摘要
铅酸蓄电池作为变电站直流电源系统的核心设备,随着投运时间的增长,将会发生内阻增大、容量减小问题,从而导致铅酸蓄电池组的使用寿命减小。因此,研究铅酸蓄电池的寿命预测方法,对于保障变电站的安全稳定运行具有重要作用。在介绍支持向量机的基本原理的基础上,结合铅酸蓄电池的样本数据,通过交叉验证选取LIBSVM回归机最优参数,通过支持向量机回归预测模型建立铅酸蓄电池的寿命预测模型。实验结果表明,基于LIBSVM的铅酸蓄电池寿命预测模型具有较高的预测精度,该方法是切实可行的。
As the core of the DC power supply system, the performance of the lead-acid battery is the safe and stable operation of the whole substation. With the use of lead-acid battery pack time increases, the battery’s internal resistance will increase, the battery capacity will be reduced, resulting in lead-acid battery life. Therefore, it is of great significance to study the life prediction of lead-acid battery. Based on the basic principle of support vector machine (SVM) and the sample data of lead-acid battery, the optimal parameters of LIBSVM regression machine are selected by cross validation, and the life prediction model of lead-acid battery is established by support vector machine regression model. The experimental results show that the LIBSVM-based lead-acid battery life prediction model has high prediction accuracy, and the method is feasible.
