Abstract: Aiming at the problem of low fault diagnosis accuracy caused by the randomness and uncertainty of multifunction vehicle bus (MVB), we designed a fault diagnosis algorithm for MVB based on fuzzy neural network. Firstly, the diagnosis model was given according to the fault types of MVB. Secondly, the subtraction clustering was used to generate fewer fuzzy rules. Finally, the T-S fuzzy neural network was used to classify the faults. The simulation results of the fitting ability and diagnosis accuracy of the algorithm in MATLAB show that the proposed algorithm simplifies the structure of the fuzzy neural network and effectively improves the accuracy of fault diagnosis.

Key words: multifunction vehicle bus (MVB), fault diagnosis, fuzzy neural network, subtraction clustering