26 March 2024 in IEEE Transactions on Systems, Man, and Cybernetics: Systems
Despite the significant progress in unsupervised domain adaptation (UDA), the performance of UDA methods is still far inferior to that of the fully supervised ones. In practical scenarios, it is usually feasible to acquire labels on a small portion of the target data through active learning (AL), which aims to train an effective model with as few queried instances as possible. However, due to the domain shift, the instances selected by existing AL algorithms can be uninformative, redundant, or outlying. To address this issue, we propose a novel approach, namely, clustering environment-aware learning (CEAL), for active domain adaptation (ADA). CEAL selects potentially the most valuable instances under domain shift by exploring the informativeness and representativeness of target samples in a clustering environment-aware manner. Specifically, for the informativeness, we not only leverage the knowledge of individual points but also their nearby neighbors, by measuring the proposed clustering environment aware informativeness score (CEAIS), thus ensuring that the selected samples are highly informative. For the representativeness, we design two schemes called point distance release (PDR) and informativeness score difference exclusion (ISDE) to guarantee the diversity and validity of the selected samples. Furthermore, we fully utilize the large amount of unlabeled data from target domain via pseudo labeling and adopt information maximization to improve the reliability of the target pseudo labels, thereby further improving the performance of the model. The effectiveness of our method is empirically verified on various benchmark datasets against recent state-of-the-art algorithms.
13 November 2023 in IEEE Transactions on Industrial Informatics
Recently, domain adaptation (DA)-based fault diagnosis approaches have been actively studied in chemical processes to build a reliable fault diagnosis model for a new operating mode (i.e., target domain) by making use of labeled data from a historical mode (i.e., source domain). However, this raises privacy concerns, such as data leakage, since industrial data contains sensitive production information. Moreover, preprocessed source and target data used to train an effective target model will result in additional computational costs. Therefore, it is crucial to develop a novel privacy preserving DA-based fault diagnosis approach that can improve the diagnosis performance for a new mode and protect the privacy of a historical mode simultaneously. To this end, fault diagnosis is formulated as the source-free DA problem and proposes a temporal attention source-free adaptation (TASFA) algorithm, which only utilizes the pretrained source model and unlabeled target data to learn a diagnosis model. Specifically, for the time-series process, an attention mechanism is designed to capture and leverage the temporal correlations between source and target domains by extracting the most transferable information from the target time series. Empirical results on both the Tennessee Eastman process and the continuous stirred tank reactor demonstrate the effectiveness and efficiency of TASFA.
15 December 2022 in IEEE Transactions on Instrumentation and Measurement
While deep neural network-based fault diagnosis methods can monitor the faults that occur on the operating modes, they cannot perform well on the modes that are never experienced before. This limitation makes it challenging to ensure the production safety of chemical processes. In this paper, this issue is formulated as domain generalization (DG), which aims to learn a universal fault diagnosis model from historical operating modes that can generalize well to unseen modes. Many existing DG approaches focus on learning a domain-invariant representation by aligning marginal distributions between domains, which ignore the conditional relations and label information. Recently, some researches start to reduce the discrepancy of the class conditional distributions across domains, while the theoretical justifications of that are still missing. To address this issue, the theoretical analysis of DG is developed to investigate how to minimize the unseen domains risk, which is a theoretical guarantee that DG methods can generalize well over unseen domains. This theory reveals that the unseen domain error can be bounded by the shift of the label and class conditional distributions across source domains. Then, this result motivates a novel labeling and class progressive adversarial learning (LCPAL) algorithm for fault diagnosis, which simultaneously controls the errors weighted based on label information and aligns the class conditional distributions between different historical operating modes, as well as reducing the adverse effect of the domain-specific feature. Empirical results on both the numerical example and the Tennessee Eastman process demonstrate the effectiveness of the LCPAL approach.
18 February 2022 in IEEE Transactions on Instrumentation and Measurement
One challenge faced by data-driven fault diagnosis methods is that they may perform well over the operating modes where the historical data are collected, but fail to generalize to unseen modes that have never appeared before. That is one of the root causes that have prevented many advanced fault diagnosis methods from being widely accepted by the chemical industry. Consequently, it is significant to develop a novel fault diagnosis method, which can build a model to determine the type of faults occurred on unseen modes. On the other hand, one chemical process generally experiences multiple operating modes, from which common knowledge of these modes can be extracted and be applied to an unseen mode. To this end, a novel weighted conditional discriminant analysis (WCDA) algorithm is proposed by adopting the context of domain generalization (DG) approaches to leverage and distill the knowledge from historical modes for unseen modes of fault diagnosis. Specifically, a novel variable weighting scheme is developed based on the Kullback–Leibler divergence between features of different modes. Then, a fault diagnosis model is constructed by learning a classifier and invariant feature representation simultaneously. Moreover, WCDA is extended to the context of domain adaptation (DA), where the performance of the fault diagnosis model is further improved by leveraging the unlabeled data collected from a new mode. Empirical results on a numerical example, the Tennessee Eastman process, and continuous stirred tank chemical reactor demonstrate the effectiveness of our method.
18 February 2025 in IEEE Transactions on Instrumentation and Measurement
Recently, domain generalization (DG) methods have been actively researched for complex industrial fault diagnosis, which aims to learn generalized representations from historical working conditions to build a diagnosis model that can perform well on unseen working conditions. However, these methods ignore the interactions between monitoring variables, which may fail to learn feature representation with topological structure in non-Eudidean space. In addition, these methods assume the same label distribution across historical and unseen working conditions, which is generally challenging in practice, as the probability of faults varies across different working conditions. This label shift problem can negatively impact the generalization performance. To address these issues, a novel dual-contrastive multi-view graph attention network (DMGAT) is proposed in this article. Specifically, a multi-view graph attention network is designed to explore the intrinsic topological structure of the data, which learns an optimal graph structure that best serves DG by integrating both graph learning and graph convolution in a unified network architecture. In addition, a novel dual-weighted contrastive learning strategy is developed. Intra-domain contrastive learning facilitates the extraction of expressive node features, while inter-domain contrastive learning simultaneously considers the alignment and separation of semantic probability distributions to extract shared feature representations for multiple source domains under both domain and label shift. Furthermore, a label sampling probability is used to weight the inter-domain contrastive loss and the source domain classification loss, to encourage the model to learn from minor classes in fault diagnosis. Experiments on two cases demonstrate the superiority of the proposed method.