6 October 2022 in IEEE Transactions on Instrumentation and Measurement
In industry, accurate remaining useful life (RUL) prediction is critical in improving system reliability and reducing downtime and accident risk. Numerous deep-learning approaches have been proposed and achieved impressive performance in RUL prediction. Nevertheless, most of them are based on an unrealistic assumption, that is, the training (source) and testing (target) data follow similar distributions. In real-world applications, the source and target domains usually have different data distributions, which degrades the model performance on the unlabeled target domain. Existing adversarial domain adaptive RUL prediction methods fail to consider the label information, which potentially aligns samples with very different semantic information and ultimately leads to negative transfer. To address the above issue, this article proposes a weighted adversarial loss (WAL) for cross-domain RUL prediction. To be specific, WAL utilizes the ground-truth labels of the source domain and the pseudo-labels of the target domain to calculate weight and then obtain the WAL. This proposed loss forces the adversarial model to align samples with similar RULs from the source and target domains. Therefore, WAL can enhance positive transfer while alleviating negative transfer. Extensive experiments demonstrate that the proposed loss can be effectively plugged into existing adversarial domain adaptation methods and yield state-of-the-art results.
4 September 2023 in IEEE Transactions on Instrumentation and Measurement
Unsupervised domain adaptation (UDA) strives to transfer the learned knowledge to differently distributed datasets by utilizing both source and target data. Recently, an increasing number of UDA methods have been proposed for domain adaptive remaining useful lifetime (RUL) prediction. However, many industries value their privacy protection a lot. The confidentiality of degradation data in certain fields, such as aircraft engines or bearings, makes the source data inaccessible. To cope with this challenge, our work proposes a source-free domain adaption method to implement cross-domain RUL prediction. Especially, an adversarial architecture with one feature encoder and two RUL predictors is proposed. We first maximize the prediction discrepancy between the predictors to detect target samples that are far from the support of the source. Then the feature encoder is trained to minimize the discrepancy, which can generate features near the support. Besides, a weight regularization is utilized to replace the supervised training on the source domain. We evaluate our proposed approach on the commonly used C-MAPSS and FEMTO-ST datasets. Extensive experiment results demonstrate that our approach can significantly improve the prediction reliability on the target domain.
23 September 2024 in IEEE Transactions on Industrial Informatics
Cross-domain bearing fault diagnosis algorithms have garnered considerable attention in recent years due to their robust ability to address domain bias. However, prevailing methods often grapple with two key challenges: the absence of privacy preservation (necessitating access to source domain data) and the inability to facilitate real-time predictions (requiring iterative training on complete target domain data). In response to these issues, this article introduces an algorithm designed to adapt a pretrained model to the target domain in an online fashion. Notably, data augmentation is employed for pretraining the source domain model, enhancing the generalization capabilities. Subsequently, self-supervised learning is integrated through weight average updating. Furthermore, a memory bank-based approach is introduced to augment the compactness of features within the same class. Evaluation on several public datasets demonstrates that our model not only effectively enhances the diagnostic accuracy of the source model, but also achieves state-of-the-art results compared to other test-time adaptation methods.
29 April 2026 in IEEE Transactions on Image Processing
With the prevalence of pre-trained vision-language models like CLIP, leveraging the generic knowledge embedded in CLIP for domain adaptation has proved to be a promising direction. However, most existing CLIP-based methods are limited to closed-set settings. This is primarily because CLIP needs the semantic labels of unknown classes for inference, thus making it not applicable to Open-Set Domain Adaptation (OSDA). To utilize the complementary roles of CLIP and the source model, our paper proposes a novel Semantic-guided Target Adaptation (SemTA) framework for OSDA in a training-free manner. Specifically, we introduce an unknown semantic discovery module. It uses the cluster centroids of the target data to obtain the semantic labels of unknown classes from the worldwide corpus. Then, the semantic-based inference can be performed with CLIP. Additionally, the dual sample attention mechanism is implemented to output sample-based inference. Representative features from both the source model and CLIP serve as the key to improve task specificity. Compared to previous OSDA methods which reject unknown data by confidence threshold, the proposed approach is more practical and offers better interpretability. Comprehensive evaluations on four benchmarks reveal our method sets a new state-of-the-art even without training. Our code will be publicly available soon.