The Community for Technology Leaders
Pacific-Asia Workshop on Computational Intelligence and Industrial Application, IEEE (2008)
Dec. 19, 2008 to Dec. 20, 2008
ISBN: 978-0-7695-3490-9
pp: 154-158
ABSTRACT
With the improvement of automobile electric degree, more and more people begin to pay attention to the fault diagnosis method and theories of electric controlled system. The precision and accuracy of On-Board Diagnosis methods, which with OBDII standard and has been widely used at present need to be further improvement. So, in this paper, take the engine idling instability as the example, put forward a multi-sensor diagnosis method which fusing Neural Network and D-S evidence theory, this method mainly use for On-Board diagnosis system data’s fusing process and analysis. The experimental result shows that, this method can make use of various faults’ redundant and complementation information sufficiently, and then promote the recognition ability obviously. With electric controlled technology widely used in automobile, the performance of automobile products has been promoted largely, but these also make fault diagnosis become more difficult, traditional methods such as experience or simple instrument could not meet the flexible diagnosis demand. At present, the On-Board diagnosis with OBDII standard has been applied for electric controlled system’s fault diagnosis, but it could only for 70%-80%’s fault, and the diagnosis results are mainly presented by fault code or data flow, and still need other’s help, and the accuracy degree still needs further improvement. Therefore, looking for the more precious and intelligent method for electric controlled system become the key direction in automobile fault diagnosis field.
INDEX TERMS
CITATION
Lili Zhang, Jiangwei Chu, "Fault Diagnosis Method Study on Automobile Electrical Controlled System Based on Fusing of ANN and D-S Evidence Theory", Pacific-Asia Workshop on Computational Intelligence and Industrial Application, IEEE, vol. 01, no. , pp. 154-158, 2008, doi:10.1109/PACIIA.2008.206
84 ms
(Ver 3.3 (11022016))