Search Results (5,082)

In classical reliability engineering, failure is a probabilistic structural failure based on lifetime distributions of Weibull models. However, in the control-critical mechanical systems, it is possible that functional failure of the system happens before material failure occurs as a result of control power loss. This paper proposes a Controllability–Reliability Coupling (CRC) model, which redefines the concept of reliability as the stabilizability in the face of progressive degradation. The actuators’ deterioration is modeled using the time-varying input effectiveness factor $\alpha \left(t\right)$, and the actuator is said to be in failure when the minimum singular value of the finite-horizon controllability Gramian becomes less than a stabilizability threshold $\epsilon$. The performance of the simulation indicates that the functional failure is a precursor of structural failure in several degradation conditions. A baseline comparison shows that the CRC metric forecasts loss of controllability at $T_{CRC}=17.0$ s, but the classical Weibull reliability never attains the structural failure threshold even in the time horizon of 20 s. The system retains margins of Lyapunov stability and H infinity robustness are not lost, and it is still stable and attenuates disturbances even when control authority is lost. In practical degradation scenarios, the forecasted CRC failure times are 21.5 s (linear wear), 13.1 s (accelerated fatigue), 23.7 s (intermittent faults), and 24.4 s (shock damage), whereas maintenance recovery abated functional failure completely. In a case study of an industrial robotic joint, at 27.0 s, functional collapse occurred, and at the same time, structural reliability was still above the failure threshold. The findings support the hypothesis that structural survival and functional controllability are distinct concepts. The proposed CRC framework is an approach to control-conscious reliability measure, which can detect early failures and offer proactive maintenance advice in the context of a cyber–physical system. Full article

The increasing proportion of renewable energy leads to frequent changes in turbine load, making the regulating stage more prone to degradation. Traditional anomaly detection methods lack sufficient sensitivity and generalization. To address this issue, this study proposes a method combining multi-attention gated fusion and physical information learning. A gated fusion mechanism is proposed to adaptively extract and fuse key temporal and feature information. Furthermore, the generalization ability of the model is improved by introducing physical constraints derived from the relationship between pressure, temperature, and valve position. Finally, a dynamic temperature prediction model is established using the multi-output long short-term memory neural network. Experiments using actual power plant data demonstrate that the proposed method effectively improves the accuracy of post-regulating-stage temperature prediction and the sensitivity of anomaly detection. The proposed gating fusion method improves prediction accuracy by 4.6% compared to direct addition, while the fusion of physical information reduces the generalization error by more than 6%. In addition, compared to traditional deep learning and machine learning models, the proposed method improves anomaly detection accuracy by at least 3.9%. This research is of great significance for the safe operation of thermal power units and the power grid. Full article

Accurate prediction of hard disk drive (HDD) health states is critical for enabling proactive data maintenance and ensuring data reliability in large-scale data centers. However, conventional models often suffer from semantic entanglement among heterogeneous SMART attributes and from the masking of incipient failure signatures by stochastic noise. To address these challenges, we propose SDGR-Net, a spatiotemporally decoupled learning framework designed to model the complex degradation dynamics of HDDs. SDGR-Net introduces three synergistic innovations: (1) a spatiotemporally decoupled dual-branch encoder that disentangles longitudinal temporal evolution from cross-variable correlations via parameter-isolated branches, thereby reducing representational interference; (2) a parsimonious dual-view temporal extraction mechanism that captures early-stage anomalies through forward–reverse sequence concatenation, enabling high-fidelity preservation of non-stationary pre-failure patterns; and (3) a cross-branch dynamic gated residual fusion module that functions as an adaptive information bottleneck to emphasize failure-critical features while suppressing redundant noise. Extensive experiments conducted on three heterogeneous HDD datasets, ST4000DM000, HUH721212ALN604, and MG07ACA14TA, demonstrate that SDGR-Net consistently outperforms six state-of-the-art baselines. In particular, SDGR-Net achieves a peak fault detection rate (FDR) of 0.9898 and a 69.6% relative reduction in false alarm rate (FAR) under high-reliability operating conditions. These results, corroborated by comprehensive ablation studies, indicate that SDGR-Net effectively balances detection sensitivity and operational robustness, offering a practical solution for intelligent HDD health monitoring. Full article

Detecting and disconnecting faults is of utmost importance in power systems to prevent damage, outages and limit the impact on the surrounding grid. However, there are faults that may not be detected by protective functions and therefore do not interrupt the operation. Such faults, which have not been considered during the design of an HVDC system despite causing negative operational impacts, are referred to as abnormal failure modes in this paper. Data from three cases of abnormal failure modes in point-to-point HVDC systems are presented. The first case regards a prolonged subsequential failure of a DC filter capacitor for an LCC-HVDC link. The second case presents a measurement disturbance resulting in power oscillations from a VSC-HVDC link. The third case shares details of an overload scenario of a grounding impedance due to DC voltage unbalance from asymmetric corona discharges. This study shares details from these failures and suggests recommendations based on the presented abnormal failure modes in HVDC applications, including multi-terminal HVDC systems. Full article

Due to their vast potential, Unmanned Aerial Vehicles (UAVs) are increasingly being utilized in various applications. To prevent in-flight failures and loss of control, implementing Internet of Things (IoT)-based Predictive Maintenance (PdM) systems is crucial. However, data collected from PdM systems often contains outliers, which can significantly degrade the accuracy and performance of predictive models. In this paper, we present a comparative performance analysis of several outlier detection methods, namely K-Nearest Neighbors (KNN), Autoencoder (AE), and Isolation Forest (IForest). The datasets used to evaluate these methods were acquired from a UAV predictive maintenance system designed to estimate the Remaining Useful Life (RUL) of Li-ion batteries and detect faults in Brushless DC (BLDC) motors. Ultimately, this study aims to determine the most effective outlier detection method for UAV predictive maintenance datasets. Full article

Early and reliable fault detection in Brushless Direct Current (BLDC) motors is essential for improving system reliability and reducing unplanned industrial downtime. This study presents a controlled experimental investigation of data-driven machine learning approaches for the classification of multiple common BLDC motor faults. Four representative fault-related indicators were obtained under systematically designed operating conditions, and a consistent feature extraction procedure was applied prior to model development. A comparative evaluation was conducted using Multi-Layer Perceptron (MLP), Support Vector Machines (SVM), k-Nearest Neighbour (kNN), and decision tree-based classifiers. All models were trained and tested on the same dataset using an identical validation protocol to ensure methodological fairness and reproducibility. Performance was assessed through standard classification metrics, enabling a transparent comparison of predictive capability and stability. The results show that the MLP model achieved the highest overall classification accuracy (91.6%), closely followed by SVM (91.4%) and kNN (90.2%). Although the performance differences are moderate, the neural network demonstrated more consistent behaviour in scenarios where fault signatures exhibited overlapping characteristics. These findings suggest that non-linear feature interactions play a significant role in BLDC fault discrimination and can be effectively captured by multi-layer architectures. The study provides a reproducible experimental framework and a balanced performance assessment that may support both academic research and the practical development of intelligent condition monitoring systems for BLDC-driven applications. Full article

Fault Detection and Diagnosis (FDD) in complex industrial systems requires methods that can handle uncertain operating conditions, soft thresholds, evolving sensor behavior, and increasing volumes of heterogeneous data. Traditional model-based or rule-driven approaches offer interpretability but lack adaptability, while purely data-driven and Large Language Model (LLM)-based methods often struggle with consistency, traceability, and causal grounding. Dynamic Master Logic (DML) provides a causal and temporal reasoning structure with fuzzy rules that capture gradual drift, soft limits, and asynchronous sensor signals while preserving traceability and deterministic evidence propagation. Building on this foundation, this paper presents a DML–LLM hybrid architecture that integrates targeted LLM inference to interpret unstructured information such as logs, notes, or retrieved documents under controlled prompts that maintain domain constraints. The combined system integrates Bayesian updating, deterministic routing, and semantic interpretation into a unified FDD pipeline. In a semiconductor manufacturing case study, the proposed framework reduced time to detection (TTD) from 7.4 h to 1.2 h and improved the F1 score from 0.59 to 0.83 when compared with conventional Statistical Process Control (SPC) and Fault Detection and Classification (FDC) workflows. Provenance completeness increased from 18% to 96%, while engineer triage time was reduced from 72 min to 18 min per event. These results demonstrate that the hybrid framework provides a scalable and explainable approach to anomaly detection and fault diagnosis in sensor-rich industrial environments. Full article

Fault detection in microgrids is a critical element of system stability and uninterrupted power delivery. Herein, a comparative study using LSTM and bidirectional LSTM networks is performed based on three-phase current data for multi-class fault classification. Five major fault types, namely LG, LL, LLG, LLL, and LLLG, were simulated using a Real-Time Digital Simulator (RTDS) under grid-connected and islanded modes. Collected current signals were preprocessed, normalized, and segmented for sequence learning. Later, both models were trained using the best hyperparameter setting to enhance their capabilities and classify faults. To measure how well they identified faults, evaluation metrics, like accuracy, precision, recall, F1-score, and ROC-AUC, were calculated. The results revealed that the Bi-LSTM outperformed the LSTM and classical machine learning models consistently, with more than 99% accuracy for most fault types. More importantly, the proposed framework also checked classification performance for LLLG faults, with the Bi-LSTM model having a test accuracy of 98.8%. These results confirm that the Bi-LSTM model can robustly and precisely classify and detect faults in real time within specific phases of microgrids; therefore, it provides a scalable foundation for the development of intelligent protection in smart power systems. Full article

To address the challenge that prolonged interruptions of Global Navigation Satellite System (GNSS) signals—such as those caused by urban obstructions—hinder signal re-locking and thereby reduce the number of available satellites for integrity monitoring algorithms, this study proposes an inertial navigation-assisted GNSS re-locking method based on vehicle motion information constraints. This method leverages vehicle motion constraints to confine the primary direction of Inertial Navigation System (INS) velocity errors to the vehicle’s forward direction. Upon GNSS signal recovery, frequency error compensation is employed to mitigate Doppler errors of the previously obstructed satellites. Simulation results show that this method significantly improves the re-lock capability after a long period of satellite signal interruption, increasing the number of available satellites from 7 to 10 and optimizing the satellite geometry. At a horizontal alarm threshold of 80 m, the availability of the GNSS integrity monitoring algorithm reaches 95.7%, which is 53.7 percentage points higher than the unassisted scheme. Moreover, it can achieve 100% fault detection and identification rate even with a pseudorange deviation of 82 m, significantly improving the performance of the integrity monitoring algorithm. Full article

Anti-friction bearings are fundamental components of rotating machines. In bearing condition monitoring, fault detection is a primary task, as any undetected faults could result in catastrophic failures and downtime losses. To ensure effective and reliable fault detection, the use of appropriate sensors and measurement technologies is essential. This paper presents a comparative study on the applications of four sensor types in bearing condition monitoring. These four sensor types are vibration accelerometer, encoder, acoustic emission (AE) sensor and motor current probe. Their effectiveness and practicability in bearing fault detection are evaluted. Data simultaneously measured from these four sensor types on a split roller bearing within an experimental rig are used for the analysis. Different factors such as machine operating speeds, bearing fault sizes and their location are considered during the experiments to understand the effectiveness and fault detectability of different sensors on a common bearing. Both the accelerometer and the AE sensor are observed to effectively detect all bearing faults from small to extended sizes and from low to high operating speeds. However, the other two sensors, the encoder and motor current probe, have been found to be sensitive only to relatively larger fault sizes and higher operating speeds. The study presents valuable insights into their advantages and limitations through a systematic comparison of roller bearing fault detection. The study provides a basis for sensor selection in bearing condition monitoring and fault detection to enhance the reliability of industrial maintenance activities. Full article

Unbalanced supply voltage (USV) represents a critical power quality challenge in industrial environments, significantly degrading the performance, efficiency, and operational lifespan of three-phase induction motors. Accurate real-time estimation of sequence impedances ($Z_a,Z_b,Z_c$) and detection of the Negative Voltage Factor (NVF) are essential for effective condition monitoring and preventive maintenance strategies. While existing machine learning methods have demonstrated promising accuracy, they often rely on manual feature engineering, lack hierarchical representation learning, and treat impedance estimation and fault detection as isolated tasks. This paper proposes a unified Deep Multi-Task Learning framework that leverages Residual Multilayer Perceptron (ResMLP) architectures for feature-based learning and Temporal Convolutional Networks (TCNs) for end-to-end raw signal learning. Our contributions include: (1) introduction of a Multi-Head ResMLP architecture that jointly optimizes phase impedance and fault detection, achieving superior NVF accuracy (MAE = 0.0007) and a fault detection F1-score of 0.8831; (2) investigation of raw-voltage TCN models for voltage-only diagnostics, with analysis of the trade-offs between end-to-end learning and feature-based approaches; (3) extensive ablation studies demonstrating the impact of network depth, data augmentation, and training protocols on model generalization; and (4) deployment of PyTorch (v2.0.1)-based models suitable for embedded systems with real-time inference capabilities (2.3 ms per prediction). Experimental validation on a 1.1 kW three-phase motor dataset under diverse load conditions (0–10 Nm) and USV magnitudes (5–15 V) confirms the robustness and practical applicability of the proposed approach for industrial fault diagnosis and condition monitoring systems. Full article

Geochemical anomaly detection is a critical stage in mineral exploration, playing a key role in predicting potential mineral targets. Traditional methodologies often struggle to integrate the spatial structure of geochemical data with underlying geological constraints effectively. To address this limitation, we propose GeoCLA, a geochemical anomaly detection framework that integrates Convolutional Neural Networks (CNNs), Bidirectional Long Short-Term Memory (BiLSTM) networks, and an Attention Mechanism (AM). This integrated spatial-attention architecture captures complex correlations among multiple features to improve anomaly identification. The method constructs spatial sequential samples from geochemical data. The CNNs extract local spatial patterns, the BiLSTM models sequential dependencies, and the AM enhances the representation of critical features. Anomaly scores are computed using the reconstruction error between the model output and the original data. In addition, a fault-distance weighting factor is incorporated to build a comprehensive anomaly evaluation index. The proposed model was applied to the Hatu gold district in Xinjiang, China. Both visual analysis and quantitative evaluation demonstrate effectiveness, achieving a ROC-AUC of 0.86 and a mineral occurrence coverage rate of 97% within moderate-to-high anomaly prospective areas, significantly outperforming baseline methods. Full article

In this paper, the task of detecting bearing faults in railway vehicles during regular operation by analyzing acoustic (airborne sound) data is addressed. To that end, various features are studied, among which the Mel Frequency Cepstral Coefficients (MFCCs) are best suited for detecting bearing faults by analyzing airborne sound. The MFCCs are used to train a Multi-Layer Perceptron (MLP) classifier. The proposed method is evaluated with real-world data for a state-of-the-art commuter railway vehicle in a dedicated measurement campaign. Classification results demonstrate that the chosen MFCC features allow for reliable detection of bearing damages, even for damages that were not included in training. Full article

Predictive maintenance aims to monitor equipment conditions through data-driven analysis and estimate failure in advance, which enables the scheduling of maintenance prior to equipment breakdown. In this work, a deep-learning neural network is used to predict the condition of the belt-drive system. A combined Convolutional Neural Network with Bi-directional Long Short-Term Memory (CNN-BiLSTM) model is assigned for processing the operational parameters along with vibrational signals to predict belt-drive system conditions in two separate binary classifications: faulty or healthy and unbalanced or balanced conditions. The data flow in the CNN-BiLSTM model initiates with the CNN to extract the features from the vibration signals and performs essential pattern detection. Consequently, the BiLSTM’s role is to capture long-term temporal relationships that cannot be captured by the CNN alone. To predict the targeted conditions, a fully connected layer with a classifier is built at the BiLSTM outputs. For efficient model training, the data is preprocessed through denoising, augmentation, and normalization. Additionally, hyperparameter tuning is conducted to explore different model configurations and select the optimal ones on the basis of relevant performance. An ablation study is conducted to investigate the use of CNN and BiLSTM models individually, confirming that combining both components is essential for accurate classification. Moreover, the cross-validation technique is used to assess the proposed model’s generality by organizing unseen data across rotational speeds, which also depicts robust performance under varying operating conditions. The key added value of this study lies in integrating deep-learning techniques to address a knowledge gap by using raw vibrational signals to establish intelligent monitoring systems, which represents a new scientific contribution to the predictive maintenance of belt-drive systems. Full article

The stable and accurate output of the inertial measurement unit array (IMU) of a micro-electro-mechanical system (MEMS) is the key to ensuring the data fusion of the MEMS IMU array. However, due to the large number of MEMS IMUs contained in the MEMS IMU array, it is susceptible to interference and has difficulty avoiding failures. The output of the MEMS IMU contains noise, outliers, and other related errors, which can seriously lead to low fault detection and isolation accuracy in the MEMS IMU. In this study, a new method of fault detection and isolation based on multivariate variational mode decomposition (MVMD), a whale optimization algorithm (WOA), and a generalized likelihood test (GLT) is proposed, which is called WOA-MVMD-GLT. Firstly, a multi-index fitness function WOA is proposed to optimize the parameters of MVMD. Secondly, MVMD is used to extract the features of the MEMS IMU’s signals. Finally, a GLT is used to construct a fault detection function and a fault isolation function to detect and isolate the faults of gyroscopes and accelerometers. The experimental results show that the method proposed in this paper can significantly reduce the false alarm rate and false isolation rate. Full article