基于GAPSO-LSSVM的蓄电池剩余容量联合检测算法

摘要

铅酸蓄电池应用广泛,准确检测其剩余容量是电池管理系统中的重要一环.提出将蓄电池开路电压、温度和内阻三个状态指标作为联合检测量,结合基于GAPSO-LSSVM算法对剩余容量进行检测.在LSSVM算法中引入PSO算法对其惩罚参数和核函数参数进行寻优,避免人为因素干扰,提高了精度.然后再引入GA算法,解决了PSO算法易局部收敛的问题,进一步提升了精度.最后,MATLAB仿真验证了基于GAPSO-LSSVM的联合检测算法在蓄电池剩余容量的检测方面效果良好,平均误差百分比可以控制在3％以内,具有极大的实际应用意义.%The lead-acid battery is widely used,and the estimation of the battery SOC is important for the BMS.The temperature,resistance and the open circuit voltage were employed as the joint detection value,and the LSSVM algorithm with the PSO and GA algorithm was adopted to estimate the battery SOC.The PSO algorithm was used to optimize the penalty parameter and kernel function parameters in LSSVM algorithm to avoid man-made factors and improve the accuracy.In order to solve the problem in PSO algorithm that it trended to converge to local optimal solution,the GA algorithm was needed to enhance its global search ability and accuracy.The MATLAB simulation results verify the joint estimation algorithm is good,and the average error percentage can be controlled within 3％,which means the method has great practical significance.