Multiscale Convolutional Neural Network Based on Channel Space Attention for Gearbox Compound Fault Diagnosis

Abstract

Gearboxes are one of the most widely used speed and power transfer elements in rotating machinery. Highly accurate compound fault diagnosis of gearboxes is of great significance for the safe and reliable operation of rotating machinery systems. However, traditional compound fault diagnosis methods treat compound faults as an independent fault mode in the diagnosis process and cannot decouple them into multiple single faults. To address this problem, this paper proposes a gearbox compound fault diagnosis method. First, a multiscale convolutional neural network (MSCNN) is used as a feature learning model, which can effectively mine the compound fault information from vibration signals. Then, an improved hybrid attention module, named the channel–space attention module (CSAM), is proposed. It is embedded into the MSCNN to assign weights to multiscale features for enhancing the feature differentiation processing ability of the MSCNN. The new neural network is named CSAM-MSCNN. Finally, a multilabel classifier is used to output single or multiple labels for recognizing single or compound faults. The effectiveness of the method was verified with two gearbox datasets. The results show that the method possesses higher accuracy and stability than other models for gearbox compound fault diagnosis.

An intelligent compound fault diagnosis method using generalized zero-shot model of bearing

“…As depicted in table 5, our fault semantic approach performs better on task S and task X, achieving an H score of 75.83 for Task S and 69.24 for Task X. In comparison, the H scores for other semantics in the two tasks were 55.91 (Binary classifiers), 50.94 (Binary classifiers), 21.31 (EEMD), 16.87 (EEMD), 66.72 (SAE), 58.52 (SAE), 36.37…”

“…employed a one-dimensional deep convolutional neural network for feature learning and utilized multi-layer capsules as a decoupling classifier, effectively identifying and decoupling compound fault. Xu et al [16]. proposed a gearbox compound fault diagnosis method combining channelspace attention module with multiscale convolutional neural network (CSAM-MSCNN), capable of decoupling compound fault into multiple single faults.…”

Research on bearing remaining useful life anti-noise prediction based on fusion of color-grayscale time-frequency features

“…The CA attention mechanism in CBAM and CSAR, detailed in figure 4(a), serves as the foundation for an enhanced channel attention enhancement (CAE) and spatial attention enhancement (SAE) mechanism proposed in this study. The original CA mechanism in CBAM, which utilizes fully connected layers for channel interaction, has been identified as inefficient and potentially detrimental to model performance [54]. The refined CAE mechanism amalgamates the strengths of CBAM and CSAR's CA mechanisms by substituting the fully connected layers with a more efficient one-dimensional convolution, thereby mitigating the drawbacks associated with fully connected layers.…”

Analysis of Wind Turbine Equipment Failure and Intelligent Operation and Maintenance Research

“…In the area of fault diagnosis models for wind energy gearboxes, Xu et al [150] proposed an improved hybrid attention module using a multi-scale convolutional neural network as a feature learning model, in which a multi-label classifier outputting single or multiple labels was used to identify single or compound faults. The method was verified to have higher accuracy and stability than other transmission compound fault diagnosis models for two transmission data sets; the diagnosis process is shown in Figure 13.…”