Subdomain Adaptation Order Network for Fault Diagnosis of Brushless DC Motors

Luo, Chong; Wang, Jianyu; Zio, Enrico; Miao, Qiang

doi:10.1109/tim.2024.3350136

Cited by 4 publications

(1 citation statement)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Data augmentation is used to increase the number and diversity of training datasets, which can relieve the underfitting phenomenon in the deep learning model [27]. However, transfer learning heavily depends on the relevance and quality of the source domain data [28], whereas data augmentation faces the risk of disrupting the original data distribution. Feature enhancement strategy concentrates on optimizing the model structure [29] or employing data fusion techniques [30] to directly capture the robust features from limited samples.…”

Section: Introductionmentioning

confidence: 99%

Fault diagnosis of induction motor in the cooling water supply system using a multi-channel data fusion transformer with limited sample conditions^*

Niu,

Wang,

Miao

2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Induction motors play a vital role in the cooling water supply system of hydropower facilities. However, it is unrealistic to collect suffi-cient fault samples in hydropower station. The scarcity of labeled samples poses a challenge in developing a powerful diagnostic model with high classification accuracy. To address this challenge, this paper proposes a multi-channel data fusion strategy based on Trans-former for feature enhancement. Initially, original signals are transferred into non-overlapping single-channel data patches to preserve correlation features across different channels. Then, temporal and spatial attention modules are applied to process the data patches, which can learn and fuse temporal and spatial information, respectively. Subsequently, the data patches are embedded to retain posi-tion information and represent fault-related features through class embedding, which are further processed by a Transformer encoder with self-attention mechanisms. Finally, the classification task is achieved by utilizing a multilayer perceptron layer connected to the class embedding. In facing up with limited training samples, the proposed method could learn robust features that are beneficial to improve the fault diagnosis ability of induction motor. The proposed method is compared with three basic models and two improved methods, demonstrating the superiority of the proposed method in accuracy and feature clustering performance with limited sample conditions. Additionally, the ablation experiment demonstrates the necessity of each module in the proposed method.

show abstract

Section: Introductionmentioning

confidence: 99%

Fault diagnosis of induction motor in the cooling water supply system using a multi-channel data fusion transformer with limited sample conditions^*

Niu,

Wang,

Miao

2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

Intelligent fault diagnosis of multi-source cross-machine bearings based on center-weighted optimal transport and class-level alignment domain adaptation

Shang,

Wu,

Liu

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Most of the current domain adaptation research mainly focuses on the single-source or multi-source domain transfer constructed under different working conditions of the same machine. In the face of cross-machine tasks with significant domain discrepancy, forcing the direct feature alignment between the source domain and the target domain samples may lead to negative transfer and reduce the diagnostic performance of the model. In order to overcome the above limitations, this paper proposes a multi-source deep transfer model based on center-weighted optimal transport and class-level alignment domain adaptation (CWOT-CLADA). Firstly, to enhance the ability to represent deep features, a multi-structure feature representation network is constructed to enrich the information capacity embedded in deep features to obtain better domain adaptation ability. Then, the local maximum mean discrepancy is introduced to mine the fine-grained information fully and discriminative features between different source domains, minimize the distribution discrepancy between each source domain, and then capture reliable and generalized multi-source domain invariant features. On this basis, a center-weighted multi-source optimal transport strategy is designed, which comprehensively considers the transport cost of intra-domain uncertainty and inter-domain correlation between samples. More effective transport is established between the source domain and the target domain, which alleviates the negative transfer problem of samples and improves the cross-machine diagnosis performance of the model. Finally, the case study of multiple cross-machine transfer diagnosis tasks proves that the diagnostic accuracy and fault transfer ability of the proposed method are better than the existing domain adaptation methods.

show abstract

DTST: A Dual-Aspect Time Series Transformer Model for Fault Diagnosis of Space Power System

Xu,

Du,

Zhang

et al. 2024

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

Subdomain Adaptation Order Network for Fault Diagnosis of Brushless DC Motors

Cited by 4 publications

References 32 publications

Fault diagnosis of induction motor in the cooling water supply system using a multi-channel data fusion transformer with limited sample conditions^*

Fault diagnosis of induction motor in the cooling water supply system using a multi-channel data fusion transformer with limited sample conditions^*

Intelligent fault diagnosis of multi-source cross-machine bearings based on center-weighted optimal transport and class-level alignment domain adaptation

DTST: A Dual-Aspect Time Series Transformer Model for Fault Diagnosis of Space Power System

Contact Info

Product

Resources

About

Subdomain Adaptation Order Network for Fault Diagnosis of Brushless DC Motors

Cited by 4 publications

References 32 publications

Fault diagnosis of induction motor in the cooling water supply system using a multi-channel data fusion transformer with limited sample conditions*

Fault diagnosis of induction motor in the cooling water supply system using a multi-channel data fusion transformer with limited sample conditions*

Intelligent fault diagnosis of multi-source cross-machine bearings based on center-weighted optimal transport and class-level alignment domain adaptation

DTST: A Dual-Aspect Time Series Transformer Model for Fault Diagnosis of Space Power System

Contact Info

Product

Resources

About

Fault diagnosis of induction motor in the cooling water supply system using a multi-channel data fusion transformer with limited sample conditions^*

Fault diagnosis of induction motor in the cooling water supply system using a multi-channel data fusion transformer with limited sample conditions^*