In this paper, a new diagnostic method for abnormal automobile sound using CNN is proposed. The procedure of the method consists of 1) calculating the autoregressive model (AR model) coefficients from the abnormal sound by using the maximum entropy method; 2) constructing the CNN whose memory patterns become standard abnormal sound patterns; 3) making the coefficients obtained as an initial pattern and recalling one from the memory patterns, and then obtaining a diagnosis result. By using the method, the influence of the noise occurring from other normal parts can be avoided and the automobile abnormal sound can be diagnosed. The results obtained demonstrate the advantages of our approach.
Cellular Neural Network and Its Application in the Diagnosis of Abnormal Automobile Sound
Sae Technical Papers
SAE Powertrain & Fluid Systems Conference & Exhibition ; 2002
2002-10-21
Conference paper
English
Cellular neural network and its application in the diagnosis of abnormal automobile sound
Automotive engineering | 2002
|Cellular Neural Network and Its Application in the Diagnosis of Abnormal Automobile Sound
British Library Conference Proceedings | 2002
|IPC2001T339 A New Diagnostic Method of Automobile Abnormal Sound using Cellular Neural Network
British Library Conference Proceedings | 2001
|Reviews on Automobile Abnormal Sound Fault Diagnosis
Trans Tech Publications | 2014
|