Title :
A diagnostic method using wavelets networks application to engine knock detection
Author :
Thomas, Jean-Hugh ; Dubuisson, Bernard
Author_Institution :
Univ. de Technol. de Compiegne, France
Abstract :
The paper proposes to use wavelet networks in order to realize a diagnostic system. First, they constitute the models of the operating modes of the system. Then they allow extraction of relevant features from acquired data. The goal of the method is to partition the feature space into classes representing the operating modes of the system. The whole process that belongs to pattern recognition, leads to diagnostic fusion. It is applied to engine knock detection. Experimental results are reported
Keywords :
automobile industry; decision theory; feature extraction; internal combustion engines; neural nets; quality control; diagnostic fusion; diagnostic method; diagnostic system; engine knock detection; pattern recognition; wavelets networks; Computer architecture; Data mining; Decision making; Electronic mail; Engines; Feature extraction; Neural networks; Paper technology; Pattern recognition; Sensor systems;
Conference_Titel :
Systems, Man, and Cybernetics, 1996., IEEE International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-3280-6
DOI :
10.1109/ICSMC.1996.569774
