Deep Domain Adaptation Model for Bearing Fault Diagnosis with Domain Alignment and Discriminative Feature Learning

Abstract

Deep learning techniques have been widely used to achieve promising results for fault diagnosis. In many real-world fault diagnosis applications, labeled training data (source domain) and unlabeled test data (target domain) have different distributions due to the frequent changes of working conditions, leading to performance degradation. This study proposes an end-to-end unsupervised domain adaptation bearing fault diagnosis model that combines domain alignment and discriminative feature learning on the basis of a 1D convolutional neural network. Joint training with classification loss, center-based discriminative loss, and correlation alignment loss between the two domains can adapt learned representations in the source domain for application to the target domain. Such joint training can also guarantee domain-invariant features with good intraclass compactness and interclass separability. Meanwhile, the extracted features can efficiently improve the cross-domain testing performance. Experimental results on the Case Western Reserve University bearing datasets confirm the superiority of the proposed method over many existing methods.

Deep Clustering Bearing Fault Diagnosis Method Based on Local Manifold Learning of an Autoencoded Embedding

“…These signals are 48 kHz of the drive end's bearing fault data. To augment data, overlap sampling technique [10] is used to increase the number of samples. The datasets are described in detail in Table 1, where dataset A consists of 10000 samples of the 10 bearing health conditions at 1 hp and 1772 rpm, dataset B consists of 10000 samples of the 10 bearing health conditions at 2 hp and 1750 rpm, and dataset C consists of 10000 samples of the 10 bearing health conditions at 3 hp and 1730 rpm.…”

“…The most remarkable applications are based on the fault diagnosis classification model. That is, these applications consider that the vibration signal data have labels, and the applications mainly address two situations: (1) The training and test data are drawn from the same distribution, such as in [3][4][5][6]; and (2) The training data and test data are obtained from different distributions, such as in [7][8][9][10][11].…”

Multipoint Optimal Minimum Entropy Deconvolution Adjusted for Automatic Fault Diagnosis of Hoist Bearing

“…Moreover, the running state of hoist bearing is often unknown in practice. Although intelligent diagnosis methods have apparent effects based on learning and classification, they need to deal with complex algorithms and collect field fault data to get accurate diagnosis results [6][7][8][9]. However, for security reasons, it is extremely hard to obtain the different fault data of hoist bearing in actual working conditions.…”

Fault Diagnosis of Rolling Bearings of Different Working Conditions Based on Multi-Feature Spatial Domain Adaptation

“…Besides, more expressive features can be extracted automatically by deep transfer learning and it utilizes the self-extraction of deep learning together with transfer learning to acquire "new knowledge", which assist to solve small sample data problem well in few-shot learning [11]. This learning method is commonly used for mechanical fault diagnosis [12][13][14][15][16]. For example, Zhao et al [17] reported a transfer learning framework based on the deep multi-scale convolutional neural network.…”