FAULT DIAGNOSIS FOR DIESEL VALVE TRAINS BASED ON TIME-FREQUENCY IMAGES FOR ASIATRIB 2006 KANAZAWA, JAPAN

摘要

In this paper, the Wigner-Ville distributions (WVD) of vibration acceleration signals were calculated and displayed in grey images; and the Probabilistic Neural Networks (PNN) were directly used to classify the time-frequency images after the images were normalized. As there is no need to extract features from time-frequency distributions before classification, the fault diagnosis process is highly simplified. The experimental results show that the faults of Diesel Valve Trains can be classified accurately by the proposed methods.