Search Results (2,143)

Lubricating oil monitoring provides continuous health information for early fault warning and maintenance decision-making in industrial gas turbines. However, real-world multi-sensor monitoring streams exhibit pronounced nonstationary thermodynamic drifts that often obscure subtle high-frequency residuals containing critical incipient degradation signatures. Prevailing data-driven monitoring models typically struggle to separate these macroscopic trends from stochastic wear-related fluctuations, and their restrictive distributional assumptions are often inadequate for the heteroscedastic and heavy-tailed nature of industrial residuals. To address these challenges, this study proposes ResAD-Net, a framework for early fault warning in nonstationary multi-sensor oil monitoring that combines trend–residual decoupling, trend-conditioned residual modeling, and residual-domain dependency learning. Specifically, a signal trend–residual decoupling strategy is adopted to separate slowly varying operational trends from stochastic residual fluctuations captured by the sensors, thereby exposing residual information that is more sensitive to incipient degradation. On this basis, a trend-conditioned diffusion model is introduced to characterize state-dependent, skewed residual distributions and generate residual sample ensembles for nonstationary monitoring. Meanwhile, a graph-based variational autoencoder is employed to learn latent intersensor dependency structures from the residual domain, providing diagnostic cues for temporal risk evolution analysis and sensor-level inspection. Experiments on a real-world industrial oil-monitoring record show that the proposed framework achieves an average F1-score of 0.985 with no observed false positives in the predefined pre-alarm reference interval of the finite test set. In addition to accurate anomaly detection, ResAD-Net captures early residual distributional shifts before clear macroscopic deviations emerge and provides diagnostic association cues for interpreting oil-monitoring changes around the system-level alarm. Full article

The increasing adoption of Plant Factories with Artificial Lighting (PFAL) has intensified the reliance on Internet of Things (IoT) technologies for real-time monitoring and control of environmental and operational variables. While IoT-based architectures enable precise resource management and productivity optimization, PFAL systems remain highly vulnerable to component failures, sensor malfunctions, communication faults, and energy disruptions, which may compromise crop integrity and system reliability. These risks are particularly critical in low-cost and small-scale PFAL implementations, where maintenance capacity and redundancy are often limited. Existing IoT-based PFAL monitoring systems typically address either hardware or software redundancy in isolation and rarely incorporate a dedicated maintenance-oriented fault detection layer validated under realistic multi-failure scenarios. This study addresses these challenges by proposing a low-cost redundant system architecture for PFAL applications that simultaneously integrates (1) hardware redundancy through multi-sensor configurations; (2) analytical redundancy based on residual generation and threshold-based fault isolation; and (3) a maintenance-oriented fault detection layer capable of identifying abnormal internal device conditions. Experimental validation was conducted using four hardware configurations—Arduino Nano with Ethernet, ESP32, STM32 with Wi-Fi, and STM32 with Ethernet—evaluated across five fault scenarios: dust accumulation, water exposure, high temperature, fire detection, and physical impact. The STM32 with Ethernet configuration consistently achieved the fastest fault detection response times across all tested scenarios. Future work will focus on the integration of machine learning-based predictive maintenance algorithms, multi-node PFAL network deployments, and long-term field validation. Full article

When operating in complex and obstacle-dense environments, micro UAV swarms often face severe cooperative positioning failures due to transient non-line-of-sight (NLOS) interference and cascaded inertial sensor drift. To address this, this work proposes a fault-tolerant positioning framework integrating multi-agent deep reinforcement learning with cooperative extended Kalman filtering (MADRL-CEKF). The system incorporates a link-level dynamic soft isolation mechanism that dynamically adjusts observation covariance to effectively sever paths of cooperative error contagion. An adaptive Markov smoothing constraint is mathematically embedded to mitigate high-frequency control jitter typical of AI-driven policies. Crucially, the framework implements a resource-aware multi-objective reward architecture tailored for micro UAVs. Evaluated through high-fidelity simulations and offline physical datasets, the proposed framework achieves a 96.01% reduction in average tracking error (RMSE) under extreme multi-node cascaded failures, completely preventing system divergence. Furthermore, through autonomous multi-objective trade-offs, the system reduces processing delay by 44% (to 25.1 ms) and computational energy consumption by 41% with only a marginal accuracy compromise of 0.16 m, strictly keeping the execution time within the 50 ms real-time threshold. The MADRL-CEKF framework effectively bridges the gap between sophisticated AI decision-making and strict engineering constraints, providing a highly robust and resource-efficient navigation paradigm for swarm robotics. Full article

This study applied density functional theory (DFT) to investigate gas-sensitive devices based on Pt- and Pd-doped SnS₂ monolayers, exploring their adsorption and sensing performance on four characteristic gases generated under normal operating or fault conditions of transformer oil. The adsorption behaviors and underlying sensing mechanisms of four gases on pristine and modified SnS₂ were systematically elucidated. The results reveal that Pt/Pd incorporation triggers a transition from weak physisorption to robust chemisorption. Compared to intrinsic SnS₂, the decorated monolayers exhibit dramatically augmented adsorption energies and accelerated interfacial charge transfer for all target molecules. Crucially, noble metal modification fundamentally modulates the electronic structure of the SnS₂ lattice, endowing the material with exceptional recognition specificity for distinguishing different gas species. These theoretical insights establish Pt- and Pd-SnS₂ as highly promising candidates for advanced DGA sensors, providing a robust materials design strategy for the condition monitoring of critical electrical infrastructure. Full article

This paper systematically investigates the performance of data-driven algorithms for fault diagnosis in aircraft hydraulic systems. Firstly, the hydraulic system of an aircraft is modeled in AMESim software, and five typical faults are artificially injected. The pressure and flow curves from different position sensors are extracted to construct the fault diagnosis dataset. Then, a multi-level feature extraction method based on deep learning algorithms, including 1DFFCNN, stacked LSTM, and improved CNN-LSTM-Attention, is designed to identify the sensitive features of potential abnormal behaviors. Finally, we study the sensitivity of multi-source heterogeneous response data of the hydraulic system to the degradation of the hydraulic system’s state, and establish the correlation between the evolution of the hydraulic system’s working state and the multi-source heterogeneous response data, achieving the early prognostics of abnormal states of the hydraulic system. Numerical experiments demonstrate that the accuracy rate of the aircraft fault diagnosis based on the data-driven algorithm presented in this paper exceeds 98%. Full article

Distributed seismic sensor networks integrated into the Internet of Things (IoT) infrastructure enable continuous condition monitoring of large-scale engineering structures. During long-term operation, however, measurement channels are subject to sensitivity drift, increased noise, and pulse artifacts that statistically mimic real vibration events. Related deep-learning techniques for noisy and ill-posed inverse problems have demonstrated the value of combining principled physical priors with deep models. Although the application domain differs, the underlying methodological insight—that constrained, physics-aware feature mappings can stabilize learning under noisy and partially observed conditions—directly motivates the use of a parameterized quantum circuit as a nonlinear feature transformer in the present work, where Hilbert space mapping serves as an analogous structural prior for the latent representation. Three principal fault modes are considered in this work, corresponding to the dominant degradation mechanisms observed in long-term seismic instrumentation: sensor drift, increased noise, and sensor failure. Each fault mode produces a distinct signature in the windowed feature space; the proposed model is trained to discriminate between them based on the latent CNN-LSTM-VQC representation. We propose a hybrid quantum-inspired deep-learning model (QC-DL) for the detection and diagnosis of channel-degradation anomalies. The architecture combines a 1D-CNN+LSTM feature extractor with a parameterized variational quantum circuit (VQC) used as a nonlinear feature transformer. All quantum experiments were performed on the QPanda3 CPUQVM simulator. The data were split chronologically prior to windowing to avoid information leakage. On real-world labeled accelerometric data with four operating modes (normal/drift/high-noise/failure), the QC-DL model achieved a macro-averaged F1 score of approximately 0.69 and per-class AUC values in the range 0.88–0.99. The mean early-detection latency was 1.6 s versus 2.1 s for the CNN-LSTM baseline (~24% reduction). An ablation study against a parameter-matched classical MLP showed that the gain is modest and not solely attributable to additional nonlinearity. The reported p-values (p = 0.70, p = 0.29) do not establish statistical significance. The results support the feasibility of hybrid quantum-inspired deep learning for sensor-channel verification, while highlighting the need for evaluation on real NISQ hardware. This paper proposes a hybrid quantum-inspired approach for detecting and diagnosing such anomalies in the time series of distributed seismic networks. The architecture combines a classical temporal feature extraction module based on one-dimensional convolutional layers and a recurrent long short-term memory (LSTM) network, which generates a latent window representation of the signal, with a parameterized variational quantum circuit used as a nonlinear feature processor in a hybrid computational circuit. Experimental validation was performed on real-world labeled data with multiple sensor degradation modes. The evaluation was organized in a scoring framework aligned with autonomous operation through window ranking and threshold alarm generation. In the experiments, the proposed model provided a macro-averaged F1 score of approximately 0.69 and area under the receiver operating characteristic (AUC) curve values in the range of 0.88–0.99 across classes, outperforming baseline deep models. The average early detection latency was 1.6 s versus 2.1 s for the baseline recurrent model (a 24% reduction). An ablative comparison with a control model based on a classical multilayer perceptron of comparable dimension confirmed that the improvement is not limited to the addition of additional nonlinearity. The obtained results indicate the potential of quantum-supported deep learning for improving the reliability of long-term vibration monitoring and verifying the correctness of sensor channels in distributed seismic networks. Full article

Semiconductor manufacturing demands exceptional precision, as even minor process deviations can result in significant yield degradation. The increasing deployment of sensors generates extensive time-series data. However, such data are often affected by temporal misalignments, nonlinear distortions, and inter-wafer variability, complicating direct comparison and automated anomaly detection. To address these challenges, this paper proposes a robust framework that employs a Dynamic Time Warping (DTW)-based two-stage alignment strategy with Sakoe–Chiba constraint followed by a bidirectional polyline distance measure to identify subtle anomalies. This approach effectively handles scarce anomaly labels and high variability in sensor data, enabling reliable process health monitoring. Experimental results on real semiconductor production data demonstrate that the framework enhances detection accuracy, contributing to early fault identification and reduced wafer scrap in manufacturing environments. Full article

Multimodal sensor fusion is increasingly used to improve observability for fault diagnosis and prognostics, enabling Remaining Useful Life estimation in complex mechatronic and robotic systems. Yet, real-world deployments remain vulnerable to sensor faults and data integrity issues—including bias and drift, miscalibration, dropouts, saturation, cross-talk, time desynchronization, and domain shift—which can propagate through fusion pipelines and lead to optimistic validation and poor generalization. These challenges are particularly consequential in safety- and health-adjacent applications such as collaborative robots, wearable/rehabilitation devices, and human-centric mechatronic systems where decisions based on faulty sensing may affect both reliability and user safety. This review synthesizes the state of the art on (i) sensor fault taxonomies and fault models relevant to multimodal fusion, (ii) fault-aware fusion strategies spanning data-, feature-, and decision-level integration, and (iii) how sensor faults and uncertainty impact diagnosis and remaining-life estimators. We will conduct a systematic scoping review of peer-reviewed literature, extracting sensor modalities, fault characterization or injection protocols, fusion architectures, validation settings (simulation, hardware-in-the-loop, bench, and in-field/on-body studies), and reporting completeness. Beyond summarizing methods, we provide practical reporting standards for sensor-fusion-based diagnosis and prognostics, including a minimum disclosure set covering synchronization, fault ground truth, missingness handling, leakage controls, uncertainty calibration, and task-relevant metrics. Reusable checklists and evidence tables are included to support more comparable, reproducible, and deployment-ready research. Full article

The operational health state of motor bearings is critical to the operational safety of harbor portal slewing cranes. However, in harsh industrial environments with strong noise and time-varying rotational speeds, existing bearing fault diagnosis methods still suffer from the problems of incomplete fault feature extraction from single-sensor signals and the excessively large size of multi-source fusion models, which makes them unable to adapt to edge deployment. To address these issues, this paper proposes a Multi-source Feature Fusion Lightweight Network (MTFL-Net) integrated with targeted structured channel pruning. First, vibration and current signals are preprocessed via differentiated time-frequency transformation and converted into 2D time-frequency images, to fully preserve transient impact and spectral fault features. Second, a multi-branch feature extraction architecture embedded with residual connections, multi-scale convolution and channel attention gating is designed, to alleviate feature degradation and adaptively enhance fault-sensitive features. Third, targeted structured channel pruning is performed on the feature extraction branches, to remove redundant channels while retaining the multi-source fusion logic and core feature extraction structure. Experiments on two public bearing datasets show that the original model achieves 99% diagnostic accuracy, and the pruned model still maintains an accuracy of 95%. The results demonstrate that MTFL-Net can significantly reduce model size and computational cost while retaining high diagnostic precision. Full article

Air pollution is primarily caused by human activities such as industrial emissions, road traffic, waste incineration, and fossil fuel power plants. Pollution refers to the presence of harmful substances in the air, such as nitrogen dioxide (NO₂), sulfur dioxide (SO₂), ozone (O₃), carbon monoxide (CO), and other environmental pollutants. Some pollutants pose health risks even at low doses. Given the critical importance of air quality, monitoring air pollution has become an urgent and essential subject. Air quality monitoring relies on accurate data, so changeable environments and sensor issues make using interval diagnostic techniques for addressing uncertainty in systems interesting. In this article, we focus on three key aspects to achieve precise and efficient results: (1) the use of an accurate fault detection method that accounts for data uncertainty while maintaining model symmetry, (2) the implementation of a reliable detection index invariant to symmetric sensor behaviors, and (3) the combination of both to improve fault localization accuracy. This paper presented a fault detection and localization framework designed for uncertain and nonlinear monitoring environments. A novel fault-sensitive detection index was developed and integrated into an elimination-based localization strategy within a reduced-rank interval kernel PCA (RR-IKPCA) model. By exploiting information contained in modified residual subspaces and explicitly accounting for measurement uncertainty, the proposed approach enhances fault sensitivity while preserving robust localization capability, as validated on the AIRLOR air quality monitoring network. Full article

Despite their demonstrated effectiveness in modeling sensor interaction networks for industrial fault diagnosis, graph neural networks (GNNs) still encounter two key limitations: black-box operation that lacks transparency in fault identification and propagation analysis, and unreliable attention mechanisms whose weights fail to faithfully reflect the genuine relevance of sensors or their interactions. To tackle these challenges, we put forward the Stochastic Mask Causal Graph Network, a novel framework that integrates a learnable stochastic masking mechanism guided by the information bottleneck principle. Unlike conventional attention-based or post-hoc approaches, our method automatically suppresses label-irrelevant graph components while preserving causally relevant structures, thereby providing faithful inherent interpretability without biased assumptions and effectively removing spurious correlations to enhance generalization. Comprehensive experiments on realistic complex industrial system datasets demonstrate that the proposed method achieves superior diagnostic accuracy and enhanced interpretability compared with existing advanced approaches. Full article

The Marmara region of Türkiye, situated along the North Anatolian Fault Zone (NAFZ), constitutes one of the most seismically active and densely monitored zones globally. Given the region’s high vulnerability and the catastrophic impacts of historical events—notably the 1999 İzmit and 2023 Kahramanmara¸s sequences—there is a critical need for advanced seismic hazard risk assessment (SHRA) methods that move beyond static models. This review examines the paradigm shift from traditional geophysics to big data seismology, characterized by the “Five Vs”: volume, velocity, variety, veracity, and value. Critically, we distinguish between two fundamentally different problems: Earthquake Early Warning (EEW), which operates on sub-second timescales after rupture initiation, and probabilistic earthquake forecasting, which operates on timescales of years to decades. The study discusses how cloud-native platforms such as Azure Databricks, combined with data pipelines using Apache Kafka (version 3.5.1) and Apache Spark (version 4.1.2), enable the real-time processing of petabyte-scale seismic sensor streams. Key technological tools, including Physics-Informed Neural Networks (PINNs) and deep learning models such as PhaseNet, are analyzed for their demonstrated ability to enhance EEW systems through sub-second phase picking and automated event detection. Seismic tomography is also undergoing AI-enabled transformation, yielding higher-resolution subsurface imaging. We present statistical validation metrics and uncertainty quantification methods essential for credible hazard assessment. By addressing computational bottlenecks through hybrid computing architectures and edge computing, this framework aims to improve the warning lead time for Istanbul’s critical infrastructure. This work provides a structured roadmap for bridging the gap between traditional seismic data analysis and operational predictive analytics in the Marmara region. Full article

The increasing complexity and distributed nature of Robot Operating System (ROS)-based robotic systems require advanced Fault Detection and Diagnosis (FDD) approaches that operate autonomously with minimal human intervention. The goal of this systematic literature review is to investigate how observability-driven FDD can be automated in ROS-based robotic systems to minimise human effort. Through this lens, the review surfaces four recurring gaps that collectively limit observability-driven automation: rich telemetry sources—logs, traces, and metrics—exist in isolation and are rarely integrated into real-time detection pipelines or leveraged collectively to improve failure diagnostics; online monitoring enables automatic fault detection but depends heavily on predefined rules and expert configuration and interpretation; failure explanations are generated post hoc and rely heavily on logs; and systems remain largely reactive, lacking the continuous monitoring infrastructure needed to anticipate faults before they propagate. Although Large Language Models (LLMs) show considerable promise for automated fault explanation and natural language interaction with robotic systems, current implementations fall short of comprehensive, real-time monitoring that unifies logs, traces, metrics, and sensor streams with Artificial Intelligence (AI) reasoning. To address these gaps, this paper motivates hybrid architectures that combine observability-first design, runtime monitoring, static analysis, and agentic LLM-based reasoning, laying the groundwork for more proactive and autonomous fault management in ROS-based systems. Full article

This paper aims to develop an on-board shock absorber detection method for general aviation aircraft. The effects of common gas and oleo leakage are analyzed in this paper. Based on the principle of landing gear dynamics, it is found that gas leakage and oleo leakage would mainly affect air spring force of shock absorbers in various ways. A rigid–flexible coupled landing gear multi-body system (MBS) model is developed by considering strut flexibility, aiming to offer more accurate simulated responses. A database is developed that considers common leakage faults and typical landing conditions using the developed landing gear model. A deep learning model is proposed in this paper. The proposed model is trained and tested using the database simulated from the rigid–flexible coupling landing gear model. The proposed method demonstrates robust detection performance, achieving over 95% precision for most fault types. This work provides a practical, sensor-efficient solution for real-time health monitoring of landing gear shock absorbers, contributing to improved maintenance strategies and operational safety for general aviation aircraft. As this is a preliminary feasibility study, full validation requires future drop tests or instrumented flight tests. Full article

This research focuses on the application of convolutional neural networks (CNNs) for fault detection in ignition coils and fuel injectors of a YESA 3140 gasoline engine. The objective is to design a CNN capable of identifying when the spark ignition engine (SIE) is operating under optimal conditions and when it presents specific power supply disconnection faults in the four injectors and four coils. Signals from the knock sensor (KS) and camshaft position sensor (CMP) of the SIE were acquired using a MyDAQ data acquisition card and LabVIEW software version 2024. A strict sampling protocol was followed: each replicate had a duration of 5 s while the engine was running at normal operating temperature and idle speed. Prior to each sampling, the SIE was operated with the corresponding fault induced for 5 min. The signals obtained from the KS sensor were transformed into spectrograms, which were then used to train various CNN models. The resulting CNN achieved a classification error of 3.21%. The algorithm was validated by inducing supervised faults in various Otto cycle engines. Full article