Semi-supervised graph convolutional network and its application in intelligent fault diagnosis of rotating machinery

Abstract

Aiming at the difficulty of mechanical fault diagnosis with small samples, an intelligent fault diagnosis method for rotating machinery is proposed based on semi-supervised graph convolutional network (SSGCN). SSGCN has a good application in analyzing the naturally formed graph data, but it has not been researched for the complex mechanical vibration data. Besides, SSGCN is only applicable to graph data, but the collected vibration signals are one-dimensional time series. To well reflect the local geometry property between all vibration samples, we construct all vibration samples into an undirected and weighted k-nearest neighbor graph. The detailed parameter analysis is also carried out for SSGCN. Experimental results indicate that our proposed method can adaptively extract the available fault features from the raw vibration signals. Even if the label ratio is only 0.05 for each gear or bearing condition, our proposed method can still obtain an average accuracy of more than 98%.