilized to optimize the penalty coefficients and hyper-parameters of SVR to enhance its prediction ability. Based on lithium battery measured data provided by NASA PCoE research center, this paper made comparative analysis with CLPSO SVR prediction algorithm, the simulation results show that the relative error of the proposed algorithm is less than 6%, mean relative error of capacity prediction is less than 0.4%, thus it has better prediction ability.