Research on CVT fault diagnosis system based on artificial neural network

To accomplish the demand of continuously variable transmission (CVT) fault diagnosis, the structure of CVT fault diagnosis system is built and the application model of Back-Propagation Neural Network is established aiming at the features of CVT faults. The structure and 3 algorithms of network are devised. The network proposed is simulated and the results are analyzed in detail. The simulation results indicate that the fault diagnosis system based on Back-Propagation neural network with momentum and self-adaptive learning rate algorithm is effective.