A novel deep learning model for fault diagnosis of rolling-element bearing based on convolution neural network and recurrent neural network

Abstract

Rolling bearings are critical components that are incredibly prone to failure in the operation of mechanical equipment. Due to the complexity of the actual working conditions, multiple types, positions and scales of bearings are problematic to accurately and completely classify using conventional classification methods. In this study, a novel end-to-end deep learning framework consisting of a one-dimensional convolutional neural network (1D-CNN) and a module fused by long short-term memory (LSTM) and gated recurrent unit (GRU) is proposed to diagnose bearing failures, thus solving the problem of the poor accuracy of traditional fault identification. First, 1D-CNN is used to extract local features from bearing data thanks to its excellent local feature extraction capabilities. Second, global features are extracted from bearing data using LSTM and GRU, and classification is performed with Softmax. Finally, the proposed model is evaluated using Case Western Reserve University and the University of Cincinnati data, with accuracy rates of 99.99% and 99.83%, respectively. The experimental results indicate that the proposed model has good feasibility and performance.