Fault Diagnosis for Rolling Bearings of a Freight Train under Limited Fault Data: Few-Shot Learning Method

Li, Chen-Zhong; Yang, Kanghua; Tang, Haichuan; Wang, Ping; Li, Jiebo; He, Qiang

doi:10.1061/jtepbs.0000554

Cited by 9 publications

(6 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed method uses the training example of a mechanical part to achieve the fault classification of different mechanical components. Li et al [ 105 ] proposed a rolling bearing fault diagnosis method based on 1D-CNN and small sample learning model C-WGAN, which can be classified when the training data are extremely limited. Wang et al [ 106 ] proposed a new domain adversarial transfer convolutional neural network DATCCNN.…”

Section: The Research Progress Of Adversarial-based Dtlmentioning

confidence: 99%

“…Physical knowledge can be integrated into the network to reduce the size of the required training set, and a small amount of learning is devoted to learning from a limited number of examples, which is a promising method for solving the problem of cross-category fault diagnosis. Xu et al [ 104 ] and Li et al [ 105 ] used few-shot learning for DTL troubleshooting, but the more challenging zero-shot technique is rarely used in DTLs troubleshooting.…”

Section: Challenges and Prospects Of Dtl In Industrial Fault Diagnosismentioning

confidence: 99%

See 1 more Smart Citation

Adversarial Deep Transfer Learning in Fault Diagnosis: Progress, Challenges, and Future Prospects

Guo,

Zhang,

Sun

et al. 2023

Sensors

View full text Add to dashboard Cite

Deep Transfer Learning (DTL) signifies a novel paradigm in machine learning, merging the superiorities of deep learning in feature representation with the merits of transfer learning in knowledge transference. This synergistic integration propels DTL to the forefront of research and development within the Intelligent Fault Diagnosis (IFD) sphere. While the early DTL paradigms, reliant on fine-tuning, demonstrated effectiveness, they encountered considerable obstacles in complex domains. In response to these challenges, Adversarial Deep Transfer Learning (ADTL) emerged. This review first categorizes ADTL into non-generative and generative models. The former expands upon traditional DTL, focusing on the efficient transference of features and mapping relationships, while the latter employs technologies such as Generative Adversarial Networks (GANs) to facilitate feature transformation. A thorough examination of the recent advancements of ADTL in the IFD field follows. The review concludes by summarizing the current challenges and future directions for DTL in fault diagnosis, including issues such as data imbalance, negative transfer, and adversarial training stability. Through this cohesive analysis, this review aims to offer valuable insights and guidance for the optimization and implementation of ADTL in real-world industrial scenarios.

show abstract

Section: The Research Progress Of Adversarial-based Dtlmentioning

confidence: 99%

Section: Challenges and Prospects Of Dtl In Industrial Fault Diagnosismentioning

confidence: 99%

Adversarial Deep Transfer Learning in Fault Diagnosis: Progress, Challenges, and Future Prospects

Guo,

Zhang,

Sun

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…However, the number of VMD modes K and penalty parameters α need to be selected and affect the decomposition. On the optimization of VMD parameters, (Ahmad et al, 2022;Li et al, 2021b) respectively estimated the value K through the frequency domain features of each mode by EMD and Local Mean Decomposition (LMD). (Asghar et al, 2021) used the correlation between the original signal and each IMF component to select the value of K, and achieved certain results, but did not consider the 1 Naval Research Institute, Beijing 100161, PR China 2 MEMS Center, Harbin Institute of Technology, Harbin 150001, China mutual influence between mode number K and penalty parameters α.…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Bearing fault diagnosis method based on variational mode decomposition optimized by CS-PSO

Liu¹,

Wang²,

Changwei³

et al. 2023

Journal of Vibration and Control

View full text Add to dashboard Cite

In order to solve the problem that bearing vibration signal fault feature is difficult to extract effectively under noise, a fault diagnosis method based on Variational Mode Decomposition (VMD) optimized by Cuckoo Search (CS) and Particle Swarm Optimization (PSO) is proposed. The effect of VMD is affected by the number of modes and the penalty parameter. The Levy flight strategy and elimination mechanism of the CS algorithm is added to PSO algorithm and the position updating process is optimized. According to the correlation coefficient and envelope entropy of the Intrinsic Mode Function (IMF), the objective function is constructed to search for the optimal combination of VMD mode number and penalty parameter. The bearing fault type is determined by analyzing the IMF envelope spectrum of the optimal objective function. The fault diagnosis classification task upon the bearing sample data from Case Western Reserve University demonstrates that the proposed CS-PSO algorithm improves the model’s classification performance by 5%, which is on average 7.3% higher than other state-of-the-art models. This model can provide an important reference for the accuracy of bearing fault diagnosis.

show abstract

“…Xu et al [17] designed a deep convolutional nearest neighbor matching network based on Matching Network and Knearest neighbors for solving the cross-component few-sample fault diagnosis problem. The metric based approach in the literature [18] uses prototypical network and relation network to solve the problem of few-shot fault diagnosis of bearings in one-shot, five-shot cases. It can be seen that these metalearning-based methods are useful in solving the problem of few-shot fault diagnosis and provide a theoretical basis for solving the problem of fault diagnosis in industrial systems.…”

Section: Introductionmentioning

confidence: 99%

Few shot cross equipment fault diagnosis method based on parameter optimization and feature mertic

Tao

Chen

Qiu

et al. 2022

Meas. Sci. Technol.

115

View full text Add to dashboard Cite

With the rapid development of industrial informatization and deep learning technology, modern data-driven fault diagnosis (MIFD) methods based on deep learning have been continuously emphasized by the industry. However, most of these methods require sufficient training samples to achieve the desired diagnostic effect, but the scarcity of fault samples in the actual industrial environment leads to the limited development of MIFD methods. In addition, due to the changes of equipment operating conditions and production requirements, data-driven fault diagnosis methods often need to face the cross domain problem of cross load or even cross different equipment. In this paper, a parameter optimization and feature metric-based fault diagnosis method with few samples, called model agnostic matching network model, is designed for the problem of sparse fault samples and cross-domain between data sets in real industrial environments. The method combines both a parameter-based optimization meta-learning network, which extracts optimization information adapted to different domains, and a metric-based meta-learning network, which extracts metric information for similarity discriminations. The experimental result show that the method outperforms the current baseline method for the 5-shot fault diagnosis problem of rolling bearings under limited data conditions and achieves an accuracy of up to 94.4% in cross-equipment diagnosis experiments from rolling bearings to gas regulators, indicating the feasibility of the method. The features are visualized by T-SNE to show the validity of the model.

show abstract

Fault Diagnosis for Rolling Bearings of a Freight Train under Limited Fault Data: Few-Shot Learning Method

Cited by 9 publications

References 36 publications

Adversarial Deep Transfer Learning in Fault Diagnosis: Progress, Challenges, and Future Prospects

Adversarial Deep Transfer Learning in Fault Diagnosis: Progress, Challenges, and Future Prospects

Bearing fault diagnosis method based on variational mode decomposition optimized by CS-PSO

Few shot cross equipment fault diagnosis method based on parameter optimization and feature mertic

Contact Info

Product

Resources

About