Search Results (151)

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

This paper presents a hybrid algorithmic framework for fault detection and isolation (FDI) in nonlinear quadrotor unmanned aerial vehicle (UAV) systems operating under closed-loop conditions. The proposed method integrates a Linear Quadratic Control (LQC) strategy, synthesized through Linear Matrix Inequalities (LMIs), with a Conditional Long Short-Term Memory Autoencoder (CLSTM-AE) and an adaptive residual-based decision mechanism. The LQC scheme provides robust trajectory tracking through regional pole-placement constraints, while the CLSTM-AE learns the nominal closed-loop input–output temporal behavior of the UAV using only fault-free data. In contrast to conventional symmetric autoencoder-based detectors, the proposed CLSTM-AE uses the control inputs together with the available attitude estimates, represented by the Euler angles yaw, pitch, and roll, as conditioning information, while reconstructing only the monitored attitude outputs. This asymmetric structure allows the residuals to capture inconsistencies between the commanded control effort and the observed attitude response, which is particularly relevant in closed-loop nonlinear systems where feedback compensation may attenuate fault signatures. Deviations from nominal behavior are detected through reconstruction residuals computed using a smoothed Mean Squared Error (MSE) criterion and evaluated against an adaptive $3\sigma$ threshold. The framework is validated in three-dimensional flight simulations considering abrupt, transient, and incipient actuator fault scenarios. The obtained results show that the proposed approach outperforms representative conventional machine-learning methods, achieving an average accuracy of 98.2%, an average recall of 97.8%, and an average false positive rate of 1.4%. These results suggest that the proposed hybrid algorithm provides an effective and interpretable solution for closed-loop fault diagnosis in nonlinear UAV systems under measurement noise and system variability. Full article

Incipient fault detection in industrial processes remains challenging, particularly for notorious faults 3, 9, and 15 in a chemical process benchmark, namely the Tennessee Eastman process (TEP). This paper proposes a novel unsupervised framework, namely self-modulated KAN-enhanced direct cross-attention (SMK-DCA). It constructs heterogeneous features by integrating raw data, process-aware features, and sliding-window singular values. Kolmogorov–Arnold networks (KAN) enhance nonlinear expressiveness before a cyclic DCA mechanism enables comprehensive interactions among heterogeneous features. A feature-wise linear modulation (FiLM) adaptively calibrates representations, while a sparse autoencoder with multi-target reconstruction amplifies subtle fault signatures. By leveraging KAN’s superior approximation capability and cyclic multi-view fusion, the proposed method effectively captures incipient fault-induced variations often overlooked by conventional approaches. Extensive experiments on TEP demonstrate that SMK-DCA effectively detects incipient faults 3, 9, and 15, while obtaining the best average detection rate across all faults among the compared MSPM and deep learning methods. Furthermore, validation on real-world data from an IGBT power system confirms the generalization capability of the proposed method across different industrial domains. Full article

This study addresses the problem of incipient fault detection in industrial processes by developing an enhanced dynamic inner principal component analysis (DiPCA) framework. This framework integrates a Transformer attention mechanism and a masked linear autoregressive moving average (ARMA) structure. In contrast to the original DiPCA, this approach can effectively characterize complex dynamic processes while maintaining the theoretical integrity of the original framework. Here, the sliding-window singular value decomposition is chosen to construct the dynamic feature matrix. The ARMA-Transformer network can capture the multi-step prediction features. A DiPCA-based dual monitoring system can then be used to establish dynamic and static residual statistics. The simulations of the Tennessee Eastman Process (TEP) demonstrate that the proposed method yields fault detection rates (FDRs) of 77.80% and 69.50% for incipient faults 3 and 9. These are higher than those of traditional DiPCA, ARMA, PCA, and DPCA by more than 40% on average. Validation on the Case Western Reserve University (CWRU) bearing dataset further shows an average FDR of 94.74% across 13 fault conditions. It thus offers an effective approach for early anomaly identification and safety monitoring in complex industrial processes. Full article

Reliable sensor fault detection is critical for the safe and efficient operation of complex industrial systems, such as thermal power plants. However, traditional data-driven methods and standard deep learning models often struggle to detect incipient gradual drift faults under severe environmental noise, primarily because they ignore the inherent physical correlations among multivariate sensor signals. To address this challenge, this paper proposes a novel Physics-Coupled Deep Long Short-Term Memory Autoencoder (PC-Deep-LSTM-AE). Specifically, we integrate a deep LSTM architecture with an explicit non-linear information compression bottleneck and layer normalization to enhance robust feature extraction in high-noise environments. Furthermore, we innovatively introduce a Physics-Coupling Loss (PCC Loss) that jointly optimizes the mean squared reconstruction error and the Pearson correlation coefficient, forcing the model to strictly preserve the dynamic physical relationships among multivariable signals. Extensive experiments were conducted on a real-world thermal power plant dataset with severe noise injection. The results demonstrate that the proposed PC-Deep-LSTM-AE achieves an outstanding F1-score of over 0.98, significantly outperforming mainstream baseline models, including Vanilla LSTM-AE, GRU-AE, Bi-LSTM-AE, and CNN-AE. The proposed method exhibits exceptional robustness and high interpretability for root-cause analysis, highlighting its immense potential for real-world industrial deployment. 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

This paper presents a unified framework for reliable motion control of permanent magnet linear motors (PMLMs) by integrating fault detection (FD) and fault-tolerant control (FTC). The framework combines a brain emotional learning-based intelligent controller (BELBIC) with a linear extended state observer (LESO) to enable rapid detection and mitigation of abrupt and incipient faults, as well as disturbances and sensor noise that degrade tracking accuracy and system reliability. The LESO is employed to estimate unknown dynamics and lumped disturbances and to generate residuals for reliable fault detection, while BELBIC provides adaptive and robust control actions without requiring prior knowledge of system parameters or explicit fault models. Extensive simulation studies under actuator faults, system dynamics faults, external disturbances, and measurement noise are conducted. Comparative evaluations with benchmark approaches demonstrate improved fault detection speed, tracking accuracy, and robustness of the proposed framework, highlighting its potential for enhancing reliability and operational continuity in high-precision industrial applications. Full article

With the advancement of intelligent manufacturing strategies, Cyber–Physical Production Systems (CPPSs) generate massive amounts of multidimensional, dynamic, and non-stationary data, posing significant challenges to real-time Process Monitoring. Existing anomaly detection methods often suffer from insufficient feature robustness when dealing with complex spatio-temporal dynamics, high computational complexity, and difficulties in effectively capturing incipient faults within deep topological structures. To address these issues, this paper proposes a Spatio-Temporal Variational Graph Statistical Attention Autoencoder (ST-VGSAE). First, the framework performs end-to-end multi-scale temporal decomposition via an Adaptive Lifting Wavelet Module, which enhances feature robustness while effectively suppressing noise. Furthermore, a spatio-temporal Token statistical self-attention mechanism with linear complexity is incorporated. By modulating local features via global statistics, it significantly reduces computational costs while enhancing anomaly discriminability. Experiments on the Tennessee Eastman (TE) process dataset demonstrate that the proposed model significantly outperforms state-of-the-art methods in key metrics such as the Fault Detection Rate and the False Alarm Rate, exhibiting superior noise robustness and real-time performance. Full article

Stator short-circuit faults (SSCFs) account for a significant portion of induction motor failures, yet their early detection remains a challenge in industrial environments where labeled fault data is scarce and installing additional sensors is often impractical. This paper proposes a novel, data-driven fault detection and diagnosis framework grounded in the Residual Information Value (RIV) principle to overcome reliability limitations of traditional spectral and residual energy methods. By redefining fault detection as a statistical test of independence between control inputs (voltages) and current residuals, the proposed method identifies incipient faults as model drifts without relying on prior knowledge of fault distributions. A key contribution of this work is the seamless integration of the diagnostic scheme into standard Variable Speed Drives (VSDs): the healthy nominal model (a Multilayer Perceptron) is trained exclusively using data from the drive’s existing self-commissioning routine, eliminating the need for manual data collection or complex physical parameter identification. Experimental validation on an industrial test bench demonstrates that the framework achieves superior diagnostic performance compared to traditional baselines, providing higher statistical separability and a reduced false alarm rate. The system can detect 1% incipient faults in approximately 61 ms while accurately identifying the faulty phase. The results confirm that the proposed RIV-based strategy offers a robust, non-intrusive, and industry-ready solution for predictive maintenance that effectively balances high-speed detection with enhanced statistical reliability. Full article

Early detection of fire-related risks in lithium-ion batteries (LIBs) remains a critical challenge, as conventional protection mechanisms typically activate only after irreversible degradation or macroscopic failure occurs. In this study, an innovative sensor-based diagnostic framework is proposed for proactive fire prediction in LIBs by simultaneously monitoring low-frequency and high-frequency electrical signatures generated during battery charge–discharge processes. An electromagnetic (EM) antenna sensor and a high-frequency current transformer (HFCT) sensor were employed to capture complementary voltage- and current-based transient signals associated with internal degradation phenomena. Cell-level experiments were conducted under various C-rates and temperature conditions, including high-stress environments, while module-level validation was performed on a 4-series, 1-parallel (4S1P) configuration at a 2C-rate under ambient temperature. Time–frequency characteristics of the measured signals were systematically evaluated using MATLAB-based continuous wavelet transform (CWT) and discrete wavelet transform (DWT) techniques. The results reveal that degradation-induced transient events exhibit non-stationary, impulsive voltage and current signatures with distinct frequency-band localization, which intensify with increasing C-rate, elevated temperature, and aging progression. At the module level, although signal amplitudes were partially attenuated due to current redistribution, characteristic wavelet energy patterns and time–frequency concentrations remained clearly distinguishable, demonstrating the scalability of the proposed approach. The combined EM antenna–HFCT sensing strategy, together with multi-resolution wavelet analysis, enables effective phenomenological differentiation between normal operational noise and incipient internal fault signatures well before conventional thermal or capacity-based indicators become evident. These findings demonstrate feasibility of the proposed method for early-stage fault diagnosis and highlight its potential applicability to advanced battery management systems for proactive fire prevention in large-scale energy storage and electric vehicle applications. Unlike conventional voltage-, temperature-, or gas-based diagnostics, the proposed approach enables the detection of incipient degradation phenomena at the microsecond scale by exploiting complementary low- and high-frequency electrical signatures. This study provides experimental evidence that wavelet-based EM and HFCT sensing can identify MISC-related precursors significantly earlier than conventional battery management indicators. Full article

Dynamic Wireless Power Transfer (DWPT) is emerging as critical smart city infrastructure for sustainable urban mobility, enabling electric vehicle charging while driving. However, DWPT introduces complex fault scenarios requiring intelligent monitoring. Existing fault diagnosis approaches for wireless power transfer systems face three key complexities: (1) they are limited to static charging with only 2–4 fault categories, failing to address the time-varying coupling dynamics and segmented coil handover transients inherent in dynamic charging; (2) they lack integration with the host distribution grid, ignoring grid-side disturbances that propagate to charging stations; and (3) they offer only reactive detection without predictive capability for incipient fault management. This paper presents a deep neural network (DNN)-based fault diagnosis framework utilizing multi-station sensor fusion for DWPT systems integrated with the IEEE 13-bus distribution network to address these limitations. The system monitors 36 sensor features across three charging stations, employing feature-level concatenation with station-specific normalization for multi-station fusion, achieving 97.85% classification accuracy across eight fault types. Unlike static charging, the framework explicitly models time-varying coupling dynamics due to vehicle motion, including segmented coil handover effects. A digital twin provides dual-horizon prediction: long-term forecasting (24–72 h) for incipient faults and real-time detection under 50 ms for critical protection, with fault probability outputs and ranked fault lists enabling actionable maintenance decisions. The DNN outperforms SVM (92.45%), Random Forest (94.82%), and LSTM (96.54%) with statistical significance ($p<0.001$), while maintaining model inference latency of 4.2 ms, suitable for edge deployment. Circuit-based analysis provides analytical justification for fault signatures, and practical parameter acquisition methods enable real-world implementation. Five case studies validate robustness across highway, urban, and grid disturbance scenarios with detection accuracies exceeding 95%. Full article

Three-phase induction motors (TIMs) are widely used in industrial applications, with bearings and rotors representing the most failure-prone components. Detecting incipient damage in these elements is particularly challenging. The associated signatures are weak and highly sensitive to variations, and their identification typically demands sophisticated filters, deep learning models, or high-cost sensors. In this context, the main goal of this work is to propose a new algorithm that reduces the dependence on such complex techniques while still enabling reliable detection of realistic faults using low-cost sensors. Therefore, the proposed Discriminative Band Energy Analysis (DBEA) algorithm operates on vibration signals acquired by low-cost accelerometers. The DBEA operates as a low-complexity filtering stage that is inherently robust to noise and variations in operating conditions, thereby enhancing discrimination among fault classes, without requiring neural networks or deep learning techniques. Moreover, the interaction of concurrent faults generates distinctive amplitude-modulated patterns in the vibration signal, making the AM demodulation-based algorithm particularly effective at separating overlapping fault signatures. The method was evaluated under a wide range of load and voltage conditions, demonstrating robustness to speed variations and measurement noise. The results show that the proposed DBEA framework enables non-invasive classification, making it suitable for implementation in compact and portable diagnostic systems. Full article

This paper presents OpS-EWMA-LLM (Operational State Shifts Detection using Exponential Weighted Moving Average and Labeling using Large Language Model), a hybrid framework that combines fleet-normalized statistical shift detection with LLM-assisted diagnostics to identify and interpret operational state changes across heterogeneous fleets. First, we introduce a residual-based EWMA control chart methodology that uses deviations of each component’s sensor reading from its fleet-wide expected value to detect anomalies. This statistical approach yields near-zero false negatives and flags incipient faults earlier than conventional methods, without requiring component-specific tuning. Second, we implement a pipeline that integrates an LLM with retrieval-augmented generation (RAG) architecture. Through a three-phase prompting strategy, the LLM ingests time-series anomalies, domain knowledge, and contextual information to generate human-interpretable diagnostic insights. Finaly, unlike existing approaches that treat anomaly detection and diagnosis as separate steps, we assign to each detected event a criticality label based on both statistical score of the anomaly and semantic score from the LLM analysis. These labels are stored in the OpS-Vector to extend the knowledge base of cases for future retrieval. We demonstrate the framework on SCADA data from a fleet of wind turbines: OpS-EWMA successfully identifies critical temperature deviations in various components that standard alarms missed, and the LLM (augmented with relevant documents) provides rationalized explanations for each anomaly. The framework demonstrated robust performance and outperformed baseline methods in a realistic zero-tuning deployment across thousands of heterogeneous equipment units operating under diverse conditions, without component-specific calibration. By fusing lightweight statistical process control with generative AI, the proposed solution offers a scalable, interpretable tool for condition monitoring and asset management in Industry 4.0/5.0 settings. Beyond its technical contributions, the outcome of this research is aligned with the UN Sustainable Development Goals SDG 7, SDG 9, SDG 12, SDG 13. Full article

A machine learning (ML) methodology for the robust detection and severity characterization of incipient gear faults under variable speed and load is postulated. The methodology is trained using vibration signals from a single accelerometer mounted on the gearbox, simultaneously acquired with tachometer signals at a sample of working conditions (WCs) from the range of interest. A special parametric identification procedure of gearbox dynamics that may account for the continuous range of WCs is introduced through ‘clouds’ of advanced stochastic data-driven Functionally Pooled models, estimated from angularly resampled vibration signals. Each cloud represents the gearbox dynamics at a specific fault severity level, while the pseudo-static effects of the WCs on the dynamics are accounted for through data pooling. Fault detection and severity characterization are achieved by testing the consistency of a vibration signal with each model cloud within a hypothesis testing framework in which the unknown load is also estimated. The methodology is assessed through 18,300 experiments on a single-stage spur gearbox including four incipient single-tooth pinion faults, 61 speeds, and four load levels. The faults produce no significant changes in the time-domain signals, while their frequency-domain effects overlap with the variations caused by the WCs, rendering the diagnosis problem highly challenging. The comparison with a state-of-the-art deep Stacked Autoencoder (SAE) demonstrates the ML method’s superior performance, achieving 95.4% and 91.6% accuracy in fault detection and characterization, respectively. Full article

Despite notable advances in load forecasting and fault detection, current power system operation and maintenance (O&M) technologies remain fragmented into independent and primarily reactive modules. Load forecasting estimates future demand, whereas fault detection identifies whether abnormal conditions exist in the present state. This paper proposes a unified and proactive Cognitive Digital Twin (CDT) system. Unlike traditional data-driven approaches, the CDT integrates Large Language Models (LLMs) and Knowledge Graphs (KGs) as cognitive cores to enable deeper reasoning and context-aware decision-making. The CDT system not only mirrors the physical grid but also acts as an intelligent O&M engine capable of understanding, reasoning, predicting, and self-diagnosing. The core innovation lies in prediction-based anomaly detection. The system first estimates the expected healthy state of the grid at future time steps and then compares real-time monitoring data against these predictions to identify incipient anomalies. This enables genuine foresight rather than simple reactive detection. By orchestrating advanced analytical modules, including CNN–LSTM hybrid models and optimization algorithms, the CDT supports autonomous O&M operations with transparent and explainable decision-making. These capabilities enhance grid resilience and improve the system’s capacity for self-healing. Full article