Search Results (78)

In this work, a fault detection method and a distributed consensus fault-tolerant control (FTC) scheme are proposed for multiple quadrotor unmanned aerial vehicles (multi-QUAVs) with actuator faults. In order to identify the actuator faults in time, an auxiliary state observer is constructed first. Subsequently, a fault detection scheme based on the observer error is presented, which can improve the early warning ability of the multi-QUAVs. Meanwhile, to handle unknown sudden faults, the Nussbaum function approach is combined with the consensus theory to design a distributed consensus FTC strategy for multi-QUAVs. Compared with the traditional direct fault estimation method using the projection function technique, the proposed Nussbaum-based FTC method can avoid the singularity problem of the controller in a simple way. Moreover, all error signals of the closed-loop system are proved to be uniformly ultimately bounded via Lyapunov stability theory and the consensus control algorithm. Finally, simulation comparison results indicate the early warning capability of the fault detection method and the formation maintenance performance of the developed fault-tolerant controller. Full article

Rolling bearing failure poses significant risks to mechanical system integrity, potentially leading to catastrophic safety incidents. Current challenges in performance degradation assessment include complex structural characteristics, suboptimal feature selection, and inadequate health index characterization. This study proposes a novel attention mechanism-based feature fusion method for accurate bearing performance assessment. First, we construct a multidimensional feature set encompassing time domain, frequency domain, and time–frequency domain characteristics. A two-stage sensitive feature selection strategy is developed, combining intersection-based primary selection with clustering-based re-selection to eliminate redundancy while preserving correlation, monotonicity, and robustness. Subsequently, an attention mechanism-driven fusion model adaptively weights selected features to generate high-performance health indicators. Experimental validation demonstrates the proposed method’s superiority in degradation characterization through two case studies. The intersection clustering strategy achieves 32% redundancy reduction compared to conventional methods, while the attention-based fusion improves health indicator consistency by 18.7% over principal component analysis. This approach provides an effective solution for equipment health monitoring and early fault warning in industrial applications. Full article

To meet the demands for real-time and accurate fault warning of wind turbine gear transmission systems, this study proposes an innovative intelligent warning method based on the integration of digital twin and multi-source data fusion. A digital twin system architecture is developed, comprising a high-precision geometric model and a dynamic mechanism model, enabling real-time interaction and data fusion between the physical transmission system and its virtual model. At the algorithmic level, a CNN-LSTM-Attention fault prediction model is proposed, which innovatively integrates the spatial feature extraction capabilities of a convolutional neural network (CNN), the temporal modeling advantages of long short-term memory (LSTM), and the key information-focusing characteristics of an attention mechanism. Experimental validation shows that this model outperforms traditional methods in prediction accuracy. Specifically, it achieves average improvements of 0.3945, 0.546 and 0.061 in Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and R-squared (R²) metrics, respectively. Building on the above findings, a monitoring and early warning platform for the wind turbine transmission system was developed, integrating digital twin visualization with intelligent prediction functions. This platform enables a fully intelligent process from data acquisition and status evaluation to fault warning, providing an innovative solution for the predictive maintenance of wind turbines. Full article

The Mw 7.8 Gorkha Earthquake of 25 April 2015 triggered over 25,000 landslides across central Nepal, with 4775 events concentrated in Gorkha District alone. Despite substantial advances in landslide susceptibility mapping, existing studies often overlook the compound role of post-seismic rainfall and lack robust spatial validation. To address this gap, we validated an ensemble machine learning framework for co-seismic landslide susceptibility modeling by integrating seismic, geomorphological, hydrological, and anthropogenic variables, including cumulative post-seismic rainfall. Using a balanced dataset of 4775 landslide and non-landslide instances, we evaluated the performance of Logistic Regression (LR), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost) models through spatial cross-validation, SHapley Additive exPlanations (SHAP) explainability, and ablation analysis. The RF model outperformed all others, achieving an accuracy of 87.9% and a Receiver Operating Characteristic (ROC) Area Under the Curve (AUC) value of 0.94, while XGBoost closely followed (AUC = 0.93). Ensemble models collectively classified over 95% of observed landslides into High and Very High susceptibility zones, demonstrating strong spatial reliability. SHAP analysis identified elevation, proximity to fault, peak ground acceleration (PGA), slope, and rainfall as dominant predictors. Notably, the inclusion of post-seismic rainfall substantially improved recall and F1 scores in ablation experiments. Spatial cross-validation revealed the superior generalizability of ensemble models under heterogeneous terrain conditions. The findings underscore the value of integrating post-seismic hydrometeorological factors and spatial validation into susceptibility assessments. We recommend adopting ensemble models, particularly RF, for operational hazard mapping in earthquake-prone mountainous regions. Future research should explore the integration of dynamic rainfall thresholds and physics-informed frameworks to enhance early warning systems and climate resilience. Full article

The Jidong Oilfield No. 2 Underground Gas Storage (UGS), located in an active fault zone in Northern China, is a key facility for ensuring natural gas supply and peak regulation in the Beijing–Tianjin–Hebei region. To evaluate the effectiveness of a combined surface and shallow borehole monitoring system under deep reservoir conditions, a 90-day microseismic monitoring trial was conducted over a full injection cycle using 16 surface stations and 1 shallow borehole station. A total of 35 low-magnitude microseismic events were identified and located using beamforming techniques. Results show that event frequency correlates positively with wellhead pressure variations instead of the injection volume, suggesting that stress perturbations predominantly control microseismic triggering. Events were mainly concentrated near the bottom of injection wells, with an average location error of approximately 87.5 m and generally shallow focal depths, revealing limitations in vertical resolution. To enhance long-term monitoring performance, this study recommends deploying geophones closer to the reservoir, constructing a 3D velocity model, applying AI-based phase picking, expanding array coverage, and developing a microseismic-injection coupling early warning system. These findings provide technical guidance for the design and deployment of long-term monitoring systems for deep reservoir conversions into UGS facilities. Full article

Gearbox failure represents one of the most time-consuming maintenance challenges in wind turbine operations. Abnormal temperature variations in the gearbox high-speed shaft (GHSS) serve as reliable indicators of potential faults. This study proposes a Spatio-Temporal Attentive (STA) synergistic architecture for GHSS fault detection and early warning by utilizing the in situ monitoring data from a wind farm. This comprehensive architecture involves five modules: data preprocessing, multi-dimensional spatial feature extraction, temporal dependency modeling, global relationship learning, and hyperparameter optimization. It was achieved by using real-time monitoring data to predict the GHSS temperature in 10 min, with an accuracy of 1 °C. Compared to the long short-term memory (LSTM) and convolutional neural network and LSTM hybrid models, the STA architecture reduces the root mean square error of the prediction by approximately 37% and 13%, respectively. Furthermore, the architecture establishes a normal operating condition model and provides benchmark eigenvalues for subsequent fault warnings. The model was validated to issue early warnings up to seven hours before the fault alert is triggered by the supervisory control and data acquisition system of the wind turbine. By offering reliable, cost-effective prognostics without additional hardware, this approach significantly improves wind turbine health management and fault prevention. Full article

To address the coupled fault diagnosis challenge between temperature sensors and equipment in traction converter cooling systems, this paper proposes a dual-level intelligent diagnostic architecture. This method achieves online sensor fault isolation and early equipment anomaly warning by leveraging spatiotemporal correlation modeling of multimodal sensor data and ensemble learning-based prediction. At the first level, it integrates multi-source parameters such as outlet temperature and pressure to establish dynamic prediction models, which are combined with adaptive threshold mechanisms for detecting various sensor faults including offset, open-circuit, and noise interference. At the second level, it monitors the status of temperature sensors through time-series analysis of inlet temperature data. Verified on an edge computing platform, the proposed method effectively resolves the coupling misdiagnosis between sensor distortion and equipment faults while maintaining physical interpretability, thereby significantly enhancing diagnostic robustness under complex operating conditions. Full article

The increasing deployment of wind energy systems, particularly offshore wind farms, necessitates advanced monitoring and maintenance strategies to ensure optimal performance and minimize downtime. Supervisory Control And Data Acquisition (SCADA) systems have become indispensable tools for monitoring the operational health of wind turbines, generating vast quantities of time series data from various sensors. Anomaly detection techniques applied to this data offer the potential to proactively identify deviations from normal behavior, providing early warning signals of potential component failures. Traditional model-based approaches for fault detection often struggle to capture the complexity and non-linear dynamics of wind turbine systems. This has led to a growing interest in data-driven methods, particularly those leveraging machine learning and deep learning, to address anomaly detection in wind energy applications. This study focuses on the development and application of a semi-supervised, multivariate anomaly detection model for horizontal axis wind turbines. The core of this study lies in Bidirectional Long Short-Term Memory (BI-LSTM) networks, specifically a BI-LSTM autoencoder architecture, to analyze time series data from a SCADA system and automatically detect anomalous behavior that could indicate potential component failures. Moreover, the approach is reinforced by the integration of the Isolation Forest algorithm, which operates in an unsupervised manner to further refine normal behavior by identifying and excluding additional anomalous points in the training set, beyond those already labeled by the data provider. The research utilizes a real-world dataset provided by EDP Renewables, encompassing two years of comprehensive SCADA records collected from a single offshore wind turbine operating in the Gulf of Guinea. Furthermore, the dataset contains the logs of failure events and recorded alarms triggered by the SCADA system across a wide range of subsystems. The paper proposes a multi-modal anomaly detection framework orchestrating an unsupervised module (i.e., decision tree method) with a supervised one (i.e., BI-LSTM AE). The results highlight the efficacy of the BI-LSTM autoencoder in accurately identifying anomalies within the SCADA data that exhibit strong temporal correlation with logged warnings and the actual failure events. The model’s performance is rigorously evaluated using standard machine learning metrics, including precision, recall, F1 Score, and accuracy, all of which demonstrate favorable results. Further analysis is conducted using Cumulative Sum (CUSUM) control charts to gain a deeper understanding of the identified anomalies’ behavior, particularly their persistence and timing leading up to the failures. Full article

This paper presents an integrated methodology for remote monitoring, technical training and early warning systems in virtual reality environments oriented towards Industry 4.0. The proposal incorporates an engine modeled as a digital twin in Unity 3D, connected to physical sensors, and transmitted through an IoT platform. This architecture allows continuous monitoring and immersive visualization, in addition to generating alerts when operating conditions exceed critical limits, allowing users to simulate fault conditions in real time and perform interactive training without putting equipment or operators at risk. This work proposes a low-cost simulation platform, based on virtual reality and real-time digital twins, designed to support training and capacity building in industrial environments. This methodology seeks to propose general guidelines that allow the integration of these technologies in a general way to enrich both preventive and predictive maintenance mechanisms, as well as training processes. Full article

Accurate temperature prediction is critical for ensuring mechanical stability and operational safety during complex operating conditions and long-term operation of rolling bearings. This study proposes a digital twin (DT) system for bearing thermal analysis and a digital twin-driven virtual–real hybrid framework, achieving thermal prediction from low-risk behaviors (low-speed/light-load) to high-risk behaviors (high-speed/heavy-load). To address the time-varying and ambiguous parameters, an efficient Nutcracker Optimization Algorithm (NOA)-based identification mechanism is introduced to dynamically calibrate the virtual thermal model, overcoming the limitations of static modeling and data isolation inherent in conventional thermal analysis methods. The Euclidean distance and uncertainty analysis between real temperature and predicted temperature demonstrate the highly reliable predictive ability of the proposed framework in terms of bearing thermal, especially under variable speed conditions. The proposed framework has certain guiding significance for enhancing thermal safety and fault early-warning capabilities of bearings during long-term operation. Full article

The contact condition of circuit breaker contacts directly affects their operational reliability, while circuit resistance, as a key performance indicator, reflects physical changes such as wear, oxidation, and ablation. Traditional offline measurement methods fail to accurately represent the real-time operating state of equipment due to large errors and high randomness, limiting their effectiveness for state awareness and precision maintenance. To address this, a non-contact multi-sensor fusion method for the online monitoring of circuit breaker circuit resistance is proposed, aimed at enhancing operational state awareness in power systems. The method integrates Hall effect current sensors, infrared temperature sensors, and electric field sensors to extract multiple sensing signals, combined with high-precision signal processing algorithms to enable the real-time identification and evaluation of circuit resistance changes. Experimental validation under various scenarios—including normal load, overload impact, and high-temperature and high-humidity environments—demonstrates excellent system performance, with a fast response time (≤200 ms), low measurement error (<1.5%), and strong anti-interference capability (SNR > 60 dB). In field applications, the system successfully identifies circuit resistance increases caused by contact oxidation and issues early warnings, thereby preventing unplanned outages and demonstrating a strong potential for application in the fault prediction and intelligent maintenance of power grids. Full article

In the context of intelligent manufacturing, equipment fault early-warning technology has become a critical support for ensuring the continuity and safety of industrial production. However, with the increasing complexity of modern industrial equipment structures and the growing coupling of operational states, traditional fault warning models face significant challenges in feature recognition accuracy and adaptability. To address these issues, this study proposes a hybrid fault early-warning framework that integrates an improved bees algorithm (IBA) with a categorical boosting (CatBoost) model and kernel density estimation (KDE). The proposed framework first develops the IBA by integrating Latin Hypercube Sampling, a multi-perturbation neighborhood search strategy, and a dynamic scout bee adjustment strategy, which effectively overcomes the conventional bees algorithm (BA)’s tendency to fall into local optima. The IBA is then employed to achieve global optimization of CatBoost’s key hyperparameters. The optimized CatBoost model is subsequently used to predict equipment operational data. Finally, the KDE method is applied to the prediction residuals to determine fault thresholds. An empirical study on a deflection fault in the valve position sensor connecting rod of the mineral oil system in a gas compressor station shows that the proposed method can issue early-warning signals two hours in advance and outperforms existing advanced algorithms in key indicators such as root mean square error (RMSE), coefficient of determination (R²) and mean absolute percentage error (MAPE). Furthermore, ablation experiments verify the effectiveness of the strategies in IBA and their contribution to CatBoost hyperparameter optimization. The proposed method significantly improves the accuracy and reliability of fault prediction in complex industrial environments. Full article

Early warning systems (EWSs) are crucial for optimising predictive maintenance strategies, especially in the industrial sector, where machine failures often cause significant downtime and economic losses. This research details the creation and evaluation of an EWS that incorporates deep learning methods, particularly using Long Short-Term Memory (LSTM) networks enhanced with attention layers to predict critical machine faults. The proposed system is designed to process time-series data collected from an industrial printing machine’s embosser component, identifying error patterns that could lead to operational disruptions. The dataset was preprocessed through feature selection, normalisation, and time-series transformation. A multi-model classification strategy was adopted, with each LSTM-based model trained to detect a specific class of frequent errors. Experimental results show that the system can predict failure events up to 10 time units in advance, with the best-performing model achieving an AUROC of 0.93 and recall above 90%. Results indicate that the proposed approach successfully predicts failure events, demonstrating the potential of EWSs powered by deep learning for enhancing predictive maintenance strategies. By integrating artificial intelligence with real-time monitoring, this study highlights how intelligent EWSs can improve industrial efficiency, reduce unplanned downtime, and optimise maintenance operations. Full article

Monitoring and early warning systems for cross-fault buried pipelines are critical measures to ensure the safe operation of oil and gas pipelines. Accurately acquiring pipeline strain response serves as the fundamental basis for achieving this objective. This study proposes a comprehensive analytical methodology combining finite element analysis (FEA) and experimental verification to investigate strain responses in cross-fault buried pipelines. Firstly, a finite element modeling approach with equivalent-spring boundaries was established for cross-fault pipeline systems. Secondly, based on the similarity ratio theory, an experimental platform was designed using Φ89 mm X42 steel pipes and in situ soil materials. Subsequently, the finite element model of the experimental conditions was constructed using the proposed FEA. Guided by simulation results, strain sensors were strategically deployed on test pipelines to capture strain response data under mechanical loading. Finally, prototype-scale strain responses were obtained through similarity ratio inverse modeling, and a comparative analysis with full-scale FEA results was performed. The results demonstrate that strike-slip fault displacement induces characteristic “S”-shaped antisymmetric deformation in pipelines, with maximum strain concentrations occurring near the fault plane. Both the magnitude and location of maximum strain derived from similarity ratio inverse modeling show close agreement with FEA predictions, with relative discrepancies within 18%. This consistency validates the reliability of the experimental design and confirms the accuracy of the finite element model. The proposed methodology provides valuable technical guidance for implementing strain-based monitoring and early warning systems in cross-fault buried pipeline applications. Full article

To enhance the safety of lithium ternary battery cases in new energy vehicles, this study designed a temperature monitoring and fault warning system based on NiCr/NiSi thin-film thermocouples. The system integrates six modules—sensor, amplifier, data acquisition, microprocessor (using the KPCA nonlinear dimensionality reduction algorithm), communication and monitoring, and alarm control—to monitor temperature, voltage, and humidity changes in real time. Multi-level warning thresholds are established (e.g., Level 1: initial temperature 35–55 °C rising to 42–65 °C after 10 min; initial voltage 400–425 V dropping to 398–375 V after 10 min). Experimental results demonstrate that the NiCr/NiSi thermocouple exhibits high sensitivity (average Seebeck coefficient: 41.42 μV/°C) and low repeatability error (1.04%), with a dense and uniform surface structure (roughness: 3.2–5.75 nm). The warning logic, triggered in four levels based on dynamic temperature and voltage changes, achieves an 80% accuracy rate and a low false/missed alarm rate of 4%. Long-term operation tests show stable monitoring deviations (±0.2 °C for temperature and ±0.02 V for voltage over 24 h). The system also adapts to varying humidity environments, with peak sensitivity (41.3 μV/°C) at 60% RH. This research provides a highly reliable solution for battery safety management in new energy vehicles. Full article