Cuckoo search and BP neural network based fault diagnosis method of photovoltaic assembly

Abstract

The invention provides a cuckoo search (CS) and BP neural network (BPNN) based fault diagnosis method of a photovoltaic assembly. The method comprises the steps that an equivalent circuit model of thephotovoltaic assembly is established, fault data representing a fault type is screened; parameters of the BP neural network and cuckoo search are initialized; coding and optimization training are carried out on the parameters of the BPNN, and the position of an optimal nest at present is recorded; the position of the present nest is updated, and a relatively worse nest position is replaced with the optimal nest position; the weight and threshold of the BPNN are assigned with those of the optimal nest position; input and output are set, and the BNPP model optimized by CS is trained; and a testsample is input, an error amount is calculated, and a result matrix of the fault type is not output until the fault data is mapped to the fault state. The fault diagnosis uses the BP neural network classification algorithm optimized by cuckoo search, parameters are easy to set, the computing complexity is low the convergence speed is high, the diagnosis precision is high, and a diagnosis result is more direct.

Description

technical field [0001] The invention relates to a photovoltaic module fault diagnosis method, in particular to a photovoltaic module fault diagnosis method based on a cuckoo algorithm and a BP neural network. Background technique [0002] As an important energy issue in the sustainable development strategy, it has attracted the attention of researchers. As one of the clean new energy sources, photovoltaic power generation has developed rapidly in recent years. As an important component of a photovoltaic power generation system, photovoltaic modules have become an important topic to diagnose their possible faults. The imagination of fires caused by photovoltaic panel failures often occurs. At present, the maintenance work of photovoltaic power plants relies on manual inspection to judge whether the output characteristics of photovoltaic modules are normal. Usually, photovoltaic modules are erected in the harsh environment or in the high places of houses, and the self-genera...

AI Technical Summary

Problems solved by technology

Usually photovoltaic modules are erected in the harsh environment of the field or high in the house, coupled with self-generated high voltage, making maintenance dangerous and costly

Images