ANFIS-based fault diagnosis cloud model of oil parameter for automobile engine

Author

Kong Li Fang ; Wang Zhe ; Zhang Wei

Author_Institution

Xuzhou Air Force Coll., Xuzhou, China

fYear

2011

fDate

19-22 Aug. 2011

Firstpage

2458

Lastpage

2462

Abstract

The thesis, in order to solve the fault diagnosis problem of oil Parameter, adaptive neural network-based fuzzy inference system (ANFIS) was applied to build a fault diagnosis model of automobile engine, with the construction of ANFIS, by using gradient descent genetic algorithm and optimization of system parameters of neutral network learning algorithm, inputs the fusion data into ANFIS, and introduces cloud model in output. Through verification of the build diagnosis model with data of engine tests, it has been found that the recognition accuracy increase from 90.26% to 98.72%, training error falling from 0.044237 to 0.02711. The experiment indicates that the recognition rate of "ANFIS + cloud model" system is significantly better than independent neural network reasoning system, fuzzy inference system and adaptive fuzzy neural network system.

Keywords

automobiles; engines; fault diagnosis; fuzzy neural nets; fuzzy reasoning; genetic algorithms; gradient methods; mechanical engineering computing; sensor fusion; ANFIS-based fault diagnosis cloud model; adaptive neural network-based fuzzy inference system; automobile engine; engine test data; fusion data; fuzzy neural network; gradient descent genetic algorithm; neutral network learning algorithm; oil parameter; system parameter optimization; Adaptation models; Automobiles; Data models; Engines; Fault diagnosis; Testing; Training; ANFIS (adaptive neural fuzzy interference system); cloud model; fault diagnosis; oil parameter;

fLanguage

English

Publisher

ieee

Conference_Titel

Mechatronic Science, Electric Engineering and Computer (MEC), 2011 International Conference on

Conference_Location

Jilin

Print_ISBN

978-1-61284-719-1

Type

conf

DOI

10.1109/MEC.2011.6025990

Filename

6025990