Title :
A fuzzy system for automotive fault diagnosis: fast rule generation and self-tuning
Author :
Lu, Yi ; Chen, Tie Qi ; Hamilton, Brennan
Author_Institution :
Dept. of Electr. & Comput. Eng., Michigan Univ., Dearborn, MI, USA
fDate :
3/1/2000 12:00:00 AM
Abstract :
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
Keywords :
automotive electronics; fault diagnosis; fuzzy set theory; internal combustion engines; leak detection; automotive assembly plants; automotive diagnostic knowledge; automotive fault diagnosis; electronic engine controller; end-of-line test; fast rule generation; fuzzy membership functions optimisation; fuzzy model; fuzzy rules generation; fuzzy system; machine learning techniques; self-tuning; vacuum leak detection; Automatic control; Automotive engineering; Electronic equipment testing; Engines; Fault diagnosis; Fuzzy control; Fuzzy systems; Leak detection; Machine learning; Machine learning algorithms;
Journal_Title :
Vehicular Technology, IEEE Transactions on
