Bidirectional Current WP and CBAR Neural Network Model-Based Bearing Fault Diagnosis

Abstract

In the era of artificial intelligence, the development of an efficient bearing, fault diagnosis method is of vital importance to ensure smooth production operations and avoid major economic losses. To this end, this paper proposes a bearing fault diagnosis method based on biphasic currents. The method first performs wavelet denoising on the biphasic current signal, then extracts its features by simple vector representation and algebraic operations, and finally, combines the CBAR model of Convolutional Block Attention Module (CBAM) and Residual Network (ResNet) for bearing fault diagnosis. The experimental results show that the highest accuracy rate reaches 100% in both single-point fault and single-point mixed with multiple faults conditions on the open source current bearing fault diagnosis dataset, respectively. Compared with other methods, the method proposed in this paper has the advantage of simple data processing, concise model structure, and high-fault diagnosis accuracy, which provides an effective way for dual-phase current-based bearing fault diagnosis. It is worth emphasizing that based on wavelet denoising, this paper uses the simplest vector representation and algebraic operations to preprocess the signal (WP), making the method more efficient and easy to implement.

A Fault Prediction Method for CNC Machine Tools Based on SE-ResNet-Transformer

“…Currently, the field of CNC machine tool failure diagnosis is starting to use deep learning techniques that are good at feature learning and pattern recognition [2]. Many researchers have made significant contributions to local data prediction and fault identification in CNC machine tools [3][4][5][6][7][8][9].…”