遗传算法优化支持向量机的光伏阵列故障诊断研究

Research on fault diagnosis of photovoltaic array based on Support Vector Machine optimized by Genetic Algorithm

研究了支持向量机(SVM)方法在光伏阵列故障诊断上的运用,对光伏阵列的输出特性以及故障类型进行了分析总结。支持向量机由于存在惩罚因子系数与核函数系数,在选用径向基核函数后通过遗传算法对其参数进行寻优,通过Matlab仿真实验得到数据,利用寻优后的参数建立模型训练与验证。研究结果表明:支持向量机使用通过遗传算法优化得到的参数在光伏阵列故障诊断上有较高的准确度。

The application of Support Vector Machine(SVM)in photovoltaic array fault diagnosis is studied.The output characteristics and fault types of photovoltaic arrays are analyzed and summarized.Because of the existence of penalty factor coefficient and kernel function coefficient,the Support Vector Machine is optimized by Genetic Algorithm after choosing the radial basis function,and the model is established by using the optimized parameters.The data are obtained through Matlab simulation experiment and the model is trained and validated.The results show that the Support Vector Machine optimized by Genetic Algorithm has high accuracy.