Intelligent Fault Diagnosis Approach for PV Arrays Based on Sparrow Search Algorithm Optimized Kernel Extreme Learning Machine

In order to accurately identify the fault types of photovoltaic arrays, a fault diagnosis method for PV arrays based on the kernel extreme learning machine optimized by sparrow search algorithm is proposed. Firstly, the output characteristics of photovoltaic arrays in typical fault types are analyzed. Then, the parameters containing the information of the photovoltaic array are used as input variables, and the normal operation, open-circuit, short-circuit, abnormal aging and partial shadow are used as output vectors. The penalty factor and kernel parameter of the kernel extreme learning machine are optimized by the sparrow search algorithm to improve the fault diagnosis accuracy. The example simulation results show that the approach proposed improve the generalization ability and stability of extreme learning machine, and has higher recognition accuracy of photovoltaic array faults than other methods.