Satellite video object tracking (SVOT) delivers comprehensive spatiotemporal insights for Earth surface observation, yet existing SVOT methods confront several critical challenges including data scarcity, modality restrictions, paradigm gaps, and underutilization of multidimensional features, sealing the performance ceiling. This study proposes STAR, a unified spatiotemporal fusion framework for satellite video object tracking, mitigating these issues. To optimize satellite video scenes, STAR first introduces a scene enhancement module for generating enhanced multi-modal representations. Then, the extraction-correlation-adaptation module is designed, incorporating a multi-modal hierarchical Transformer architecture with local and unified relation modeling, which jointly achieves feature extraction, relation learning, and domain adaptation. Additionally, the temporal decoding structure is introduced to integrate deep temporal features via attention propagation. Finally, the inertial navigation module models physical temporal features, including an awareness selector to assess the tracking confidence-uncertainty and an inertial navigation scheme to manage anomalous interferences and continuous trajectory. Inspired by the prompt learning pattern, STAR introduces a minimal number of tunable parameters yet achieves competitive performance across various SVOT benchmarks. Implementation details and evaluation results will be available at: https://github.com/YZCU/STAR.

Remaining useful life (RUL) prediction is vital for the safety of engineering assets. In the real scenario, due to the lack of failure data and variable working conditions, the accuracy of predictive RUL is significantly compromised as models struggle to generalize across diverse operating environments. Existing solutions manage to shift the degradation information from the ideal laboratory environment to the complex real-world environment. However, they fail to consider the heterogeneity of operating machines under different working conditions. This ignorance of inherent properties will eventually hamper the accuracy of RUL prediction. Consequently, a novel Bayesian adversarial Fast Linear Attention with a Single Head (FLASH) Transformer with feature disentanglement model (BAFTFD) was proposed in this article to tackle with the problem. The proposed BAFTFD model can disentangle the private feature representations from the raw data, preserving the shared feature representation for the prediction. The adversarial training method is also exploited to facilitate the transfer of degradation knowledge. Besides, the feature extractor is equipped with the effective FLASH Transformer model to retain the most informative degradation features for model training, improving the efficiency of feature extraction. Moreover, considering the impact of insufficient training data, inherent data noise on the trustworthiness of the predictive results, the Bayesian DL method is adopted to quantify the prediction uncertainties, ensuring the reliability of maintenance decisions. Two commercial turbofan datasets are leveraged to validate the designed model.

The subdomain adaptation (SA) based intelligent cross-domain fault diagnosis methods aim to reduce the conditional distribution shift caused by variable working conditions. However, existing SA methods may be limited by the quality of pseudolabels, since misclassified pseudolabels will lead to alignment between irrelevant subdomains, resulting in erroneous category-invariant knowledge being accumulated. To tackle this, we present a dynamic subdomain pseudolabel correction and adaptation (DSPC-A) framework. Specifically, we propose an end-to-end pseudolabel correction algorithm, which integrates an auxiliary network to learn clean and general target label distribution from noisy pseudolabels. So that, the auxiliary network can guide the SA model to perform precise subdomain alignment using learned label distribution. Moreover, to allow the synergy training of the additional auxiliary network and SA model, we introduce an iterative learning strategy to dynamically perform pseudolabel correction and subdomain alignment. The iterative training makes two models complement each other, thus achieving better SA ability and diagnosis performance. The DSPC-A framework has been thoroughly verified under three fault diagnostic scenarios: cross load, cross fault severity, and cross mechanical equipment. Case study results demonstrate the superiority of the DSPC-A, which improves the SA performance by solely implementing simple pseudolabel correction methods without other complex techniques.

Fault diagnosis under distribution shifts induced by previously unseen operating conditions is of significant practical value. The main challenge lies in the lack of data from unseen conditions, which prevents diagnostic models from capturing the corresponding distribution patterns, resulting in degraded prediction accuracy. To address this issue, we propose a fault diagnosis framework aimed at enhancing generalization against distribution shifts arising from unseen operating conditions, with its effectiveness validated specifically on gearbox diagnostics. Our approach first employs a modified 1-D stable diffusion model to generate samples under unseen operating conditions. Concurrently, adversarial samples are supplied from monitoring data under known operating conditions using the fast gradient sign method to further enhance model robustness. Then, the monitoring samples, the synthetic samples, and the adversarial samples are jointly used to train an uncertainty-aware deep learning (UDL) model until convergence. Finally, both the classification accuracy and prediction uncertainty of the UDL model are assessed. To validate the effectiveness of the proposed approach, two planetary gearbox datasets were employed for testing. Experimental results demonstrate that the proposed method is capable of accurately performing fault diagnosis under unseen operating conditions, thereby verifying its robustness and generalization capability.

The growing prevalence of the photovoltaic (PV) systems has intensified the focus on fault prediction and health management within both the academic and industrial realms. Electroluminescence (EL) imaging technology, recognized as an advanced detection method, has substantiated its efficiency and practicality in identifying diverse defects. In this study, we introduce a novel framework for anomaly detection in the PV panel systems, leveraging multiscale linear attention and scale distribution alignment learning (MLA-SDAL). Initially, we employ a feature extraction framework based on the multihead linear attention to facilitate the deep-level feature modeling. This network excels in the high-dimensional feature extraction while optimizing the model complexity, achieving a lightweight design tailored for efficient deployment. Subsequently, an unsupervised anomaly detection framework is devised based on scale learning. This framework employs feature dimension transformation and generates efficient supervised signals for distribution alignment learning. This surrogate task enables the framework to adeptly capture and characterize the feature distribution of healthy samples. By gauging the consistency between the input data and the learned model, we precisely quantify the anomaly level of each instance, effectively executing anomaly detection. This approach not only bolsters the accuracy of anomaly detection but also enhances the model’s adaptability to intricate data distributions. Through experimentation on a genuine EL data set, our proposed framework demonstrates pronounced advantages. Comparative to the alternative machine learning or deep learning-based methods, its performance is notable. This accomplishment is poised to furnish robust support for practical applications in the PV panel anomaly detection within the industry.

The unknow fault diagnosis technology in industrial systems implies significant engineering application value and opportunities. The difficulty stems from the fact that the unknown fault samples frequently originate from the diagnostic model’s unknow distribution, leading to an out-of-distribution (OOD) problem. An incorrect diagnosis in the diagnostic model might readily arise from this. To deal with this problem, this paper proposes a novel trustworthy fault diagnosis with out-of-distribution detection which can be applied on industrial systems and equipment. First, deep base learners (DBLs) with different activation functions are designed to construct the deep ensemble model. After that, use in-distribution (ID) inputs to train the initial deep ensemble model. Then, with the proposed max consistency and min similarity guided criterion, the DBLs of the initial ensemble model are chosen to reconstruct the ensemble model. Finally, the diagnostic results’ uncertainty of the reconstruct ensemble model is estimated to accurately determine the type of the sample to be diagnosed. To verify the effectiveness of the proposed method, two gearbox datasets were used to test the proposed method and the max consistency and min similarity guided criterion. The experimental results demonstrate that the proposed approach can accurately identify unknown fault samples in the gearbox.

Multimodal change detection (MCD) is a crucial technology for applications in natural resource monitoring, disaster assessment, and urban planning. To address the reliance on labeled data and enhance the robustness of structural features in the existing methods, we propose a structure difference compensation graph autoencoder (SDC-GAE) for unsupervised MCD. It is recognized that the registered multimodal images exhibit consistency in structural features in unchanged areas, while the structural features in changed areas are distinct. SDC-GAE utilizes a graph convolutional network (GCN) to extract deep structural features from multimodal images. It uses the structural features of one time-phase image to reconstruct its spectral features in the spectral feature space of the target image. Through structural difference compensation, SDC-GAE learns the structural disparities between different images, with the compensation value directly reflecting the intensity of the changes. The SDC-GAE loss function consists of three components: image reconstruction loss, which evaluates the spectral feature discrepancy between the reconstructed and target images, guiding the model to reduce these differences via structural difference compensation; sparse constraint loss, which accounts for the fact that changes are typically confined to a few areas, ensuring the sparsity of the detected changes; and structural consistency loss, which aligns the structural features of the reconstructed image closely with those of the target image. The efficacy of our method is validated through experiments on eight multimodal datasets, where it is compared with the state-of-the-art methods.

Heterogeneous image change detection, in contrast to homogeneous image change detection, has been a research hotspot due to the information complementary of different imaging mechanisms. However, the imaging difference leads to challenges on change detection by image comparison. To address the incomparability among heterogeneous images and improve the efficiency of heterogeneous image change detection, this paper proposes a novel heterogeneous image change detection method based two-stage joint feature learning. Assuming that the change is few and the image differences in unchanged areas between heterogeneous images are related to the imaging and environmental differences, it maps heterogeneous images into a similar feature space for comparison. Firstly, the bi-temporal similar feature maps with high similarity are extracted after joint feature learning of heterogeneous image. And the similar feature maps are used for joint feature learning optimized by a similarity measure in order to map them to an approximate feature space for comparison. Then the change map is obtained by segmenting the difference between the optimal feature maps. The experiments prove its superiority over existing methods on two heterogeneous image datasets (optical and synthetic aperture radar (SAR) images).

Intelligent fault detection methods based on deep learning have been developed rapidly in recent years. However, most of these methods are based on supervised learning which requires a fully labeled training set. It is difficult to obtain massive labeled samples in real applications incredibly accurately labeled fault samples from an operating system. The lack of labels and label noise becomes a great challenge for fault detection. To tackle this problem, in this article, we propose a positive-unlabeled learning based hybrid network (PUHN). It only needs part of the normal operating samples to be labeled. All other samples (including the rest of the normal samples and all fault samples) are unlabeled, which greatly reduces the labeling cost. PUHN consists of three modules: a nonnegative risk positive-unlabeled (PU) network for training the classifier, a feature extraction module, and a clustering layer for improving data separability and estimating the class priors of PU learning. The three are optimized as a whole and the corresponding optimization strategy is designed. The monitoring data of 24 wind turbines are used to verify the effectiveness and robustness of the proposed method. The experimental results indicate that the proposed method is superior to the benchmark methods, and the performance is significantly better than the supervised learning method when there exists label noise.

A method to reduce the supply voltage sensitivity of digitally-controlled ring oscillators (DCROs) using digital current-regulated tuning is presented. By regulating the supply current of ring oscillator instead of its supply voltage, the proposed technique overcomes the limitations of conventional voltage regulator, achieves high supply-noise rejection performance and digital tuning of current-regulated DCRO. The proposed DCRO system implemented in a 0.13-μm CMOS process operates from 1.8 to 3.7 GHz. At 2.7 GHz, the current-regulated DCRO achieves static and dynamic supply-noise immunity of 0.0006%-fOUT/1%-VDDand 0.0014%-fOUT/1%-VDDrespectively, while employing a 150-pF decoupling capacitor, and consuming 1.7 mW from a 1.2 V supply.

A novel frequency search algorithm is proposed in this paper to achieve fast locking in all digital PLL (ADPLL) with no phase tracking being required. According to phase and frequency error, the normalized tuning word (NTW) is calculated so that the output frequency reaches the desired frequency immediately. As the non-idealities, such as DCO gain estimation error and TDC finite resolution, greatly affect the accuracy of the calculation, the output frequency is continuously measured and frequency error is averaged to minimize those impacts. With 0.13um CMOS process, the proposed ADPLL operates at 2.7 GHz and achieves 0.35 us locking time while consuming 7.47mW.

A source coding problem is considered which generalizes the Slepian-Wolf-Cover theorem on noiseless coding of correlated sources so as to include the case of arbitrary cross observations at the encoders. The achievable rate region is established by using Cover's result. Also a co-polymatroidal property of the relevant polytope is pointed out.