Fault Diagnosis Of Ship Power Supply System Based on grey correlation improved BP neural network

Abstract

The ship power system is becoming more and more complex, and the probability of failure is also greatly increased. In this paper, the ship power system fault diagnosis algorithm of BP neural network is put forward based on the grey correlation improved BP neural network, the structure of BP neural network is improved by using grey correlation. In view of the different effects of each hidden layer neuron to the network output layer, the function of the output layer is analyzed by using the gray correlation analysis method, and the gray correlation degree is calculated to effectively eliminate the hidden layer neurons those has small influence on the output layer, which can optimize the structure of BP neural network. The simulation results of fault diagnosis for ship power system are analyzed, which show that the optimized BP neural network can effectively improve the accuracy of the fault diagnosis of the ship power system.