Bearing fault diagnosis under various operation conditions using synchrosqueezing transform and improved two-dimensional convolutional neural network

Abstract

In real-world industrial applications, bearings are typically operated under variable speeds and loads depending on the production condition, which results in nonstationary vibration signals from the bearings. Synchrosqueezing transform is a method that can effectively reflect the change in frequency with time, which is suitable for processing nonstationary bearing signals. However, significant classification features are difficult to extract from time–frequency information when operation conditions such as speed and load change frequently. Hence, an improved two-dimensional (2D) convolutional neural network (CNN) named the 2D multiscale cascade CNN (2D MC-CNN) is proposed for performing bearing fault diagnosis under various operating conditions. In a 2D MC-CNN, a multiscale information fusion layer is added prior to the convolutional layer of a conventional CNN to form MC images such that sensitive bands can be acquired for fault recognition. Experiments are conducted on bearings by considering various sets of fault categories and fault severity levels under six operating conditions. The experimental results show that the proposed method effectively extracts fault-related features and demonstrates excellent diagnostic accuracy and robustness. Comparisons with the original CNN and other typically used fault diagnosis methods based on the same dataset demonstrate the effectiveness of the proposed 2D MC-CNN and bearing fault diagnosis method.