A Deep Transfer Model With Wasserstein Distance Guided Multi-Adversarial Networks for Bearing Fault Diagnosis Under Different Working Conditions

Zhang, Ming; Wang, Duo; Lu, Weining; Yang, Jun; Li, Zhiheng; Liang, Bin

doi:10.1109/access.2019.2916935

Cited by 101 publications

(51 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In [15], Cheng et al utilized Wasserstein distance to minimize distribution discrepancy through adversarial training in fault diagnosis transfer learning scenarios. Instead of minimizing Wasserstein distance between one single layer of the neural network, Zhang et al [16] proposed to learn domain invariant representations through minimizing the Wasserstein distance between multi-layers of the deep neural network and achieves better accuracy on bearing fault diagnosis tasks.…”

Section: Wasserstein Distancementioning

confidence: 99%

“…The feature extractor is trained to confuse the domain discriminator while minimizing the classification loss. The Wasserstein distance has recently been introduced into domain adaptation of fault diagnosis and achieves competitive results [15,16]. In [15] Cheng et al utilized Wasserstein distance to minimize distribution discrepancy through adversarial training in fault diagnosis transfer learning scenarios.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Triplet Loss Guided Adversarial Domain Adaptation for Bearing Fault Diagnosis

Wang

Liu

2020

Sensors

View full text Add to dashboard Cite

Recently, deep learning methods are becomingincreasingly popular in the field of fault diagnosis and achieve great success. However, since the rotation speeds and load conditions of rotating machines are subject to change during operations, the distribution of labeled training dataset for intelligent fault diagnosis model is different from the distribution of unlabeled testing dataset, where domain shift occurs. The performance of the fault diagnosis may significantly degrade due to this domain shift problem. Unsupervised domain adaptation has been proposed to alleviate this problem by aligning the distribution between labeled source domain and unlabeled target domain. In this paper, we propose triplet loss guided adversarial domain adaptation method (TLADA) for bearing fault diagnosis by jointly aligning the data-level and class-level distribution. Data-level alignment is achieved using Wasserstein distance-based adversarial approach, and the discrepancy of distributions in feature space is further minimized at class level by the triplet loss. Unlike other center loss-based class-level alignment approaches, which hasto compute the class centers for each class and minimize the distance of same class center from different domain, the proposed TLADA method concatenates 2 mini-batches from source and target domain into a single mini-batch and imposes triplet loss to the whole mini-batch ignoring the domains. Therefore, the overhead of updating the class center is eliminated. The effectiveness of the proposed method is validated on CWRU dataset and Paderborn dataset through extensive transfer fault diagnosis experiments.

show abstract

Section: Wasserstein Distancementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Triplet Loss Guided Adversarial Domain Adaptation for Bearing Fault Diagnosis

Wang

Liu

2020

Sensors

View full text Add to dashboard Cite

show abstract

“…Based on the theory, several recent studies have focused on obtaining domain-invariant representations using maximum mean discrepancy (MMD) [15] or adversarial training [16]- [18]. In [22], using Wasserstein distance in adversarial training was suggested to minimize the dissimilarity between the source and target domain distributions.…”

Section: B Domain Adaptationmentioning

confidence: 99%

“…Wasserstein distance has recently gained popularity as an ingredient for loss functions in the field of artificial intelligence, due to its advantage over other discrepancy measures between probability distributions, such as total variation distance, Kullback-Leibler divergence, and Jensen-Shannon divergence. [22], [28]- [30]. Since Wasserstein distance takes into account the properties of the underlying geometry, unlike the other dissimilarity measures mentioned, it assigns finite distance value even when two distributions do not share support [28].…”

Section: ) Notationmentioning

confidence: 99%

Joint Transfer of Model Knowledge and Fairness Over Domains Using Wasserstein Distance

Yoon

Lee

2020

IEEE Access

View full text Add to dashboard Cite

Owing to the increasing use of machine learning in our daily lives, the problem of fairness has recently become an important topic in machine learning societies. Recent studies regarding fairness in machine learning have been conducted to attempt to ensure statistical independence between individual model predictions and designated sensitive attributes. However, in reality, cases exist in which the sensitive variables of data used for learning models differ from the data upon which the model is applied. In this paper, we investigate a methodology for developing a fair classification model for data with limited or no labels, by transferring knowledge from another data domain where information is fully available. This is done by controlling the Wasserstein distances between relevant distributions. Subsequently, we obtain a fair model that could be successfully applied to two datasets with different sensitive attributes. We present theoretical results validating that our approach provably transfers both classification performance and fairness over domains. Experimental results show that our method does indeed promote fairness for the target domain, while retaining reasonable classification accuracy, and that it often outperforms comparative models in terms of joint fairness.

show abstract

“…The Regularized Convolutional Neural Networks (RCNN) [32] combines CNNs and multiple kernel learning to address the small-sample-size problem in bearing fault diagnosis under various working conditions. The Wasserstein Distance guided Multi-Adversarial Networks (WDMANs) [33] employ a multiple-domain critic network to learn the shared feature representation between the source domain and target domain. The Triplet Loss guided Adversarial Domain Adaptation (TLADA) [34] aligns the domain distributions using the Wasserstein distance to match the class distribution by assigning pseudolabels for target samples.…”

Section: Related Workmentioning

confidence: 99%

Prediction Consistency Guided Convolutional Neural Networks for Cross-Domain Bearing Fault Diagnosis

Jing

Zhang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

An underlying assumption in bearing fault diagnosis is that the training data from a source domain and the test data from a target domain obey the same distribution. But this assumption can be easily violated in practical industrial environments due to domain shift, which leads to significant performance degradation. To overcome this issue, we propose a novel convolutional neural network model to identify cross-domain bearing fault types based on 1-D vibration signals. Different from current single-networkbased approaches, our model comprises a student network and a teacher network that simultaneously conduct data distribution matching and discriminative feature learning. Moreover, the two networks promote each other with the label prediction consistency constraint, so that the discriminative knowledge is able to transfer between the domains. Our model bridges the semantic information of the source vibration signals and the distribution information of the target vibration signals by jointly performing cross-domain feature disentanglement and adaptation. The proposed method is evaluated extensively on the Case Western Reserve University bearing fault dataset in two scenarios: varying working loads and different sensor locations. Experimental results show the superior performance of our method compared with existing shallow and deep learning methods in the literature. INDEX TERMS Bearing fault diagnosis, domain shift, convolutional neural networks, bearing reliability, mean-teacher model, rotating machinery, domain adaptation, knowledge transfer.

show abstract

A Deep Transfer Model With Wasserstein Distance Guided Multi-Adversarial Networks for Bearing Fault Diagnosis Under Different Working Conditions

Cited by 101 publications

References 32 publications

Triplet Loss Guided Adversarial Domain Adaptation for Bearing Fault Diagnosis

Triplet Loss Guided Adversarial Domain Adaptation for Bearing Fault Diagnosis

Joint Transfer of Model Knowledge and Fairness Over Domains Using Wasserstein Distance

Prediction Consistency Guided Convolutional Neural Networks for Cross-Domain Bearing Fault Diagnosis

Contact Info

Product

Resources

About