A multi-source ensemble domain adaptation method for rotary machine fault diagnosis

Yang, Shengkang; Kong, Xianwen; Wang, Qibin; Li, Zhongquan; Cheng, Huang; Lu, Yu

doi:10.1016/j.measurement.2021.110213

Cited by 49 publications

(9 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, because these are all single-source domain transfer models, negative transfer is still possible. Yang et al [8] proposed a data-based multisource domain transfer model in response to this circumstance, which successfully suppressed the problem of the diagnosis shift in single-source domain transfer. The data-based multisource domain transfer model, however, has a complicated structure and a limited capacity for generalization.…”

Section: Introductionmentioning

confidence: 99%

A cross-domain intelligent fault diagnosis method based on multi-source domain feature adaptation and selection

Jia,

Huang,

Cheng

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Although fault diagnosis methods integrating transfer learning are research hotspots, their ability to handle industrial fault diagnosis problems with large domain differences still needs to be improved. A multi-source domain feature adaptation and selection (MDFAS) method is presented to address the issues of domain mismatch and domain negative transfer. The method integrates the top-level network parameter transfer strategy with the 2D Convolutional Neural Network (2DCNN) backbone network to acquire the target domain feature extractor quickly. Multiple feature adaptive extractors (FAEs) are constructed using a multi-branch structure to align the source and target domain's feature distributions, respectively. The inter-domain distance computed by multi-kernel maximum mean discrepancy (MK-MMD) is embedded in the FAEs loss function to improve the inter-domain matching degree. Based on the information gain of the adaptively integrated features, the ensemble adaptive selection is performed on the extracted feature matrices to exclude the negative transfer feature. Finally, the effective feature matrix is input into the diagnosis classifier for classification. Cross-domain fault diagnosis experiments are developed based on the data set gathered from several types of rotating machinery operated under varied working conditions. The experimental results show that the proposed method outperforms the existing intelligent fault diagnosis methods in terms of fault detection accuracy, generalization, and stability.

show abstract

Section: Introductionmentioning

confidence: 99%

A cross-domain intelligent fault diagnosis method based on multi-source domain feature adaptation and selection

Jia,

Huang,

Cheng

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…For the DL-based RUL prediction, sufficient training data and the hypothesis of distribution consistency are required to achieve high accuracy and robustness. These requirements are challenging to meet in real-world prognostic tasks because different operating conditions or degradation patterns can cause changes in the data characteristics of mechanical entities [12,13]. Aiming at these problems, the fine-tuning strategy, one of the transfer learning (TL) approaches, has been used to transfer the pretraining model to the target prediction tasks [14,15].…”

Section: Introductionmentioning

confidence: 99%

Multi-representation transferable attention network for remaining useful life prediction of rolling bearings under multiple working conditions

Shi,

Cui,

Cheng

et al. 2023

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

Remaining useful life (RUL) prediction improves equipment reliability by avoiding unexpected breakdowns. However, different operating conditions may cause the performance degradation of the prediction model due to the domain-shift problem. Therefore, a novel method based on the multiple representation transferable attention network (MRTAN) is proposed in this paper for RUL prediction under multiple working conditions. In the MRTAN-based method, multiple convolutional modules are first used to learn the degradation features. Next, the multi-representation adaptation module is utilized to further mine the multiple domain-invariant representations. Then, during the training process, the transferable attention module can activate the representation with high transferability dynamically. Finally, the prognostic model is optimized by multiple optimization objectives and the back-propagation algorithm. Besides, multiple cross-domain RUL prediction tasks are employed to validate the effectiveness of the MRTAN-based model. Experiments demonstrate that the proposed method can provide better prognostic performance and avoid the negative transfer problem.

show abstract

“…Transfer learning is an effective approach to improve the generalization and reliability of models under varying working conditions. [14][15][16] Specifically, domain adaptation 17,18 is able to learn the correlation between the features of the source and target domains, and reduce the domain discrepancy, thereby enabling knowledge transfer between domains. By leveraging domain adaptation techniques, the problem of domain shift caused by varying working conditions in equipment status monitoring can be effectively addressed, leading to better adaptation to practical applications of status monitoring equipment under variable working conditions.…”

Section: Introductionmentioning

confidence: 99%

Health status monitoring of high-speed train brake pads considering noise under variable working conditions

Kang

Zhang

et al. 2023

Structural Health Monitoring

View full text Add to dashboard Cite

The brake pads of high-speed trains operate under complex and variable conditions, and the collected brake signals are easily affected by noise, making monitoring the health status of brake pads more difficult. A multi-representation adaptation network for online monitoring the health status of high-speed train brake pads, which are affected by noise under variable working conditions, is proposed in this study. First, a parameter-sharing deep residual network is used to extract the friction block features of the source and target domain data. Then, the features are mapped to different low-dimensional feature spaces through the inception adaptation module, and multiple representations are obtained. The network applies conditional maximum mean discrepancy to align representations of the source and target domains, thus learning multiple domain-invariant representations. Hence, the network acquires more knowledge of the friction block status and attenuates the interference of noise signals on the status monitoring. The friction block vibration data were collected from various brake disc speeds, and variable working condition-transfer experiments under the influence of noise were performed on the brake friction and bearing datasets. The results show that the proposed network outperforms other transfer methods, which can better extract and identify the status features of the friction block under the noise interference.

show abstract

A multi-source ensemble domain adaptation method for rotary machine fault diagnosis

Cited by 49 publications

References 41 publications

A cross-domain intelligent fault diagnosis method based on multi-source domain feature adaptation and selection

A cross-domain intelligent fault diagnosis method based on multi-source domain feature adaptation and selection

Multi-representation transferable attention network for remaining useful life prediction of rolling bearings under multiple working conditions

Health status monitoring of high-speed train brake pads considering noise under variable working conditions

Contact Info

Product

Resources

About