Simultaneously Improve Transferability and Discriminability for Adversarial Domain Adaptation

Although adversarial domain adaptation enhances feature transferability, the feature discriminability will be degraded in the process of adversarial learning. Moreover, most domain adaptation methods only focus on distribution matching in the feature space; however, shifts in the joint distributions of input features and output labels linger in the network, and thus, the transferability is not fully exploited. In this paper, we propose a matrix rank embedding (MRE) method to enhance feature discriminability and transferability simultaneously. MRE restores a low-rank structure for data in the same class and enforces a maximum separation structure for data in different classes. In this manner, the variations within the subspace are reduced, and the separation between the subspaces is increased, resulting in improved discriminability. In addition to statistically aligning the class-conditional distribution in the feature space, MRE forces the data of the same class in different domains to exhibit an approximate low-rank structure, thereby aligning the class-conditional distribution in the label space, resulting in improved transferability. MRE is computationally efficient and can be used as a plug-and-play term for other adversarial domain adaptation networks. Comprehensive experiments demonstrate that MRE can advance state-of-the-art domain adaptation methods.     

Domain Adaptation with Data Uncertainty Measure Based on Evidence Theory

Domain adaptation aims to learn a classifier for a target domain task by using related labeled data from the source domain. Because source domain data and target domain task may be mismatched, there is an uncertainty of source domain data with respect to the target domain task. Ignoring the uncertainty may lead to models with unreliable and suboptimal classification results for the target domain task. However, most previous works focus on reducing the gap in data distribution between the source and target domains. They do not consider the uncertainty of source domain data about the target domain task and cannot apply the uncertainty to learn an adaptive classifier. Aimed at this problem, we revisit the domain adaptation from source domain data uncertainty based on evidence theory and thereby devise an adaptive classifier with the uncertainty measure. Based on evidence theory, we first design an evidence net to estimate the uncertainty of source domain data about the target domain task. Second, we design a general loss function with the uncertainty measure for the adaptive classifier and extend the loss function to support vector machine. Finally, numerical experiments on simulation datasets and real-world applications are given to comprehensively demonstrate the effectiveness of the adaptive classifier with the uncertainty measure.     

TESPDA-SEI: Tensor embedding substructure preserving domain adaptation for specific emitter identification

For the specific emitter identification (SEI) with few or no labels, domain adaptation make the model respond quickly with the help of empirical information. However, the more extreme case is that there are so few labeled samples in the source domain that it is difficult to train an excellent recognition model. In fact, it is more valuable to make full use of these limited label information. This work aims at proposing an unsupervised domain adaptation (UDA)-based method to accommodate the typical case of no labels in the target domain and small samples in the source domain when new devices are first introduced. The basic principle is to learn tensor embedding shared feature space and preserving inter-class substructure, which perform feature space mapping under the joint source and target domain led by mapping error minimize in the source domain. Specifically, this tensor embedding substructure preserving domain adaptation (TESPDA) consist of three parts, tensor invariant subspace learning, substructure preserving feature space mapping and pseudo-label prediction, which are used to learn inter-class substructure after tensor space mapping and identify the predict labels for the target domain. Finally, experiments are conducted on the real-word ADS-B dataset to demonstrate the effectiveness of the TESPDA method.     

A New Universal Domain Adaptive Method for Diagnosing Unknown Bearing Faults

The domain adaptation problem in transfer learning has received extensive attention in recent years. The existing transfer model for solving domain alignment always assumes that the label space is completely shared between domains. However, this assumption is untrue in the actual industry and limits the application scope of the transfer model. Therefore, a universal domain method is proposed, which not only effectively reduces the problem of network failure caused by unknown fault types in the target domain but also breaks the premise of sharing the label space. The proposed framework takes into account the discrepancy of the fault features shown by different fault types and forms the feature center for fault diagnosis by extracting the features of samples of each fault type. Three optimization functions are added to solve the negative transfer problem when the model solves samples of unknown fault types. This study verifies the performance advantages of the framework for variable speed through experiments of multiple datasets. It can be seen from the experimental results that the proposed method has better fault diagnosis performance than related transfer methods for solving unknown mechanical faults.     

A New Deep Dual Temporal Domain Adaptation Method for Online Detection of Bearings Early Fault

With the quick development of sensor technology in recent years, online detection of early fault without system halt has received much attention in the field of bearing prognostics and health management. While lacking representative samples of the online data, one can try to adapt the previously-learned detection rule to the online detection task instead of training a new rule merely using online data. As one may come across a change of the data distribution between offline and online working conditions, it is challenging to utilize the data from different working conditions to improve detection accuracy and robustness. To solve this problem, a new online detection method of bearing early fault is proposed in this paper based on deep transfer learning. The proposed method contains an offline stage and an online stage. In the offline stage, a new state assessment method is proposed to determine the period of the normal state and the degradation state for whole-life degradation sequences. Moreover, a new deep dual temporal domain adaptation (DTDA) model is proposed. By adopting a dual adaptation strategy on the time convolutional network and domain adversarial neural network, the DTDA model can effectively extract domain-invariant temporal feature representation. In the online stage, each sequentially-arrived data batch is directly fed into the trained DTDA model to recognize whether an early fault occurs. Furthermore, a health indicator of target bearing is also built based on the DTDA features to intuitively evaluate the detection results. Experiments are conducted on the IEEE Prognostics and Health Management (PHM) Challenge 2012 bearing dataset. The results show that, compared with nine state-of-the-art fault detection and diagnosis methods, the proposed method can get an earlier detection location and lower false alarm rate.