Deep dynamic adaptation network: a deep transfer learning framework for rolling bearing fault diagnosis under variable working conditions

Xu, Huoyao; Liu, Jie; Peng, Xiangyu; Wang, Junlang; He, Chaoming

doi:10.1007/s40430-022-03950-9

Cited by 9 publications

(4 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 2 provides detailed information on the four operating conditions of the test platform. To obtain sufficient samples, the vibration signal recordings were segmented into short pieces with 2048 data points (0.1707 s) using overlapping sampling [42]. There are 1024 overlapping data points between two adjacent pieces.…”

Section: Dataset Descriptionmentioning

confidence: 99%

Adaptive graph-guided joint soft clustering and distribution alignment for cross-load and cross-device rotating machinery fault transfer diagnosis

Xu,

Peng,

Wang

et al. 2024

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

Domain adaptation (DA) is an effective solution for addressing the domain shift problem. However, existing DA techniques usually directly match the distributions of the data in the original feature space, where some of the features may be distorted by a large domain shift. Besides, geometric and clustering structures of the data, which play a significant role in revealing hidden failure patterns, are not considered in traditional DA methods. To tackle the above issues, a new joint soft clustering and distribution alignment with graph embedding (JSCDA-GE) method is proposed. Specifically, weighted subspace alignment (WSA) is proposed to align bases of source and target subspaces by combining instance reweighting and subspace alignment strategies. Then, JSCDA-GE formulates an objective function by incorporating dynamic distribution alignment (DDA), soft large margin clustering (SLMC), and graph embedding (GE) in a unified structural risk minimization (SRM) framework. Ultimately, JSCDA-GE aims to learn a generalization classifier for fault diagnosis. Its effectiveness and superiority have been confirmed through thirty-six tasks on two bearing databases.

show abstract

Section: Dataset Descriptionmentioning

confidence: 99%

Adaptive graph-guided joint soft clustering and distribution alignment for cross-load and cross-device rotating machinery fault transfer diagnosis

Xu,

Peng,

Wang

et al. 2024

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…To substantiate the superior performance of the DTCNN-SJM framework and advantages of the proposed SJM, we constructed a variety of fault diagnosis models for comparative analysis. These models utilize both conventional and widely-recognized methods such as KNN, SVM, Softmax, JDA, TCA, BDA, GFK, MEDA, JGSA, TJM, CORAL [52], EasyTL [53], JPDA [54], MEKT [55], STL [56] and SA [57]. Accordingly, the Table 6 lists 18 comparative models built by these methods, DTCNN and SJM.…”

Section: (3) Comparative Experimentsmentioning

confidence: 99%

A New Bearing Fault Diagnosis Method Based on Deep Transfer Network and Supervised Joint Matching

Liu,

Dong,

et al. 2024

IEEE Photonics J.

View full text Add to dashboard Cite

In practical industrial environment, variable working condition can result in shifts in data distributions, and the labeled fault data in various working conditions is difficult to collect because rotating machines often works in normal status, and the insufficient labeled fault data brings data samples imbalance and performance degradation of intelligent fault diagnosis model. To overcome these problems, by integrating the superiority of deep learning method and feature-based transfer learning method, this work proposes an innovative cross-domain fault diagnosis framework based on deep transfer convolutional neural network and supervised joint matching. Firstly, the continue wavelet transform is used to process original bearing vibration signals and extract time-frequency images. Secondly, a deep transfer convolutional neural network is built by the way of fine-tuning, and the trained network is used to extract deep features from different domains. Thirdly, a new domain adaptation approach, supervised joint matching, is developed to conduct joint feature distribution matching and instance reweighting with the consideration of maximum marginal criterion. The intelligent bearing fault diagnosis model is then trained to predict the labels of the target domain's feature data. To verify the performance of the proposed approaches, this study uses two distinct datasets pertaining to bearing defects for conducting cross-domain fault diagnosis in the presence of balanced and imbalanced data. The experimental analysis indicates that the designed methods can achieve desirable diagnostic accuracy and possess robust generalization ability.

show abstract

“…The number of iterations T, t. Output: Domain-adaptive classifier f. 1: Maximize the variance matrix of source and target data by equation ( 4) and utilize the label information of the source data by equation ( 5) to minimize the within-class scatter matrix and maximizing the between-class scatter matrix. 2: Align the subspaces of the Ds and Dt by equation (10), and then obtain subspace transferable features by Zs = X T s AΦ , Zt = X T t B. 3: Train a base classifier using Zs, then exploit it to predict Zt and obtain its pseudo labels y * t .…”

Section: Pseudo-label Correctionmentioning

confidence: 99%

“…However, obtaining high-quality labeled data from various working scenarios is often impractical [9]. Firstly, rotating machinery typically operates under healthy conditions, resulting in far more healthy data than failure data [10]. Additionally, manually labeling data from different working conditions is timeconsuming and costly.…”

Section: Introductionmentioning

confidence: 99%

Discriminative subspace embedded dynamic geometrical and statistical alignment based on pseudo-label correction for cross-domain bearing fault diagnosis

Xu,

Liu,

Peng

et al. 2023

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

Many domain adaptation (DA) approaches have been developed to address the challenge of domain divergence in cross-domain fault diagnosis. However, most of them only attempt to align statistical distribution while neglecting geometric alignment between source and target data. Furthermore, the use of some unreliable pseudo-labels may cause geometrical and statistical distributions mismatching and interfere with the DA model generating correct pseudo-labels during the iterative learning. In this paper, we propose a new model called discriminative subspace embedded dynamic geometrical and statistical alignment based on pseudo-label correction (DSDGSA-PC) for bearing fault diagnosis. Firstly, discriminative subspace alignment is proposed to mitigate feature redundancy and divergence by generating aligned subspaces for two domains, while preserving class discriminative information and global structures of data. Then, DSDGSA-PC leverages the representer theorem and the principle of structural risk minimization (SRM) to learn a domain-invariant classifier in the subspace, while minimizing statistical and geometrical shift by jointly optimizing dynamic graph embedding and dynamic weighted distribution alignment strategies. Finally, a novel pseudo-label correction mechanism is integrated into DSDGSA-PC to evaluate the credibility of pseudo-labels and rectify the unreliable ones during the iterations. The experimental results illustrate that DSDGSA-PC has higher transfer performance compared to several advanced methods on 24 transfer tasks.

show abstract

Deep dynamic adaptation network: a deep transfer learning framework for rolling bearing fault diagnosis under variable working conditions

Cited by 9 publications

References 48 publications

Adaptive graph-guided joint soft clustering and distribution alignment for cross-load and cross-device rotating machinery fault transfer diagnosis

Adaptive graph-guided joint soft clustering and distribution alignment for cross-load and cross-device rotating machinery fault transfer diagnosis

A New Bearing Fault Diagnosis Method Based on Deep Transfer Network and Supervised Joint Matching

Discriminative subspace embedded dynamic geometrical and statistical alignment based on pseudo-label correction for cross-domain bearing fault diagnosis

Contact Info

Product

Resources

About