Aug 2026· IEEE Sensors Journal· Vol 26, pp. 24144-24159· 0 citations· 31 references
Abstract
Long-term health monitoring of unattended sensing nodes is essential for remote Earth observation networks (EONs); yet, it remains challenging because anomaly-induced response drifts often resemble genuine geophysical variations in both spectral and morphological characteristics. This ambiguity makes sensor degradation difficult to distinguish from valid observations, particularly when measurements are affected by regional spatiotemporal coupling and labeled fault data are unavailable. To address these issues, we propose a physics-informed and data-driven anomaly detection framework for EON sensing nodes. Multidomain complementary features describing amplitude, spectral, and phase behaviors are constructed to improve the separability between natural geophysical variability and sensor-induced distortions. Building on these features, a memory-enhanced Transformer-graph convolutional network (ME-TGCN) is developed to model spatiotemporal dependencies and disentangle node-specific abnormal responses from shared regional variations, while an external memory mechanism preserves long-term healthy operating patterns. Residual modeling errors are further compensated to improve normal-response estimation. Anomalies are then identified from the discrepancy between predicted and observed sensor responses through Mahalanobis-distance-based residual analysis with adaptive thresholding, enabling detection without labeled fault samples. Experiments on real-world EON datasets show that the proposed method outperforms representative baseline methods in both normal-state prediction and anomaly detection and can reliably track progressive sensor degradation and localized anomalies. Cross-regional transfer results further demonstrate its robustness, generalization capability, and practical value for large-scale unattended sensor network monitoring.
Structural health monitoring (SHM) of aging bridges requires reliable methods to capture deformation behavior at multiple scales. Persistent Scatterer Interferometric Synthetic Aperture Radar (PS-InSAR) provides millimeter-level displacement measurements, but interpretation of these datasets remains challenging for slender structures.
This study presents an anomaly detection framework for PS-InSAR displacement data combining temporal feature analysis and spatial structuring. Features such as velocity and thermal sensitivity are analyzed using an unsupervised Isolation Forest model, with SHapley Additive exPlanations (SHAP) used for interpretability. Persistent scatterers are projected onto the bridge axis and aggregated into span-scale zones, and a normalized relative anomaly density metric is introduced to enable cross-satellite comparison.
The framework is applied to descending-pass Sentinel-1 and RADARSAT Constellation Mission datasets over the Victoria Bridge in Montreal. Results show consistent identification of key anomalous segments across datasets despite differences in spatial resolution.
The proposed approach provides a structured and interpretable framework for PS-InSAR-based bridge monitoring.
Ehsan Sadeghian, D. Cusson, E. Dragomirescu et al.· e-Journal of Nondestructive...· 0 citations
Modal frequencies identified from bridge vibration measurements are indirect structural measurands whose long-term interpretation is complicated by environmental and operational variability and asynchronous sensor outages. This study develops a missing-aware measurement-correction framework that maintains normal modal-frequency references from incomplete multi-source monitoring data and quantifies their uncertainty for anomaly screening. Physically interpretable temperature, traffic, wind and cyclic-time features are combined with decay-filled values, observation masks and elapsed-time descriptors in a residual temporal convolutional network (TCN). Adaptive conformal prediction constructs mode-specific intervals from normal residuals, with guarded updating to prevent suspected state changes from contaminating calibration. Persistent coordinated upper-bound exceedance of at least two modes for three consecutive samples then triggers an alarm. The framework is evaluated using 30 min records collected from Mingzhou Bridge between January 2018 and May 2020, including a documented deck-pavement replacement. Missing-aware inclusion retained 34,501 labelled endpoints, compared with 17,369 complete-window endpoints, while the normal-period modal references achieved R
2
values of 0.864, 0.794 and 0.746 and empirical coverage near the nominal 95%. During the intervention period, adaptive calibration reduced the false-alarm rate from 2.79% to 1.31% relative to static conformal prediction, and the persistent rule achieved 99.04% recall and an F
1
score of 99.24%. Controlled asynchronous-missingness tests confirmed uninterrupted reference availability with graceful accuracy degradation. Site-specific validation on an independent cable-stayed bridge further supported the applicability of the prediction and uncertainty-calibration workflow. These results demonstrate uncertainty-calibrated modal-frequency interpretation under incomplete long-term monitoring records.
Miao Xu, Cheng Pan, Guang Qu et al.· Measurement science and tech...· 0 citations
Long-term environmental monitoring in wireless sensor networks (WSNs) often uses sparse sampling to extend network lifetime, but sparse sensing can miss short-lived, localized, and potentially diffusive anomalies. This paper proposes a sentinel-assisted adaptive sampling framework as a cooperative sensing-control pipeline for WSN anomaly monitoring. During normal periods, nodes perform sparse sensing driven by Kalman filter (KF) predictive uncertainty. During anomalous periods, continuously sampled sentinel nodes perform hybrid GLR-based detection with node-relative thresholds, and local detections trigger one-hop neighborhood wake-up with recovery-aware alert control. Experiments on the Intel Berkeley Research Lab temperature dataset with abrupt random spatiotemporal anomalies show that the proposed method raises the anomaly-window sampling ratio (AWSR) from 0.439 to 0.933 in the main experiment. It also improves AWSR over Adaptive Data Acquisition with Energy Efficiency and Critical-Sensing Guarantee (AAS) and Adapted e-Sampling while reducing total cost by 15.4\% and 2.1\%, respectively. These results show that integrating KF-based sparse sampling, sentinel GLR detection, and local alert propagation improves anomaly-window visibility while maintaining a lower sampling-cost trade-off.
Structural Health Monitoring (SHM) increasingly relies on data-driven methods applied to dense vibration measurements, however, reliable damage detection from acceleration time series remains challenging due to environmental variability, limited labeled damage data, and severe class imbalance.
This work investigates self-supervised learning for anomaly detection in bridge acceleration signals. First, we adopt a contrastive framework that captures temporal and contextual dependencies to pretrain an encoder exclusively on fixed-length windows of data collected under healthy conditions. To account for real-world variability, physics-informed data augmentations are introduced to simulate measurement disturbances such as sensor noise and signal variations. Following pretraining, anomalies are identified by measuring deviations of streamed windows from the learned representation of healthy structural behavior, enabling damage detection without explicit labels or predefined damage categories. Experiments on the RT345 multi-scenario bridge benchmark show that the learned representations achieve superior separation between healthy and damaged windows compared to classical baselines and reconstruction-based deep autoencoders.
Finally, we evaluate an online post-processing strategy that aggregates consecutive anomaly scores to emulate streaming deployment. While this aggregation improves detection sensitivity (achieving a True Positive Rate above 96%), it can increase false alarms when using a fixed operating point. These findings indicate that the proposed contrastive-learning-based approach enables effective damage detection from vibration signals in an online setting.
Mohamed Abdellilah Fidma, J. Bercher, Franziska Schmidt· e-Journal of Nondestructive...· 0 citations
Extreme meteorological events—such as winter cold waves, ice accretion, and typhoons—are increasingly becoming primary triggers that threaten the safe and stable operation of power systems. Their disaster-causing processes exhibit strong spatial correlations and multi-stage temporal evolution characteristics, posing severe challenges to traditional static risk assessment methods. Although existing spatiotemporal graph neural network approaches can characterize grid topological dependencies, they generally suffer from limitations including the absence of physical mechanism constraints, insufficient utilization of semantic information from disaster warning texts, and the inability of single-scale graph structures to capture the inherent hierarchical nature of “bus-level fine-grained topology versus meteorological-zone coarse-grained granularity.” To address these issues, this paper proposes an LLM-Assisted Physics-Guided Spatiotemporal Graph Learning model (LPG-STGNet). The proposed model incorporates a large language model (LLM) to perform structured semantic encoding of meteorological warning texts, constructs dynamic graph failure priors based on wind load guidelines and physical equations governing conductor ice accretion growth, and designs a hierarchical spatiotemporal graph encoder that integrates bus-level fine-grained topology with meteorological-zone coarse-grained structure. Furthermore, a semantic–physical dual-gating fusion mechanism is proposed to achieve adaptive weighting among multi-source information, thereby synergistically leveraging data-driven representations, physical priors, and semantic priors within a unified framework. Experiments are conducted on a disaster-evolution dataset constructed through DC-OPF cascade simulation on the ACTIVSg2000 synthetic power grid—built from real geographic and electrical parameters of the Electric Reliability Council of Texas (ERCOT) region and comprising 2,000 bus nodes, 1,250 substations, 3,206 branches, and 8 real meteorological zones—covering 600 synthetic winter cold-wave scenarios (43,200 hourly snapshots). Evaluated against nine mainstream spatiotemporal graph baselines under a unified protocol with three random seeds, LPG-STGNet achieves an F1-score of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$0.798\pm 0.004$$\end{document} and a load-loss RMSE of \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$10.02\pm 0.15$$\end{document} MW on the branch-level trip-classification and node-level load-loss regression tasks, respectively, representing improvements of 6.2 percentage points in F1-score and 21.3% in RMSE over the strongest single-modality baseline. Ablation studies further confirm the effectiveness and complementarity of the physics-guided module and the LLM semantic module. This work provides a novel paradigm for power systems to cope with extreme meteorological disasters, featuring both physical interpretability and semantic understanding capabilities.
Shuanglong Jin, Shenbing Hua, Xiaolin Liu et al.· Discover Artificial Intellig...· 0 citations
Machine learning offers substantial potential for improving anomaly detection in satellite telemetry, a task central to spacecraft health monitoring. As modern satellites generate increasingly large volumes of multivariate telemetry, automated detection systems must evolve to reduce the monitoring burden on spacecraft operations engineers (SOEs) and mitigate operational risks. Although numerous time series anomaly detection (TSAD) methods have been proposed, reliably evaluating their performance under realistic telemetry conditions remains a persistent challenge. Recent transformer-based models have demonstrated strong capability in capturing long-range dependencies and multichannel interactions in telemetry and remote sensing data, thereby gaining increasing adoption in TSAD applications. However, these models exhibit characteristic behaviors—such as smooth attention-driven score transitions near event boundaries, sensitivity to weak precursor patterns leading to slight onset misalignment, and multi-head-induced isolated false alarms—that are not adequately handled by existing evaluation metrics. From an operational perspective, an effective metric should reward timely detection, tolerate the inherent ambiguity of expert-annotated anomaly boundaries, penalize dispersed false alarms that substantially increase SOE workload, and discourage the complete omission of anomalous events, since missing an entire spacecraft anomaly may lead to severe operational consequences even if the missed segment is short. To address these limitations, we propose fuzzy-boundary timeliness and dispersion-weighted F-score (FB-TDF1), a new evaluation metric that jointly accounts for i) detection timeliness, ii) boundary uncertainty in expert annotations, iii) the dispersion characteristics of false positives, and iv) event-level missed-anomaly risk through an event-aware recall correction. FB-TDF1 is specifically designed to reflect the behavioral patterns of modern transformer-based TSAD models and align with the practical evaluation needs of real satellite telemetry monitoring systems.
Kaixiang Yang, Jia-Rong Liu, Jian He et al.· IEEE Journal of Selected Top...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
