Conditional Adversarial Domain Adaptation With Discrimination Embedding for Locomotive Fault Diagnosis

Yu, Xiaolei; Zhao, Zhibin; Zhang, Xingwu; Sun, Chuang; Gong, Baogui; Yan, Ruqiang

doi:10.1109/tim.2020.3031198

Cited by 49 publications

(22 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most existing works focus on the adaptation between operating conditions and have found classic DA methods beneficial [33]. Adversarial alignment [34] is widely used by existing works [35], [36] and improved by conditional discriminators [37], [38]. Generative adversarial networks (GANs) are also explored to generate faults [39] to alleviate domain gap.…”

Section: Da For Fault Diagnosismentioning

confidence: 99%

Integrating Expert Knowledge With Domain Adaptation for Unsupervised Fault Diagnosis

Wang

Taal

Fink

2022

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

Data-driven fault diagnosis methods often require abundant labeled examples for each fault type. On the contrary, real-world data is often unlabeled and consists of mostly healthy observations and only few samples of faulty conditions. The lack of labels and fault samples imposes a significant challenge for existing data-driven fault diagnosis methods. In this article, we aim to overcome this limitation by integrating expert knowledge with domain adaptation (DA) in a synthetic-to-real framework for unsupervised fault diagnosis. Motivated by the fact that domain experts often have a relatively good understanding on how different fault types affect healthy signals, in the first step of the proposed framework, a synthetic fault dataset is generated by augmenting real vibration samples of healthy bearings. This synthetic dataset integrates expert knowledge and encodes class information about the faults types. However, models trained solely based on the synthetic data often do not perform well because of the distinct distribution difference between the synthetically generated and real faults. To overcome this domain gap between the synthetic and real data, in the second step of the proposed framework, an imbalance-robust DA approach is proposed to adapt the model from synthetic faults (source) to the unlabeled real faults (target) which suffer from severe class imbalance. The framework is evaluated on two unsupervised fault diagnosis cases for bearings, the CWRU laboratory dataset and a real-world wind-turbine dataset. Experimental results demonstrate that the generated faults are effective for encoding fault type information and the DA is robust against the different levels of class imbalance between faults.

show abstract

Section: Da For Fault Diagnosismentioning

confidence: 99%

Integrating Expert Knowledge With Domain Adaptation for Unsupervised Fault Diagnosis

Wang

Taal

Fink

2022

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

show abstract

“…Robust knowledge of source features maps into approximate target maps by fooling the feature extractor with a reverse gradient layer. Consequently, a classifier can use the knowledge to define unlabeled fault types in the target domain [47]. As a final point, The Optimization objective as a binary cross entropy loss of the adversarial domain network is shown as follows:…”

Section: Domain Adversarial Networkmentioning

confidence: 99%

Spatial Graph Convolutional Neural Network via Structured Subdomain Adaptation and Domain Adversarial Learning for Bearing Fault Diagnosis

Ghorvei¹,

Kavianpour²,

Beheshti³

et al. 2021

Preprint

View full text Add to dashboard Cite

Unsupervised domain adaptation (UDA) has shown remarkable results in bearing fault diagnosis under changing working conditions in recent years. However, most UDA methods do not consider the geometric structure of the data. Furthermore, the global domain adaptation technique is commonly applied, which ignores the relation between subdomains. This paper addresses mentioned challenges by presenting the novel deep subdomain adaptation graph convolution neural network (DSAGCN), which has two key characteristics: First, graph convolution neural network (GCNN) is employed to model the structure of data. Second, adversarial domain adaptation and local maximum mean discrepancy (LMMD) methods are applied concurrently to align the subdomain's distribution and reduce structure discrepancy between relevant subdomains and global domains. CWRU and Paderborn bearing datasets are used to validate the DSAGCN method's efficiency and superiority between comparison models. The experimental results demonstrate the significance of aligning structured subdomains along with domain adaptation methods to obtain an accurate data-driven model in unsupervised fault diagnosis.

show abstract

“…39,40 Yang et al 38 proposed a deep multi-layer domain adaptation network with MMD minimization for health monitoring and diagnosis of bearings used in real-case machines. Yu et al 39 conducted the conditional adversarial training between sufficient labeled source data and unlabeled target data and verified the methods in the case studies of bearing, traction motor, and railway locomotive, respectively. Chen et al 40 designed a domain adversarial transfer network with an asymmetric structure for the task-specific feature learning of machinery and achieved superior transfer performance between different rotating speeds.…”

mentioning

confidence: 99%

“…[34][35][36][37][38][39][40] The widely discussed domain adaptation schemes mainly include maximum mean discrepancy (MMD) minimization [36][37][38] and adversarial training. 39,40 Yang et al 38 proposed a deep multi-layer domain adaptation network with MMD minimization for health monitoring and diagnosis of bearings used in real-case machines. Yu et al 39 conducted the conditional adversarial training between sufficient labeled source data and unlabeled target data and verified the methods in the case studies of bearing, traction motor, and railway locomotive, respectively.…”

mentioning

confidence: 99%

“…These works assume the existence of sufficiently labeled source data and unlabeled target data. [34][35][36][37][38][39][40] The widely discussed domain adaptation schemes mainly include maximum mean discrepancy (MMD) minimization [36][37][38] and adversarial training. 39,40 Yang et al 38 proposed a deep multi-layer domain adaptation network with MMD minimization for health monitoring and diagnosis of bearings used in real-case machines.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Cross‐machine intelligent fault diagnosis of gearbox based on deep learning and parameter transfer

Han

Zhou

Xiang

et al. 2021

Structural Contr & Hlth

View full text Add to dashboard Cite

With the rapid development of artificial intelligence technologies, data-driven methods have significantly contributed to the intelligent monitoring and diagnosis of mechanical systems. However, the state-of-the-art approaches, especially the deep learning-based ones, implicitly assume the availability of large amounts of labeled fault data for supervised training, which is often infeasible due to the highly reliable system design in the field. In this research, a deep transfer convolutional neural network (CNN) scheme is proposed to enhance the diagnosis performance when dealing with insufficient training data in the target domain. By utilizing transfer learning, rich but relevant feature representation can be learnt from massive data in the source domain. The learnt weights and biases in the source domain are transferred to the target task as the initial parameter values. Then, the transferred parameters are properly fine-tuned with the small labeled datasets in the target domain. To avoid overfitting in the case of scarcely labeled samples in the target domain, global average pooling (GAP) is introduced to replace the fully-connected layers, and the traditional architecture in CNN is modified, to reduce the number of trainable parameters. Finally, by fully considering the transfer scenarios between diverse operating conditions and diverse machines, the cross-machine transfer experiments are designed with three gearbox datasets provided by the Prognostic and Health Management (PHM) 2009 conference, the Tsinghua University, and the University of Alberta. The results demonstrate the effectiveness of the proposed method with scarce labeled samples in the target domain. K E Y W O R D S convolutional neural network, deep transfer learning, gearbox fault diagnosis, global average pooling, scarcely labeled samples 1 | INTRODUCTION Machinery condition monitoring and fault diagnosis is a classic problem in the manufacturing industry. 1-4 Generally, the machinery fault diagnosis methods can be categorized into three classes, including model-based methods, knowledge-based methods, and data-driven methods. The model-based methods, such as finite element simulation and system identification, can perform fault diagnosis by monitoring the consistency between the real-time variables of the practical machine and the model-predicted values. However, due to the complex structure and working mechanism,

show abstract

Conditional Adversarial Domain Adaptation With Discrimination Embedding for Locomotive Fault Diagnosis

Cited by 49 publications

References 28 publications

Integrating Expert Knowledge With Domain Adaptation for Unsupervised Fault Diagnosis

Integrating Expert Knowledge With Domain Adaptation for Unsupervised Fault Diagnosis

Spatial Graph Convolutional Neural Network via Structured Subdomain Adaptation and Domain Adversarial Learning for Bearing Fault Diagnosis

Cross‐machine intelligent fault diagnosis of gearbox based on deep learning and parameter transfer

Contact Info

Product

Resources

About