Search Results (11)

Under varying operating conditions, motor bearings undergo continuous changes, necessitating the development of deep learning models capable of robust fault diagnosis. While meta-learning can enhance generalization in low-data scenarios, it is often susceptible to overfitting. Domain adaptation mitigates this by aligning feature distributions across domains; however, most existing methods primarily focus on global alignment, overlooking intra-class subdomain variations. To address these limitations, we propose a novel Dynamic Balance Domain-Adaptation based Few-shot Diagnosis framework (DBDA-FD), which incorporates both global and subdomain alignment mechanisms along with a dynamic balancing factor that adaptively adjusts their relative contributions during training. Furthermore, the proposed framework implicitly leverages the concept of symmetry in feature distributions. By simultaneously aligning global and subdomain-level representations, DBDA-FD enforces a symmetric structure between source and target domains, which enhances generalization and stability under varying operational conditions. Extensive experiments on the CWRU and PU datasets demonstrate the effectiveness of DBDA-FD, achieving 97.6% and 97.3% accuracy on five-way five-shot and three-way five-shot tasks, respectively. Compared to state-of-the-art baselines such as PMML and ADMTL, our method achieves up to 1.4% improvement in accuracy while also exhibiting enhanced robustness against domain shifts and class imbalance. Full article

To overcome the challenges of limited data, domain distribution differences, and the need for retraining in unsupervised learning methods for cross-scenario anomaly detection in dams, this study introduces a novel approach; the Temporal Displacement Subdomain Adaptation Network (TDSAN) combines temporal convolutional networks with subdomain adaption. This study presents the first application of subdomain adaptation for cross-scenario anomaly detection in dams, addressing distribution shifts across varying operational conditions. The proposed method comprises three key components: a feature extraction network leveraging temporal convolutional layers to capture long-term displacement patterns, a classifier network with fully connected layers to distinguish between normal and anomalous behaviors, and a domain alignment module that uses Local Maximum Mean Discrepancy (LMMD) to align feature distributions between the source and target domains, thereby enhancing the method’s robustness. The approach was validated using data from gravity and arch dams in a specific canyon region in China. The results show that the proposed method demonstrates high classification accuracy and stability in both same-domain and cross-domain scenarios. Compared to other state-of-the-art methods, the proposed approach demonstrates superior classification accuracy and more reliable risk control. This makes it particularly well-suited for cross-domain applications, which are prevalent in real-world engineering scenarios, thereby significantly enhancing its practical applicability. Full article

Subdomain adaptation plays a significant role in the field of bearing fault diagnosis. It effectively aligns the pertinent distributions across subdomains and addresses the frequent issue of lacking local category information in domain adaptation. Nonetheless, this approach overlooks the quantitative discrepancies in distribution between samples from the source and target domains, leading to the vanishing gradient issue during the training of models. To tackle this challenge, this paper proposes a bearing fault diagnosis method based on Wasserstein metric residual adversarial subdomain adaptation. The Wasserstein metric is introduced as the optimized objective function of the domain discriminator in RASAN-W. The distribution discrepancy between the source domain and target domain samples is quantitatively measured, achieving the alignment of the relevant subdomain distributions between the source domain and the target domain. Ultimately, extensive experiments conducted on two real-world datasets reveal that the diagnostic accuracy of this method is significantly enhanced when compared to various leading bearing fault diagnosis techniques. Full article

In order to obtain more fine-grained information from multiple sub-feature spaces for domain adaptation, this paper proposes a novel multi-representation joint dynamic domain adaptation network (MJDDAN) and applies it to achieve cross-database facial expression recognition. The MJDDAN uses a hybrid structure to extract multi-representation features and maps the original facial expression features into multiple sub-feature spaces, aligning the expression features of the source domain and target domain in multiple sub-feature spaces from different angles to extract features more comprehensively. Moreover, the MJDDAN proposes the Joint Dynamic Maximum Mean Difference (JD-MMD) model to reduce the difference in feature distribution between different subdomains by simultaneously minimizing the maximum mean difference and local maximum mean difference in each substructure. Three databases, including eNTERFACE, FABO, and RAVDESS, are used to design a large number of cross-database transfer learning facial expression recognition experiments. The accuracy of emotion recognition experiments with eNTERFACE, FABO, and RAVDESS as target domains reach 53.64%, 43.66%, and 35.87%, respectively. Compared to the best comparison method chosen in this article, the accuracy rates were improved by 1.79%, 0.85%, and 1.02%, respectively. Full article

Conventional OCT retinal disease classification methods primarily rely on fully supervised learning, which requires a large number of labeled images. However, sometimes the number of labeled images in a private domain is small but there exists a large annotated open dataset in the public domain. In response to this scenario, a new transfer learning method based on sub-domain adaptation (TLSDA), which involves a first sub-domain adaptation and then fine-tuning, was proposed in this study. Firstly, a modified deep sub-domain adaptation network with pseudo-label (DSAN-PL) was proposed to align the feature spaces of a public domain (labeled) and a private domain (unlabeled). The DSAN-PL model was then fine-tuned using a small amount of labeled OCT data from the private domain. We tested our method on three open OCT datasets, using one as the public domain and the other two as the private domains. Remarkably, with only 10% labeled OCT images (~100 images per category), TLSDA achieved classification accuracies of 93.63% and 96.59% on the two private datasets, significantly outperforming conventional transfer learning approaches. With the Gradient-weighted Class Activation Map (Grad-CAM) technique, it was observed that the proposed method could more precisely localize the subtle lesion regions for OCT image classification. TLSDA could be a potential technique for applications where only a small number of images is labeled in a private domain and there exists a public database having a large number of labeled images with domain difference. Full article

In application, training data and test data collected via indoor positioning algorithms usually do not come from the same ideal conditions. Changes in various environmental conditions and signal drift can cause different probability distributions between the data sets. Existing positioning algorithms cannot guarantee stable accuracy when facing these issues, resulting in dramatic reduction and the infeasibility of the positioning accuracy of indoor location algorithms. Considering these restrictions, domain adaptation technology in transfer learning has proven to be a promising solution in past research in terms of solving the inconsistent probability distribution problems. However, most localization algorithms based on transfer learning do not perform well because they only learn a shallow representation feature, which can only slightly reduce the domain discrepancy. Based on the deep network and its strong feature extraction ability, it can learn more transferable features for domain adaptation and achieve better domain adaptation effects. A Deep Joint Mean Distribution Adaptation Network (DJMDAN) is proposed to align the global domain and relevant subdomain distributions of activations in multiple domain-specific layers across domains to achieve domain adaptation. The test results demonstrate that the performance of the proposed method outperforms the comparison algorithm in indoor positioning applications. Full article

Deep learning models have been widely used in data-driven bridge structural damage diagnosis methods in recent years. However, these methods require training and test datasets to satisfy the same distribution, which is difficult to satisfy in practice. Domain adaptation transfer learning is an efficient method to solve this problem. Most of the current domain adaptation methods focus on close-set scenarios with the same classes in the source and target domains. However, in practical applications, new damage caused by long-term degradation often makes the target and source domains dissimilar in the class space. For such challenging open-set scenarios, existing domain adaptation methods will be powerless. To effectively solve the above problems, an adversarial auxiliary weighted subdomain adaptation algorithm is proposed for open-set scenarios. Adversarial learning is introduced to proposed an adversarial auxiliary weighting scheme to reflect the similarity of target samples with source classes. It effectively distinguishes unknown damage from known states. This paper further proposes a multi-channel multi-kernel weighted local maximum mean discrepancy metric (MCMK-WLMMD) to capture the fine-grained transferable information for conditional distribution alignment (sub-domain alignment). Extensive experiments on transfer tasks between three bridges verify the effectiveness of the algorithm in open-set scenarios. Full article

The data distribution of the vibration signal under different speed conditions of the gearbox is different, which leads to reduced accuracy of fault diagnosis. In this regard, this paper proposes a deep transfer fault diagnosis algorithm combining adaptive multi-threshold segmentation and subdomain adaptation. First of all, in the data acquisition stage, a non-contact, easy-to-arrange, and low-cost sound pressure sensor is used to collect equipment signals, which effectively solves the problems of contact installation limitations and increasingly strict layout requirements faced by traditional vibration signal-based methods. The continuous wavelet transform (CWT) is then used to convert the original vibration signal of the device into time–frequency image samples. Further, to highlight the target fault characteristics of the samples, the gray wolf optimization algorithm (GWO) is combined with symmetric cross entropy (SCE) to perform adaptive multi-threshold segmentation on the image samples. A convolutional neural network (CNN) is then used to extract the common features of the source domain samples and the target domain samples. Additionally, the local maximum mean discrepancy (LMMD) is introduced into the parameter space of the deep fully connected layer of the network to align the sub-field edge distribution of deep features so as to reduce the distribution difference of sub-class fault features under different working conditions and improve the diagnostic accuracy of the model. Finally, to verify the effectiveness of the proposed diagnosis method, a fault preset experiment of the gearbox under variable speed conditions is carried out. The results show that compared to other diagnostic methods, the method in this paper has higher diagnostic accuracy and superiority. Full article

The insufficient learning ability of traditional convolutional neural network for key fault features, as well as the characteristic distribution of vibration data of rolling bearing collected under variable working conditions is inconsistent, and decreases the bearing fault diagnosis accuracy. To address the problem, a deep subdomain adaptation split attention network (SPDSAN) is proposed for intelligent fault diagnosis of bearings. Firstly, the time-frequency diagram of a vibration signal is obtained by the continuous wavelet transform to show the time-frequency characteristics. Secondly, a residual split-attention network (ResNeSt) that integrates multi-path and channel attention mechanisms is constructed to extract the key features of rolling bearings to prevent feature loss. Then, a subdomain adaptation layer is added to ResNeSt to align the distribution of related subdomain data by minimizing the local maximum mean difference. Finally, the SPDSAN model is validated using the Case Western Reserve University datasets. The results show that the average diagnostic accuracy of the proposed method is 99.9% when the test set samples are not labeled, which is higher compared to the accuracy of other mainstream intelligent fault diagnosis models. Full article

Domain adaptation-based models for fault classification under variable working conditions have become a research focus in recent years. Previous domain adaptation approaches generally assume identical label spaces in the source and target domains, however, such an assumption may be no longer legitimate in a more realistic situation that requires adaptation from a larger and more diverse source domain to a smaller target domain with less number of fault classes. To address the above deficiencies, we propose a partial transfer fault diagnosis model based on a weighted subdomain adaptation network (WSAN) in this paper. Our method pays more attention to the local data distribution while aligning the global distribution. An auxiliary classifier is introduced to obtain the class-level weights of the source samples, so the network can avoid negative transfer caused by unique fault classes in the source domain. Furthermore, a weighted local maximum mean discrepancy (WLMMD) is proposed to capture the fine-grained transferable information and obtain sample-level weights. Finally, relevant distributions of domain-specific layer activations across different domains are aligned. Experimental results show that our method could assign appropriate weights to each source sample and realize efficient partial transfer fault diagnosis. Full article

A better understanding of the spatiotemporal distribution of water resources is crucial for the sustainable development of hyper-arid regions. Here, we focus on the Arabian Peninsula (AP) and use remotely sensed data to (i) analyze the local climatology of total water storage (TWS), precipitation, and soil moisture; (ii) characterize their temporal variability and spatial distribution; and (iii) infer recent trends and change points within their time series. Remote sensing data for TWS, precipitation, and soil moisture are obtained from the Gravity Recovery and Climate Experiment (GRACE), the Tropical Rainfall Measuring Mission (TRMM), and the Advanced Microwave Scanning Radiometer for Earth Observing System (AMSR-E), respectively. The study relies on trend analysis, the modified Mann–Kendall test, and change point detection statistics. We first derive 10-year (2002–2011) seasonal averages from each of the datasets and intercompare their spatial organization. In the absence of large-scale in situ data, we then compare trends from GRACE TWS retrievals to in situ groundwater observations locally over the subdomain of the United Arab Emirates (UAE). TWS anomalies vary between −6.2 to 3.2 cm/month and −6.8 to −0.3 cm/month during the winter and summer periods, respectively. Trend analysis shows decreasing precipitation trends (−2.3 × 10⁻⁴ mm/day) spatially aligned with decreasing soil moisture trends (−1.5 × 10⁻⁴ g/cm³/month) over the southern part of the AP, whereas the highest decreasing TWS trends (−8.6 × 10⁻² cm/month) are recorded over areas of excessive groundwater extraction in the northern AP. Interestingly, change point detection reveals increasing precipitation trends pre- and post-change point breaks over the entire AP region. Significant spatial dependencies are observed between TRMM and GRACE change points, particularly over Yemen during 2010, revealing the dominant impact of climatic changes on TWS depletion. Full article