Abstract—An engine fault diagnosis method based on discrete wavelet transform and a support vector machine using engine vibration and sound signals is proposed in the present study. The use of mechanical vibration and sound signals for fault analysis in rotating machinery has grown significantly due to the progress of digital signal processing algorithms and implementation techniques. In general, the conditions of rotating machineries can be monitored by measuring the mechanical vibration and sound signals. In the present study, both the vibration and sound signals are used to find faults in the engine timing gear and valve clearance. The diagnosis system consists of feature extraction using the discrete wavelet transform and fault classification using the artificial neural network technique with the support vector machine method. In the experimental work, an electronic fuel injection scooter engine is used for simulating six working conditions in the faults of timing gear and intake-exhaust valves. The experimental results indicated the proposed technique is effective in fault diagnosis for experimental cases.
Index Terms—Discrete wavelet transforms, Expert system, Fault diagnosis system, Support vector machine.
Jian-Da Wu is with the National Changhua University of Education, Changhua, ROC (e-mail: jdwu@ cc.ncue.edu.tw).
Jian-Bin Chain was with the Graduate Institute of Vehicle Engineering, National Changhua University of Education, Changhua, ROC. He is now graduated (e-mail:firstname.lastname@example.org).
Chen-Wei Chung was with the Graduate Institute of Vehicle Engineering, National Changhua University of Education, He is now study doctorate in mechanical engineering from National Central University of ROC (e-mail: email@example.com).
Hao Yu was with the Graduate Institute of Vehicle Engineering, National Changhua University of Education, Changhua, ROC. He is now graduated (e-mail: firstname.lastname@example.org).
Cite: Jian-Da Wu, Jian-Bin Chain, Chen-Wei Chung, and Hao Yu, "Fault Analysis of Engine Timing Gear and Valve Clearance Using Discrete Wavelet and a Support Vector Machine," International Journal of Computer Theory and Engineering vol. 4, no. 3, pp. 386-390, 2012.