Optimization of BP Neural Network Based on Improved Dung Beetle Algorithm for PV Array Fault Diagnosis

With the rapid growth of the scale and quantity of photovoltaic (PV) power station construction, more and more PV arrays are facing operational and maintenance challenges. In recent years, many artificial intelligence algorithms have been successfully applied to fault diagnosis of PV arrays. In response to the problem of falling into local minima in the backpropagation (BP) neural network algorithm, this paper proposes a fault diagnosis method based on an improved dung beetle algorithm optimized BP neural network (LIDBO-BP). This method initializes the population by logistic chaotic mapping, and adaptively adjusts the reproduction and foraging boundaries of dung beetles by introducing optimization state information. The improved dung beetle algorithm is applied to optimize the initial weights and thresholds of the BP neural network to establish a fault diagnosis model. The results of simulation and experiments show that optimizing BP neural network through the improved dung beetle algorithm can effectively improve the accuracy of PV array fault diagnosis, and show practicality in online fault diagnosis.