Search Results (1,872)

While predictive maintenance increasingly relies on artificial intelligence, strict dependence on cloud computing introduces network latency and demands continuous connectivity, creating critical bottlenecks for time-sensitive industrial applications. To overcome this, we introduce a novel hybrid edge-cloud architecture, which allows deploying an ultra-low-power microcontroller (ESP32-S3) without dedicated AI acceleration hardware to perform complete, operational, predictive maintenance on ultra-constrained embedded hardware. The edge model is optimized to be very small to ensure that increasing model complexity does not cause inference latency to exceed 100 ms or make real-time operation infeasible. We created a very compact INT8-quantized neural network to perform the simultaneous classification of faults and estimation of Time-to-Failure (TTF) with a deterministic mean inference time of 42.3 ms. It dynamically estimates prediction confidence, processes high-confidence predictions locally, and offloads uncertain predictions to a higher-capacity cloud model, and recovers 97.3% of the cloud accuracy gain at 92% of the cloud latency budget. An asymmetric loss function penalizes over-prediction of the remaining useful life, and thus it provides conservative and safe warnings of fault. Operators’ interpretability is improved with Shapley Additive exPlanations (SHAP) and natural-language recommendations. Network outages of up to 50% have not influenced the safety-critical fault recall (above 0.924), so graceful degradation is reached when the network is used in real time in industrial applications. The edge-first with adaptive cloud fallback approach is demonstrated to be technically feasible for a full predictive maintenance workflow—including inference, confidence fusion, and explainability on a low-cost commercial microcontroller. Full article

The 6 February 2023 Kahramanmaraş earthquakes highlighted the importance of emergency assembly areas for disaster response, evacuation safety, and urban resilience in earthquake-prone cities. Although GIS-based multi-criteria decision-making approaches are widely used to assess spatial suitability, relatively few studies integrate suitability, capacity adequacy, and accessibility within a single framework, particularly in cities directly affected by the 2023 earthquakes. This study evaluates emergency assembly areas in Malatya, Türkiye, using an integrated GIS–Best–Worst Method (BWM) framework. Nine criteria—geology, population density, building density, elevation, slope, distance to roads, distance to rivers, distance to fault lines, and distance to buildings—were weighted based on the judgements of 15 experts involved in Provincial Disaster Risk Reduction Plan (İRAP) processes. The BWM results show that geology and distance to fault lines received the highest weights, whereas distance to roads had the lowest weight. The spatial analysis indicates that highly suitable areas are concentrated mainly in the city centre, while several peripheral neighbourhoods are constrained by geological, topographical, and accessibility-related factors. Existing official emergency assembly areas cover only 27.9% of the population and are located in 13 of 88 neighbourhoods. Estimated access times range from 0 to 5 min in central areas to 10–15 min, or beyond effective service coverage, in peripheral neighbourhoods. Although integrating parks and green spaces substantially increases potential capacity, it does not fully eliminate neighbourhood-level inequalities. The findings provide a spatial decision-support framework for emergency planning in earthquake-prone cities. Full article

In this work, we present a decentralized, event-driven control architecture for collaborative rigid object manipulation using omnidirectional wheeled mobile robots. Unlike fixed manipulators, mobile manipulation requires complex coordination between robots, making robustness and fault tolerance critical. Our framework is implemented in ROS2, in which each robot operates independently, with control, kinematic, and motor nodes that communicate via structured message passing. This decentralized design enhances fault tolerance, as individual component failures do not compromise the entire system. To enable perception, an ArUco-based vision system is employed to estimate robot and object poses, supporting the execution of three coordinated subtasks: approaching, grasping, and transporting. The proposed scheme is validated in a Gazebo simulation through different experiments, in which two robots successfully manipulate individual cubes or a beam. Results demonstrate that the proposed event-driven, decentralized control strategy enables consistent coordination, fault-tolerant operation under agent failures, and successful task execution in collaborative manipulation scenarios. Full article

Cross-noise fault diagnosis remains challenging due to the mismatch between training and testing noise conditions, which degrades feature reliability and model generalization. To address this issue, this paper proposes a reliability-guided adaptive feature fusion framework (RGAF-Net). The method focuses on sample-wise adaptive feature fusion, where the enhanced wide first-layer convolutional neural network(WDCNN) backbone is employed to improve multi-scale feature extraction under noisy environments. In addition, a dual-path architecture is introduced to provide complementary representations, including globally robust structural representations and locally detail-sensitive structural responses. Furthermore, a lightweight reliability estimation module is designed to characterize the signal degradation tendency under noisy conditions of each input sample, based on which a sample-wise routing mechanism dynamically adjusts feature contributions during feature fusion. Experiments on two public bearing datasets (PU and JNU) under cross-noise settings demonstrate that the proposed method achieves improved performance compared with representative approaches, particularly under severe noise conditions. For example, on the JNU dataset at −10 dB, the proposed method improves the Macro-F1 score by over 19 percentage points compared with the baseline WDCNN. Ablation studies and visualization analyses further demonstrate the effectiveness and adaptive fusion behavior of the proposed framework. The results indicate that the proposed method provides an effective solution for robust fault diagnosis under noise mismatch scenarios. Full article

Reliable fault detection and quantification are essential for the operational integrity of electric machines. While traditional current-based analysis relies on harmonic signatures or wavelet-based time-frequency representations, this study investigates modern learning formulations that capture spectral, multiscale, and temporal characteristics of fault-affected signals. Moving beyond conventional models, including our earlier CNN-based approaches, we develop sequence-based and operator-learning architectures within a multi-output formulation for eccentricity fault analysis. Three models are investigated: Mamba for temporal dynamics, the Fourier Neural Operator for global spectral mapping, and the Wavelet Neural Operator for localized multiscale decomposition. Evaluated on induction, salient pole synchronous, and inverter-based reluctance synchronous machines, each model maps stator current waveforms to multiple diagnostic quantities, including voltages, operating conditions, and fault severity. With time-delay embedding, all three achieve low prediction errors, with severity RMSE reaching the ${10}^{-4}$ scale for the induction machine, a notable reduction from the $0.04$ errors of our earlier hierarchical CNN models. These results show that modern sequence-based and operator-learning formulations can broaden machine fault analysis by enabling simultaneous prediction and estimation of multiple aspects of machine condition within a single model. Full article

Cooperative localization enables teams of robots to maintain better positioning in GNSS-denied environments by sharing state estimates and inter-robot range measurements to reduce the rate of proprioceptive odometry drift. In scenarios without fixed navigation beacons or pre-surveyed reference nodes, each robot functions as both a positioning client and a mobile ranging peer. A critical vulnerability in this architecture is silent fault propagation. A robot with a degraded localization solution may broadcast an incorrect, often overconfident position estimate, corrupting its peers’ localization. Classical Global Navigation Satellite System (GNSS) Receiver Autonomous Integrity Monitoring (RAIM) methods are ineffective in this context because meter-scale inter-robot separations introduce strong geometric nonlinearity and unstable Geometric Dilution of Precision (GDOP), resulting in scattered subset solutions rather than the coherent, biased clusters that RAIM is designed to detect. This paper addresses this vulnerability by proposing a two-stage distributed Fault Detection and Identification (FDI) architecture for peer-to-peer ranging-based cooperative localization. The first stage applies a global chi-square test on Weighted Least-Squares trilateration residuals to detect the presence of a fault. The second stage identifies the faulty robot by computing Leave-One-Out and Leave-Two-Out subset solutions, which are then partitioned using a clustering algorithm. The cluster that exempts measurements from the faulty robot is identified using either a maximum-cardinality or a minimum-variance criterion. A decentralized voting protocol that requires at least two independent corroborations is then employed for network-wide fault declaration. Monte Carlo simulations show that the clustering-based identification method outperforms classical residual-based methods across multiple fault types, with results reported for the planar (2D) case. No single clustering configuration dominates in terms of identification performance across all tested fault conditions, as performance varies with the fault profile. The proposed architecture operates fully in a distributed manner, requiring only the exchange of position estimates, covariances, and binary votes. Full article

Abnormal circulating current induced by sheath grounding faults in cross-bonded high-voltage cables is a major cause of single-phase grounding faults. For the early detection and localization of sheath grounding faults, this paper constructs an equivalent circuit model for three-phase nine-section cross-bonded cables. Circuit model parameters are estimated via online monitoring data. The relational equation between sheath electrical quantities, fault impedance, and distance is derived for typical sheath grounding faults. Using the Adam algorithm, the solution of fault impedance and location is converted into the minimization of an optimization objective function. Simulation results show that under the influences of phase current imbalance, measurement error, and fault impedance fluctuation, the Adam algorithm exhibits superior optimization accuracy and computational efficiency in comparison with the ED and GA algorithms. Experimental results show that for low-resistance sheath grounding, the proposed method has a fault impedance calculation error ≤ 0.59% and a fault positioning error ≤ 1.89%. For metallic sheath grounding with zero resistance, the positioning error is ≤1.37%. Field test results demonstrate that the proposed method performs similarly to the time-domain reflectometry method, with a positioning deviation ≤ 0.15 m, and can meet online monitoring requirements. Full article

Autonomous vehicles must enforce safety constraints even when their state estimates are corrupted by sensor faults and disturbances. This paper develops a separation-based robust safety-control framework that couples a fault-tolerant observer with a control barrier function (CBF) safety filter through an explicit estimation-error envelope. First, a uniformly ultimately bounded observer-error estimate is derived. This bound is then injected into an estimated-state robust CBF condition, yielding safety margins that account for both observation error and bounded disturbances. The construction is further extended to time-varying safe sets induced by moving obstacles. For implementation, the resulting condition is realized as a quadratic-program safety filter with high-order obstacle and lane constraints. Simulations on a nonlinear 3-DOF bicycle model evaluate bias faults, gust-like disturbances, dense traffic, and tightened stress tests. Compared with a standard CBF baseline and observer/safety-filter ablations, the proposed method preserves nonnegative safety margins while keeping slack activation negligible. Additional sensitivity experiments quantify the trade-off among safety margin, slack usage, observer accuracy, control conservatism, and QP computation time. The results support the proposed architecture as a practical bridge between bounded state estimation and fault-aware safety filtering. Full article

In this paper, for leader–follower structure multi-agent systems (MASs), a new fault-tolerant consensus control mechanism which is called the distributed information estimation and centralized control scheme is developed. To begin with, for each follower agent, an unknown input observer (UIO) is designed to obtain the asymptotic convergence state estimation. Then, a fault reconstruction (FR) method is proposed through constructing an interval observer by sensor measurement output. Most importantly, using the leader’s state estimation provided by the local observer, a distributed observer (DO) is designed so that each follower can obtain the leader’s state estimation. Subsequently, for each follower agent, by using its own state estimation and FR, and the leader’s state estimation offered by the DO, a centralized controller is designed. In this way, a DO-based distributed fault-tolerant control protocol is developed, in which the distributed feature is majorly reflected by the DO construction, resulting in the controller being formulated in a centralized way. In addition, under the DO-based distributed fault-tolerant control protocol, MAS consensus can be reached. Finally, two simulation examples are given to show the effectiveness of the proposed methods. Full article

In permanent magnet synchronous generator-based wind energy conversion systems, generator-side measurements may become unreliable due to sensor faults, which can degrade system reliability. To address this issue, a redundant control framework based on load-side encoder feedback is proposed, where the load-side encoder serves as an alternative measurement source under sensor degradation. Compared with conventional generator-side sensing strategies, the proposed approach enhances fault tolerance without requiring additional hardware redundancy. An extended state observer is employed to estimate system states and lumped disturbances, enabling improved robustness. Simulation results show that the proposed method significantly improves speed tracking performance, reducing the root mean square error by approximately 45% compared with conventional PI control, while maintaining stable operation under sensor degradation conditions. The results demonstrate that the proposed strategy enhances system reliability and robustness in fault scenarios. Full article

Edge Internet of Things (IoT) blockchain deployments increasingly rely on continuous transaction ingestion from resource-constrained IoT devices to nearby edge gateways over heterogeneous wireless links. In this setting, transient channel noise and packet corruption can inject invalid payloads into the edge processing pipeline and trigger unnecessary buffering, parsing, and, most critically, computationally expensive cryptographic operations such as digital signature verification. This leads to wasted computation, increased latency, and reduced energy efficiency at the edge, particularly under dense IoT traffic. This paper presents an energy-aware and fault-tolerant Quantum-Dot Cellular Automata (QCA)-based integrity pre-filter for IoT-to-edge blockchain transaction ingestion. At the circuit level, we adapt and modify a previously reported fault-tolerant five-input majority gate (MV5) structure and use it as a robust primitive for nanoscale integrity-screening circuits. Building on this modified MV5, we design a set of QCA integrity blocks, including a parity checker, a compact XNOR gate circuit, a parity-bit generation circuit, and a sender-to-channel/receiver nano-communication integrity workflow suitable for early screening of corrupted payloads. Compared with the best previously reported baseline considered in this study, the modified MV5 achieves 76.47% tolerance to single-cell omission defects, corresponding to a 17.47 percentage-point increase and an approximately 29.61% relative improvement over the prior 59% omission-tolerance result, while preserving 100% tolerance against extra-cell deposition defects. At the system level, the proposed circuit is discussed as a potential early screening stage for edge-IoT blockchain transaction ingestion. A bounded analytical model is used to estimate the possible reduction in unnecessary signature-verification workload under assumed corruption and detection conditions. This analysis is not intended as a deployment-level validation; full edge-node implementation, throughput measurement, queueing-delay evaluation, real traffic traces, retransmission behavior, and empirical signature-verification profiling remain future work. The proposed parity/chunk-parity pre-filter is designed for low-cost detection of random transmission-induced corruption and does not replace cryptographic authentication, hashing, digital signatures, CRC-based detection, or blockchain validation. All proposed designs are validated using QCADesigner tools. Full article

Soft operational faults can noticeably degrade the performance of heat pumps and influence key monitored variables, emphasizing the need for reliable Fault Detection, Diagnosis, and Evaluation (FDDE) strategies. The BEYOND project tackles this challenge by analyzing simultaneous soft faults using a calibrated simulation model informed by data from a dedicated test rig. Achieving reliable results depends on both accurate measurements and proper model calibration. However, sensor uncertainty and errors in sub-models and correlations calibration can compromise model reliability. This work investigates the influence of measurement accuracy and calibration quality on both experimental variables and simulation outcomes for a residential air-to-water heat pump operating in cooling mode, with particular focus on refrigerant charge estimation. Two sensor configurations—“low accuracy” and “high accuracy”—are assessed, representing commercial- and laboratory-grade instruments, respectively, along with two corresponding calibration strategies. In the low-accuracy case, uncertainties around 10% were found for cooling capacity, energy efficiency ratio, and refrigerant mass flow rate, whereas high-accuracy setups reduced these to approximately 3%. Ultimately, the comparison between experimental and model-derived uncertainties confirms that achieving reliable predictions requires a balanced investment in both high-quality instrumentation and careful model calibration. Overall, this study serves as a crucial tool during the preliminary design of an experimental setup, assisting in the selection of a sensor suite that ensures not only the reliability of secondary variables and KPIs but also a robust and accurate calibration of physics-based models using the acquired experimental data. Full article

This systematic literature review explores the intersection of Artificial Intelligence (AI) and Predictive Maintenance (PdM) within Industry 4.0. Using a PRISMA-based methodology, 123 studies published between 2014 and April 2024 were analyzed to characterize technological trends, algorithmic choices, industrial applications, and evaluation practices. The review reveals a consistent growth of research interest, driven by the widespread adoption of Internet of Things (IoT) devices and increased data availability. The manufacturing sector dominates the literature, although most studies rely on standardized datasets rather than real industrial environments. Among the identified AI methods, Random Forest (RF), Support Vector Machine (SVM), Decision Tree (DT) and K-Nearest Neighbors (KNNs) represent the most frequently applied algorithms for tasks such as failure prediction, fault detection, and remaining useful life (RUL) estimation. Model performance is commonly evaluated with Accuracy (Acc), Precision, Recall, F1-Score, and Root Mean Square Error (RMSE), reflecting the prevalence of both classification and regression-based PdM analyses. Despite significant advances, this review identifies persistent gaps, including limited domain diversity, scarce long-term real-world validation, and insufficient use of eXplainable AI (XAI) techniques. The findings highlight the need for broader domain coverage, improved interpretability, and validation under realistic industrial conditions. Overall, this review consolidates current knowledge on AI-enabled PdM and outlines critical directions to enhance reliability, transparency, and industrial relevance in the context of Industry 4.0. Full article

This paper mainly focuses on the prescribed-time attitude tracking problem of quadrotor unmanned aerial vehicles (QUAVs) with unknown disturbances and actuator faults. Firstly, a prescribed-time disturbance observer (PTDO) is designed based on the prescribed-time stability theorem to estimate the compound lumped disturbance consisting of unknown disturbances and actuator faults, and its prescribed-time stability is proved. Then, a PTDO-based prescribed-time fault-tolerant controller is designed by using the sliding mode control method. A sliding mode fault-tolerant controller is designed based on a prescribed-time sliding surface and reaching law, and its prescribed-time stability is analyzed and proved. The controller aims to achieve the convergence of attitude tracking errors for the QUAVs within a prescribed time in the presence of unknown disturbances and actuator faults. In addition, the convergence time of the controller is determined by simple prescribed-time parameters. The simulation results show that the proposed prescribed-time fault-tolerant control scheme is effective. Full article

This paper proposes a novel prescribed-time formation tracking control farmework of multi-fixed-wing UAVs under external disturbance and actuator failures. As the complexity of aerial missions intensifies, achieving precise position and attitude tracking within a user-defined upper bound of settling time becomes a paramount challenge for intelligent swarm systems. Unlike traditional finite or fixed-time methods, where convergence depends on initial states or suffers from conservative estimation, the proposed approach ensures stability within a prescribed time independent of initial conditions. A key innovation is the introduction of a piecewise reference convergence differential function. This mechanism eliminates the need for state transitions, thereby reducing computational complexity while ensuring smooth tracking without control surface chattering across the entire mission. Additionally, a prescribed-time sliding mode disturbance observer is developed to provide precise and timely compensation for external disturbances and actuator faults. Rigorous Lyapunov analysis proves that all closed-loop signals are bounded and the tracking errors converge to a small neighborhood of zero within the predefined time. Numerical simulations demonstrate that, under time-varying disturbances and actuator faults, the disturbance estimation errors converge within 4 s, while both attitude and velocity tracking errors converge within 6 s, achieving fast transient response and high tracking accuracy. The UAV swarm successfully maintains the desired formation during aggressive maneuvers, including speed variations, climbing, and diving. These results verify that the proposed method provides a computationally efficient, robust, and high-precision solution for time-critical formation control of fixed-wing UAV swarms under complex uncertainties. Full article