Fault diagnosis of fire control system based on genetic algorithm optimized BP neural network

Abstract

In view of the complex structure of the fire control system, difficulty in obtaining fault information, and multiple fault characteristics. This paper proposes a fire control system fault diagnosis method based on genetic algorithm optimized BP neural network. For the problem of poor prediction accuracy of BP neural network in the operation process, and easy to fall into local extreme value. In order to obtain a better diagnosis effect, the principle of complementary advantages is used to combine genetic algorithm with BP neural network algorithm. The genetic algorithm is used to calculate the initial values of network parameters, optimize the initial weights and thresholds, and find the optimal number of hidden layer nodes. Combined with case analysis, the accuracy of this method is improved compared with traditional BP neural network in solving the problem of fire control system fault diagnosis. At the same time, it proves the effectiveness of the proposed method in fire control system fault diagnosis.