A fuzzy system for automotive fault diagnosis: fast rule generation and self-tuning

This paper describes a fuzzy model that learns automotive diagnostic knowledge through machine learning techniques. The fuzzy model contains the algorithms for automatically generating fuzzy rules and optimizing fuzzy membership functions. The fuzzy model has been implemented to detect a vacuum leak in the electronic engine controller (EEC) as part of the end-of-line test at automotive assembly plants. The implemented system has been tested extensively, and its performance is presented.

[1]  Hans-Jürgen Zimmermann,et al.  Fuzzy Set Theory - and Its Applications , 1985 .

[2]  Sankar K. Pal,et al.  Fuzzy multi-layer perceptron, inferencing and rule generation , 1995, IEEE Trans. Neural Networks.

[3]  H. Tennant.  Onboard Knowledge Systems in Vehicles , 1990 .

[4]  H. Zimmermann,et al.  Fuzzy Set Theory and Its Applications , 1993 .

[5]  Frank Chung-Hoon Rhee,et al.  Fuzzy rule generation methods for high-level computer vision , 1993 .

[6]  M. Ayoubi,et al.  Neuro-fuzzy structure for rule generation and application in the fault diagnosis of technical processes , 1995, Proceedings of 1995 American Control Conference - ACC'95.

[7]  Sergei Ovchinnikov,et al.  Fuzzy sets and applications , 1987 .

[8]  Yi Lu,et al.  Diagnosis of automobile failures using fuzzy logic , 1995, IEA/AIE '95.

[9]  L. Zadeh,et al.  Towards a theory of fuzzy systems , 1996 .

[10]  James C. Bezdek,et al.  Pattern Recognition with Fuzzy Objective Function Algorithms , 1981, Advanced Applications in Pattern Recognition.

[11]  M. Glesner,et al.  Rule weight generation for a fuzzy classification system based on fuzzy clustering methods , 1994, Proceedings of 1994 IEEE 3rd International Fuzzy Systems Conference.

[12]  Yang Shuzi,et al.  A knowledge-based diagnosis system for automobile engines , 1988 .

[13]  Hoon Kang.  An automated rule design of fuzzy logic controllers for uncertain dynamic systems , 1993, [Proceedings 1993] Second IEEE International Conference on Fuzzy Systems.

[14]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Michio Sugeno,et al.  Fuzzy identification of systems and its applications to modeling and control , 1985, IEEE Transactions on Systems, Man, and Cybernetics.