Fault Diagnosis for Diesel Valve Trains Based on Time-Frequency Images

摘要

In this paper, the Wigner-Ville distributions (WVD) of vibration acceleration signals, which were acquired from the cylinder head in eight different states of valve train, 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. By this way, the problem of fault diagnosis for valve train was transferred to the classification of time-frequency images. 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.