An improved BP algorithm and application in the fault diagnosis of the diesel engine fuel system

摘要

Back-Propagation algorithm is one of the most popular algorithms in neural network. But it converges slowly, easily falling into local minima. This paper presents an improved BP algorithm, which can adjust learning rate using golden section method. Based on the algorithm, a diesel engine fault diagnosis system is designed. The simulation results indicate that the algorithm has much faster learning speed and more superior learning precision compared with the standard BP algorithm.