2 April 2021 in IEEE Transactions on Industrial Informatics
Existing data-driven fault diagnosis methods assume that the label sets of the training data and test data are consistent, which is usually not applicable for real applications since the fault modes that occur in the test phase are unpredictable. To address this problem, open set fault diagnosis (OSFD), where the test label set consists of a portion of the training label set and some unknown classes, is studied in this article. Considering the changeable operating conditions of machinery, OSFD tasks are further divided into shared-domain open set fault diagnosis (SOSFD) and cross-domain open set fault diagnosis (COSFD) in this article. For SOSFD, 1-D convolutional neural networks are trained for learning discriminative features and recognizing fault modes. For COSFD, due to the distribution discrepancy between the source and target domains, the deep model needs to learn domain-invariant features of shared classes and separate features of outlier classes. Thus, by utilizing the output of an additional domain classifier, a model named bilateral weighted adversarial networks is proposed to assign large weights to shared classes and small weights to outlier classes during the feature alignment. In the test phase, samples are classified according to the outputs of the deep model and unknown-class samples are rejected by the extreme value theory model. Experimental results on two bearing datasets demonstrate the effectiveness and superiority of the proposed method.
14 July 2023 in Computers in Industry
1 April 2016 in Journal of Sound and Vibration
1 April 2019 in Mechanical Systems and Signal Processing
8 April 2021 in IEEE Transactions on Instrumentation and Measurement
Traditional deep learning assumes that the probability distributions of the test set and the training set are exactly the same. When the test samples and the training samples are from different working conditions, the distribution gap between different conditions might dramatically lower the accuracy. To address this problem, domain adaptation (DA) via joint using training and test sets is adopted to increase the final accuracy. The disadvantage of DA is that it requires test samples to participate in the training phase. However, sometimes it is impossible to collect the test samples beforehand. To solve this problem, this article proposes a conditional adversarial domain generalization with a single discriminator, which aims to extract domain-invariant features from different working conditions and generalize the features to unseen working conditions. To realize conditional adversarial training, a new conditional adversarial strategy that the feature extractor can allow the discriminator to distinguish the fault classes, but cannot distinguish the domains, is designed to better confuse the discriminator and generalize the features. Meanwhile, three loss functions, including mean square error (MSE), cross-entropy coupled with entropy, and cross-entropy combined with traditional adversarial methods, are proposed to achieve the new conditional adversarial strategy. The effectiveness of the conditional adversarial strategy is verified by training conditional generative adversarial networks (CGANs) on two image data sets, and the performance of the proposed domain generalization method for bearing fault diagnosis is also verified by bearing data sets. Compared with traditional conditional adversarial domain generalization, the proposed method can save computing resource consumption and improve accuracy that does not appear in the training phase.
19 October 2020 in IEEE Transactions on Instrumentation and Measurement
Deep-learning-based methods have been widely applied to fault diagnosis for its capability of automatically extracting features from massive data. However, there are still two problems that limit the application of these methods to the locomotive fault diagnosis, which has practical significance for ensuring the safety and reliability of the locomotive. First, due to variation in the operating condition in locomotive operation, the distribution of the training data is different from the distribution of the test data, which degrades the performance of the deep-learning-based methods. Second, the existing domain-adaptation (DA)-based diagnosis models are not robust enough to diagnose locomotive with many disturbances in its vibration signals. To tackle these problems, conditional adversarial DA with discrimination embedding (CADA-DE) is proposed in this article. By adding the discriminative information conveyed in the label predictions to the domain classifier, the distribution discrepancy between the source and target domains is alleviated more sufficiently. Meanwhile, the center-based discriminative loss is introduced to enforce features more discriminative. The experimental results conducted on three different data sets demonstrate the effectiveness and superiority of the proposed CADA-DE.