Research on fault diagnosis of photovoltaic array based on GA_IPSO-SFLA-WNN model
In order to accurately identify the operation faults of the photovoltaic modules,a fault diagnosis method based on the combination of genetic algorithm and improved particle swarm optimization(GA_IPSO),shuffled frog leaping algorithm(SFLA)and wavelet neural network(WNN)was proposed.Firstly,the operation model of PV module is established,and the operation data of PV module under fault condition is extracted;Then,a photovoltaic fault diagnosis model based on WNN is built.Aiming at the problem that the initial value of WNN model parameters is sensitive and easy to fall into local minimum,SFLA is adopted to optimize the initial value;In order to solve the problems of large individual differences and randomness of moving steps in different subgroups of WNN model optimized by SFLA,GA_IPSO solves the optimal individual and optimal step size.The experimental results show that the average recognition accuracy of this method for five photovoltaic faults(open circuit,short circuit,shadow,aging and potential vector machine(PID)reaches 98.50％,which is 9.5％higher than that before the improvement,and is better than back propagation(BP),extreme learning machine(ELM)and support vector machine(SVM)in Australia photovoitaic data set.
NETL
NSTL
万方数据
