Federated Multi-Model Transfer Learning-Based Fault Diagnosis with Peer-to-Peer Network for Wind Turbine Cluster

Yang, Wanqian; Nakahara, Yuya

doi:10.3390/machines10110972

Cited by 5 publications

(3 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The fault diagnosis model applicable to most clients was constructed by filtering biased data in iterations. Similarly, Yang and Yu [9] proposed a peer-to-peer federation migration learning method based on multi-task learning model transfer and model fusion with dynamic adaptive weight adjustment. Sima et al [10] fine-tuned client models to accommodate the smallsample imbalanced problem of the power line fault data.…”

Section: Ftl-based Fault Diagnosismentioning

confidence: 99%

Open-set federated adversarial domain adaptation based cross-domain fault diagnosis

Song

2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

Data-driven fault diagnosis techniques utilizing deep learning have achieved widespread success. However, their diagnostic capability and application possibility are significantly reduced in real-world scenarios where fault modes are not fully covered and labels are lacking. Owing to potential conflicts of interest and legal risks, industrial equipment fault data usually exist in the form of isolated islands, making it difficult to carry out large-scale centralized model training. This paper proposes open-set federated adversarial domain adaptation (OS-FADA) to achieve collaborative evolution of fault diagnosis capabilities among cross-domain data owners while protecting privacy. The OS-FADA is a general fault diagnosis framework that employs two-phase adversarial learning. First, faced with the data distribution shift caused by variable working conditions, a generative adversarial feature extractor training strategy is designed to achieve domain-invariant fault feature extraction by approximating the feature distributions of clients to a unified generated distribution. Second, considering the label distribution shift of unknown faults occurring in the target client, an adversarial learning method is proposed to establish decision boundaries between known and unknown faults. Ultimately, the co-evolution of fault diagnosis models between clients is achieved by combining two-phase adversarial learning and federated aggregation. Results from an industrial gearbox case demonstrate that our proposed method achieves over 20% diagnostic accuracy improvement and has excellent potential for cross-domain fault diagnosis tasks with unknown faults when the data silos problem cannot be ignored.

show abstract

Section: Ftl-based Fault Diagnosismentioning

confidence: 99%

Open-set federated adversarial domain adaptation based cross-domain fault diagnosis

Song

2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…TL method fetches existing knowledge to solve problems in different fields [7], which has been gradually applied in fault diagnosis of wind turbines , e.g. blade defects detection [8], gearbox fault diagnosis [9], bearing fault diagnosis [10], power forecasting [11,12], et al Jamil et al proposed a coined deep boosted TL for fault detection of wind turbine gearbox [13]. Zhang proposed a method based on balanced joint adaptive network to transfer WTs data from other wind farms to the target new wind farm [14].…”

Section: Introductionmentioning

confidence: 99%

A novel multi-task transfer model to realize unsupervised fault diagnosis of newly constructed wind turbines under variable conditions

liu,

Sha,

Zhang

et al. 2024

Fourth International Conference on Mechanical Engineering, Intelligent Manufacturing, and Automation Technology (MEMAT 2023)

View full text Add to dashboard Cite

Fault diagnosis can effectively improve the power generation of the wind turbines. Deep learning has promoted the intelligent development of wind turbine fault diagnosis. Traditional deep learning usually requires a sufficient amount of labeled data. However, for newly constructed wind turbines, there are problems such as insufficient samples, limited labels, variable operating conditions. Transfer learning provides a new way to solve these problems. Establishing appropriate models to reduce the distribution differences between existing and newly built units is the key to improving unsupervised fault diagnosis accuracy for newly built units. To address these challenges, a novel multi-task transfer model based on improved model agnostic meta learning (MT-TL-MAML) was proposed to realize unsupervised fault diagnosis of newly constructed wind turbines. The proposed model utilizes the advantages of MAML in generalization of new tasks and small sample diagnosis, and can adapt to randomly changing working conditions. By means of iterative learning, the gap between source domain and target domain is further narrowed, and the classifier can realize more accurate diagnosis of target domain data. This article takes the SCADA and CMS data of two wind farms as case studies to conduct unsupervised fault diagnosis and compare it with other literatures. The results validate the advantages of the proposed model in unsupervised fault diagnosis of newly constructed wind turbines.

show abstract

“…The results show that the accuracy of the fusion model is 84.6%, which is 7.7%, 12.8% and 10.2% higher than that of the single model. Yang and Yu [36] proposed a multi-model transfer and dynamic adaptive weight adjustment model fusion method for fault diagnosis of large-scale wind turbine groups. The test results on the CWRU dataset, FSTB Direction-X dataset and FSTB Fusion dataset show that the proposed multimodel fusion method has high effectiveness and better performance than the single model algorithm.…”

Section: Introductionmentioning

confidence: 99%

An intelligent feature recognition method of natural gas pipelines based on shapelet and blending fusion model

Ma,

Hu,

Wang

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

Despite the availability of pipeline bending strain detection technologies based on inertial measurement unit (IMU), there is a lack of intelligent and efficient methods for accurately identifying pipeline features by bending strain. Therefore, this paper proposes a novel method for identifying features in natural gas pipelines based on shapelet and blending fusion model. Specifically, the shape features of the bending strain data are extracted and transformed by shapelet. Then a blending fusion model with SVM, Decision Tree and Gradient Boosting as base learners and Random Forest as meta-learner is constructed. Finally, the extracted features are fed into the blending fusion model for pipeline feature recognition. The model is trained with bending strain data obtained from a real natural gas pipeline, the results indicate that the recognition accuracy of the proposed method is 97.17%. Compared with other models, the superiority of the proposed model is verified, and it is proved that the proposed method has better accuracy than the existing models (over 1.3%). Overall, the method proposed in this paper can be effectively combined with the in-line inspection system to provide a reference for pipeline companies to carry out pipeline integrity management.

show abstract

Federated Multi-Model Transfer Learning-Based Fault Diagnosis with Peer-to-Peer Network for Wind Turbine Cluster

Cited by 5 publications

References 60 publications

Open-set federated adversarial domain adaptation based cross-domain fault diagnosis

Open-set federated adversarial domain adaptation based cross-domain fault diagnosis

A novel multi-task transfer model to realize unsupervised fault diagnosis of newly constructed wind turbines under variable conditions

An intelligent feature recognition method of natural gas pipelines based on shapelet and blending fusion model

Contact Info

Product

Resources

About