Fault Diagnosis of Vehicle Network Control System Based on GA Improved ANN Algorithm
Vehicle-mounted network control system is a kind of important control equipment to ensure the safe-ty of operation,and also the core component to ensure the stable operation of the system.In order to improve the fault diagnosis efficiency of on-board network control system,the global optimization function of genetic algorithm(GA)is used to optimize the initial threshold and weight of neural network,and the optimization results are substi-tuted into the neural network to complete the training process.Making full use of the mapping performance of ANN generalization method can prevent the occurrence of local minimum and obtain higher classification accuracy.An example is used to test the validity of on-board fault diagnosis process.The results show that using GA to improve ANN algorithm can effectively optimize the average error and data accuracy,and effectively reduce the number of iterations,indicating that GA can improve ANN method to improve the performance of neural network.The ANN optimized by genetic algorithm can get faster convergence rate than the initial ANN in the training process.
vehicle-mounted network control systemfault diagnosisgenetic algorithmANNeffectivenessclassification accuracy
NETL
NSTL
万方数据
维普
