基于SSA-SVM的光伏阵列故障诊断模型

Fault diagnosis model of photovoltaic array based on SSA-SVM

针对支持向量机(Support Vector Machine,SVM)算法在光伏阵列故障诊断过程中,模型诊断精度受惩罚因子和核函数影响而不稳定的问题,提出了一种麻雀搜索算法(Sparrow Search Algorithm,SSA)优化支持向量机的光伏阵列故障诊断模型。通过麻雀搜索算法对支持向量机中的惩罚因子、核函数加以搜索,寻优运算以获得模型的最优参数。实验收集了320组实地故障数据和仿真数据加以整合,通过Matlab/Simulink对各类故障状态数据分析并以寻优后的关键参数构建故障诊断模型。试验结果表明,所提算法与两种对比算法相比在精度上有所提升,故障诊断精度高达100%。

In order to solve the problem that the diagnostic accuracy of the Support Vector Machine algorithm is unstable due to the influence of penalty factor and kernel function in the process of photovoltaic array fault diagnosis,a new photovoltaic array fault diagnosis model based on support vector machine optimized by Sparrow Search Algorithm was proposed.The improved algorithm searches the penalty factor and kernel function in the support vector machine model by the Sparrow Search algorithm and obtains the optimal parameters of the model.In the experiment,320 groups of field fault data and simulation data were collected and integrated.All kinds of fault state data were analyzed by Matlab/Simulink and the fault diagnosis model was built with the optimized key parameters.The experimental results show that compared with the two comparison algorithms,the accuracy of the proposed algorithm is improved,and the fault diagnosis accuracy is up to 100%.