改进PSO优化LSSVM的锂电池SOC估算模型

为提高锂电池荷电状态(SOC)的估算精度,提出一种改进粒子群优化(PSO)算法;对最小二乘支持向量机(LSSVM)的惩罚参数C和核函数参数σ进行寻优,建立基于改进PSO-LSSVM的锂电池SOC估算模型.对磷酸铁锂充放电实验数据进行仿真分析,结果表明:改进PSO-LSSVM模型的平均相对误差为2.96%,均方根误差为0.018,全局最大相对误差为4.79%;改进PSO-LSSVM模型明显提高锂电池SOC估算精度.

Lithium Battery SOC Estimation Model Based on Improved PSO and Optimized LSSVM

In order to improve the estimation accuracy of state of charge(SOC)of lithium battery, an improved particle swarm optimization(PSO)algorithm is proposed to optimize the penalty parameter C and kernel function parameter σ of least squares support vector machine(LSSVM), and a SOC estimation model of lithium battery based on improved PSO-LSSVM is established. The charge-discharge experimental data of FePO₄ are simulated and analyzed, the results show that the average relative error of the improved PSO-LSSVM model is 2.96%, the root mean square error is 0.018, and the global maximum relative error is 4.79%, which shows that the improved PSO-LSSVM model can significantly improve the SOC estimation accuracy of lithium battery.