Deep Transfer Learning for Bearing Fault Diagnosis: A Systematic Review Since 2016

Insufficient and imbalanced samples pose a significant challenge in bearing fault diagnosis, leading to low diagnosis accuracy. However, the fault characteristics of vibration signals are weak and difficult to extract when faults occur in the early stage. This paper proposes an effective fault diagnosis method that addresses small and imbalanced sample problems under noise interference. First, the number of faulty samples in the form of 1D signals is increased mainly by the sliding split sampling method. The preprocessed data are used to create 2D time–frequency diagrams using the continuous wavelet transform (CWT), which can extract effective features to improve the data quality. Subsequently, the minority samples are oversampled by combining Synthetic Minority Oversampling Technique (SMOTE) to realize TFCAO. Moreover, the clustering method and random undersampling method are introduced to prevent the overfitting and underfitting problems respectively. Then, we propose a hybrid attention mechanism to enhance the extraction of effective feature information. This combination, integrating CWT with a multicolumn modified DRN, effectively extracts fault characteristics and suppresses noise effects. The experimental results demonstrate the effectiveness of the proposed method by comparison with other advanced methods using two case studies of bearing datasets.

Section: Introductionmentioning

confidence: 99%

A novel approach for bearings multiclass fault diagnosis fusing multiscale deep convolution and hybrid attention networks

Li,

Zhao

2024

“…Signal processing approaches in fault diagnosis often require extensive expertise, whereas data-driven approaches based on machine learning can reduce reliance on expert diagnostic experience. Data-driven methods primarily encompass machine learning methods, deep learning methods, and transfer learning methods [11]. The general process of fault diagnosis using machine learning methods involves two key stages: feature extraction and fault classification.…”

Section: Introductionmentioning

confidence: 99%

A novel algorithm for complex transfer conditions in bearing fault diagnosis

Dong,

Su,

Jiang

et al. 2024

Transfer learning in bearing fault diagnosis can effectively improve model generalization and accelerate the practical application of fault diagnosis algorithms. However, previous algorithms primarily focused on simple transfer conditions like known target domain data or the same device. In industrial practice, the conditions for algorithm transfer are more complex. Therefore, cross-domain fault diagnosis under complex transfer conditions is a challenging task with significant practical value. This paper proposes a new bearing fault diagnosis algorithm based on attention mechanism and feature enhancement, which provides better feature extraction capabilities. The main approach involves performing deep aliasing on deep features and training the model to identify domain-invariant classification features under extreme conditions for effective fault diagnosis. Additionally, our network performs well in handling low signal-to-noise ratio problems. Extensive experiments were conducted on three different bearing case studies to validate the effectiveness of the proposed method, showing superior performance compared to other deep transfer learning methods.

“…Xie et al [27] designed an MLP-based bearing fault diagnosis model, complementary ensemble EMD (CEEMD) was first applied to decompose the bearing vibration signals, and then recurrence plots were used to transform the one-dimensional signals into two-dimensional images to fit the model input. Furthermore, to address the limitations of deep learning in actual industrial scenarios, some scholars have conducted research on transfer learning [28][29][30]. Zhao et al [31] proposed a class-aware adversarial multi-wavelet CNN to effectively extract and align features from both the source and target domains, addressing the cross-domain issue in rotational machinery fault diagnosis.…”

Section: Introductionmentioning

confidence: 99%

AdaClass filter and its application in bearing fault diagnosis

Zhang,

Li,

Zhang

et al. 2024

The vibration signals recorded by the sensor reflect the operating state of bearings, and extracting recognizable features effectively from them has become a hot issue in fault diagnosis. Currently, signal processing based filtering methods have emerged as a popular approach for extracting fault-related features. However, conventional filters based on specified assumptions and theoretical models have limited adaptability to multiple types of bearings under different operating conditions, which can significantly impact the diagnostic results. Given this, a data-driven Adaptive Class (AdaClass) filter is proposed to extract the response characteristics of different categories within the latent space. The filter details are obtained by statistically analyzing the mean vectors of each class samples in the reconstructed feature subspaces. Notably, the latent feature space is mapped by linear operators LDA and class-wise PCA, where the data has a more concise feature representation and a more distinct feature structure. The low-dimensional projection operations enhance the differential information among different categories, and reorganize the internal structure within the same category. Furthermore, a bearing fault diagnosis model is developed based on the AdaClass filter banks, utilizing one-step convolution to improve the efficiency of feature extraction. Experimental results show that the proposed method outperforms the competitors in terms of accuracy, time consumption, and noise resistance, especially for small sample scenarios.