Ignition Pattern Analysis for Automotive Engine Trouble Diagnosis Using Wavelet Packet Transform and Support Vector Machines

作     者：VONG Chi-man WONG Pak-kin TAM Lap-mou ZHANG Zaiyong 

作者机构：Department of Computer and Information Science Faculty of Science and Technology University of Macao Macao China Department of Electromechanical Engineering Faculty of Science and Technology University of Macao Macao China 

出 版 物：《Chinese Journal of Mechanical Engineering》 (中国机械工程学报（英文版）)

年 卷 期：2011年第24卷第5期

页      面：870-878页

核心收录：

学科分类：0817[工学-化学工程与技术] 082304[工学-载运工具运用工程] 08[工学] 0807[工学-动力工程及工程热物理] 0802[工学-机械工程] 0811[工学-控制科学与工程] 0801[工学-力学（可授工学、理学学位）] 0823[工学-交通运输工程] 

基　　金：supported by University of Macao Research Grant China (Grant No. RG057/08-09S/VCM/FST  Grant No. UL011/09-Y1/ EME/ WPK01/FST) 

主　　题：automotive engine ignition pattern diagnosis pattern classification wavelet packet transform support vector machines. 

摘      要：Engine spark ignition is an important source for diagnosis of engine *** on the waveform of the ignition pattern,a mechanic can guess what may be the potential malfunctioning parts of an engine with his/her experience and ***,this manual diagnostic method is imprecise because many spark ignition patterns are very ***,a diagnosis needs many trials to identify the malfunctioning *** the mechanic needs to disassemble and assemble the engine parts for *** tackle this problem,an intelligent diagnosis system was established based on ignition ***,the captured patterns were normalized and *** wavelet packet transform（WPT） was employed to extract the representative features of the ignition ***,a classification system was constructed by using multi-class support vector machines（SVM） and the extracted *** classification system can intelligently classify the most likely engine fault so as to reduce the number of diagnosis *** results show that SVM produces higher diagnosis accuracy than the traditional multilayer feedforward neural *** is the first trial on the combination of WPT and SVM to analyze ignition patterns and diagnose automotive engines.