Rotating Shaft Fault Prediction Using Convolutional Neural Network: A Preliminary Study

Abstract One of the most important subsystems of the vehicles and machines operating currently in industry and transportation are the rotating subsystems. During the operation, due to the forcing factors influence, the technical state of them is changing and the failure can occur. Fault diagnosis is maintenance task considered as an essential in such subsystems, since possibility of an early detection and diagnosis of the faulty condition can save both time and money. To do this the analysis of the subsystems vibrations is performed. The identified technical state should be considered in a context of the ability and different inability states. Therefore, the first step of the diagnostic procedure is the ability and different inability states identification. Traditional data-driven techniques of fault diagnosis require signal processing for feature extraction, as they are unable to work with raw signal data, consequently leading to need for both expert knowledge and human work. The emergence of deep learning architectures in condition-based maintenance promises to ensure high performance fault diagnosis while lowering necessity for expert knowledge and human work. This article presents authors initial research in deep learning-based data-driven fault diagnosis of rotating subsystems. The proposed technique input raw three-axis accelerometer signal as high-definition image into deep learning layers, which automatically extract signal features, enabling high classification accuracy.