A novel joint distinct subspace learning and dynamic distribution adaptation method for fault transfer diagnosis

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

doi:10.1016/j.measurement.2022.111986

Cited by 15 publications

(3 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DL-based IFD methods usually hold the assumption that a large amount of labeled and equally distributed data are available [7,8]. However, the above assumptions do not always hold in complex practical scenarios, resulting in serious degradation of diagnostic performance [9,10].…”

Section: Introductionmentioning

confidence: 99%

Non-Uniformly Weighted Multisource Domain Adaptation Network For Fault Diagnosis Under Varying Working Conditions

Zhang,

Wang

et al. 2024

Neural Process Lett

View full text Add to dashboard Cite

Most transfer learning-based fault diagnosis methods learn diagnostic information from the source domain to enhance performance in the target domain. However, in practical applications, usually there are multiple available source domains, and relying on diagnostic information from only a single source domain limits the transfer performance. To this end, a non-uniformly weighted multisource domain adaptation network is proposed to address the above challenge. In the proposed method, an intra-domain distribution alignment strategy is designed to eliminate multi-domain shifts and align each pair of source and target domains. Furthermore, a non-uniform weighting scheme is proposed for measuring the importance of different sources based on the similarity between the source and target domains. On this basis, a weighted multisource domain adversarial framework is designed to enhance multisource domain adaptation performance. Numerous experimental results on three datasets validate the effectiveness and superiority of the proposed method.

show abstract

Section: Introductionmentioning

confidence: 99%

Non-Uniformly Weighted Multisource Domain Adaptation Network For Fault Diagnosis Under Varying Working Conditions

Zhang,

Wang

et al. 2024

Neural Process Lett

View full text Add to dashboard Cite

show abstract

“…Secondly, the collected monitoring data exhibit significant distribution differences across different machines, loads, speeds, and noise interference [11,12]. Consequently, there is a significant gap between the probability distributions of the training and test sets, which may substantially degrade the generalization and robustness of DL-based diagnostic models [13,14]. Therefore, developing advanced models to address domain shift has become an urgent need.…”

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

“…The conditional (local) distribution between domains and the marginal (global) distribution, however, typically contribute differently to adaptation in actual applications. [19,20] Therefore, taking into account both marginal and conditional distributions is a better set which allows adversarial training to learn better domain-invariant features.…”

mentioning

confidence: 99%

Joint alignment network preserving structural information for multimode process fault diagnosis

Tan,

Xu,

Shi

et al. 2023

Can J Chem Eng

View full text Add to dashboard Cite

Production conditions are complex and varied for a number of reasons. Models for defect diagnosis may perform worse as a result of the distributional mismatch between test data and training data. In order to diagnose process faults, it is crucial to take into account the fact that data exhibits varied distribution characteristics under various conditions. In the case of multiple operating conditions, the cross‐domain problem caused by different data distributions can degrade the performance of deep learning‐based fault diagnosis models. To overcome this challenge, a joint alignment network preserving structural information (JANSI) method is proposed. To extract richer and fine‐grained domain‐invariant features, the structural information preservation is proposed, which combines domain labels, category labels, and data distribution structures. To increase intra‐class compactness and inter‐class separability, class centre alignment is proposed. The effectiveness of the method on the cross‐domain unsupervised fault diagnosis problem is verified through three case studies.

show abstract

A novel joint distinct subspace learning and dynamic distribution adaptation method for fault transfer diagnosis

Cited by 15 publications

References 41 publications

Non-Uniformly Weighted Multisource Domain Adaptation Network For Fault Diagnosis Under Varying Working Conditions

Non-Uniformly Weighted Multisource Domain Adaptation Network For Fault Diagnosis Under Varying Working Conditions

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

Joint alignment network preserving structural information for multimode process fault diagnosis

Contact Info

Product

Resources

About