The Vibration Parameter Fault Diagnosis Cloud Model for Automobile Engine Based on ANFIS

Abstract

In order to solve the fault diagnosis problem of Vibration Parameter, Adaptive Neuro-Fuzzy inference system (ANFIS) was applied to build a fault diagnosis model of automobile engine and induce cloud model of fan-out, outputting results are continued. Through verification of the built diagnosis model with data of engine tests, it has been found that the recognition accuracy increase from 88.75% to 99.68%, training error falling from 0.001683 to 0.0011526. Simulation results show that the fitting ability, convergence speed and recognition accuracy of improved ANFIS model are all superior to ANFIS. So a contingent fault of automobile engine can be identified effectively.