Fault Identification for I.C. Engines Using Artificial Neural Network

Due to progress in the vehicular technology, vehicles have gradually become a popular form of transportation in people´s daily life. The stability and the performance of the vehicles has been the subject of much attraction. Road vehicle engines are controlled by engine management system (EMS) in which fault identification & diagnosis is the vital part. The pressure of the engine intake system always demonstrates the engine condition and affects the volumetric efficiency, fuel consumption and performance of internal combustion engines. Conventional engine diagnostic technology already exists through analyzing the differences between the signals and depends on the experience of the technician. Obviously the conventional detection is not a precise approach for pressure detection when the engine in operating condition. In this paper, a system is consisted of pressure signal feature extraction using discrete wavelet transform (DWT) and fault recognition using the neural network technique. To verify the effect of the proposed system for identification, the radial basis function network (RBFN) is used. It has been observed that the training procedure can be accomplished in short time. Also, the conventional flaw of too much reliance on the experience of technicians can be reduced.