Search Results (377)

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

The presence of non-stationary features poses a major challenge to root cause diagnosis in industrial processes, as they can distort fault propagation paths inferred through causal testing. To address this issue, an adaptive moving-window dual-test Granger causality framework is proposed for non-stationary industrial processes. First, a dual non-stationary test mechanism, which integrates the Augmented Dickey–Fuller and Kwiatkowski–Phillips–Schmidt–Shin tests, is developed to assess the stationarity of process variables. Next, an adaptive moving-window strategy is designed to adjust window lengths based on the non-stationarity test results. Time series are then segmented according to the selected windows, and a vector error-correction model is fitted to provide a robust basis for causal testing. Subsequently, Granger causality tests are conducted within each window to capture the true causal relationships among variables. Finally, window-wise scores are aggregated to identify the root cause and infer the fault propagation path. The proposed framework is evaluated on the Tennessee Eastman Process, and the results demonstrate that it effectively improves the accuracy of root cause diagnosis. Full article

In offshore wind farms, modular multilevel converters (MMCs) may operate under a deloading condition to accommodate wind-speed volatility and dispatch constraints. Here, deloading is defined as transmitted power < 0.2 pu (scenario S2, low-power non-reversal). Under this condition, submodule capacitor-voltage fault signatures are weak and exhibit strong operating-point-dependent drift, which degrades conventional threshold-based or offline-trained methods. We propose a lightweight switch-level IGBT open-circuit fault localization framework for deloaded MMCs. Wavelet packet decomposition is used to extract time–frequency energy features, and principal component analysis reduces feature dimensionality for lightweight deployment. An enhanced XGBoost model further integrates severity-index weighting to alleviate class imbalance and incremental learning to adapt to condition drift induced by wind-power fluctuations. MATLAB2024b/Simulink results show 99.6% accuracy in S2 with less than 2 ms inference latency, and robust performance in extended scenarios including partial-power operation and power reversal. Full article

A tool-health digital twin for CNC predictive maintenance is developed and operationalised as a fusion-and-state-estimation core that produces a latent tool-health trajectory (wear level and wear-rate dynamics) from multi-rate sensor streams for diagnosis and remaining useful life (RUL) forecasting under strict edge latency constraints. The scope is tool-health–informed maintenance decisions (condition-based tool replacement/scheduling), rather than a comprehensive maintenance twin for all CNC subsystems. Multi-rate vibration, spindle-current, and temperature signals are synchronized and windowed, and a linear state-space model with Kalman filtering and innovation-guided adaptive noise estimation stabilizes the latent health state across operating-regime changes. The fused state is then used by compact sequence learners, an LSTM for edge feasibility, and a compact Transformer as a higher-accuracy comparison, to output fault categories and RUL estimates. Predictive uncertainty is quantified via a Monte Carlo dropout and linked to reliability-aware actions through a simple alarm/defer/schedule policy, while SHAP provides feature-level interpretability. On a CNC testbed, fusion improves fault F1 from 0.811 to 0.892 and PR-AUC from 0.867 to 0.918 while reducing RUL RMSE from 10.4 to 8.1 cycles; the compact Transformer reaches 0.903 F1 and 7.9-cycle RMSE at higher inference time. The end-to-end pipeline remains within a ≤100 ms breakdown, maintains in-band innovation statistics, supports rehearsal-based updates under drift, and is additionally evaluated on external tool-wear and turbofan datasets. Full article

Accurate prediction of contact temperature in disconnectors is critical for early fault detection. However, purely physics-based models face difficulties in parameter identification, while purely data-driven models often suffer from error accumulation in long-term forecasting. To address these challenges, this paper proposes a novel framework named Hybrid Physics-Informed Long Short-Term Memory (Hybrid-PI-LSTM). Firstly, this paper mathematically formulates the transient heat transfer process as a constrained optimization problem governed by a nonlinear ordinary differential equation (ODE), embedding physical laws into the loss function as a regularization term to promote dynamic consistency. Secondly, to address the inverse problem of parameter drift caused by environmental changes, an Adaptive Parameter Updating (APU) mechanism is introduced. This algorithm utilizes a gradient-based iterative approach to dynamically estimate equivalent physical coefficients (e.g., heat capacity) from observational residuals during inference. Finally, numerical experiments on a real-world dataset demonstrate that the proposed framework significantly outperforms baseline models. Specifically, it achieves a Root Mean Squared Error (RMSE) of 0.283 at a 720-step forecasting horizon, reducing the prediction error by over 35% compared to static-parameter physical models. The results indicate that the proposed adaptive constraint mechanism contributes to enhanced long-term numerical stability and physics-guided parameter tracking. Full article

To address the challenges commonly encountered in civil aircraft operating under multi-mode, strongly coupled closed-loop control—namely scarce fault samples, pronounced distribution shift, and root-cause explanations that are easily confounded by covariates—this paper proposes a root-cause analysis method that integrates ensemble learning with constraint-guided reasoning by large language models (LLMs). First, for Full Authority Digital Engine Control (FADEC) monitoring sequences, a feature system comprising environment-normalized ratios, mechanism-informed mixing indices, and multi-scale temporal statistics is constructed, thereby improving cross-mode comparability and enhancing engineering-semantic expressiveness. Second, in the anomaly detection stage, a cost-sensitive LightGBM model is adopted and a validation-set-based adaptive thresholding strategy is introduced to achieve robust identification under highly imbalanced fault conditions. Furthermore, for Root Cause Analysis (RCA), a “computation–reasoning decoupling” framework is developed: Shapley Additive exPlanations (SHAP) are used to generate segment-level contribution evidence, while causal chains, engineering prohibitions, and structured output templates are injected into prompts to constrain the LLM, enabling it to infer root-cause candidates and produce structured explanations under mechanism-consistency constraints. Experiments on real flight data demonstrate that our method yields an anomaly detection F1-score of 0.9577 and improves overall RCA accuracy to 97.1% (versus 62.3% for a pure SHAP baseline). Practically, by translating complex high-dimensional data into actionable natural language diagnostic reports, the proposed method provides reliable and interpretable decision support for rapid RCA. Full article

Artificial intelligence technology offers an intelligent and efficient new pathway for bearing fault diagnosis, holding significant importance for ensuring the stable operation of industrial systems. However, bearing fault samples are scarce in industrial practice, and traditional data-driven methods exhibit a marked decline in diagnostic performance under conditions of small sample sizes. To address this, this paper proposes a few-shot bearing fault diagnosis method that integrates an Improved Generative Adversarial Network with a CNN-BiLSTM-Attention hybrid network. The method comprises three core stages: in the data augmentation stage, a class-center-constrained Least Squares Generative Adversarial Network (CCC-LSGAN) model featuring class center constraint and joint loss optimization is proposed to generate high-quality fault samples through frequency-domain feature constraints, effectively expanding the training data; in the feature learning stage, a one-dimensional Convolutional Neural Network, Bidirectional Long Short-Term Memory, and Attention hybrid network (1D-CNN-BiLSTM-Attention) hybrid base classifier is constructed, which combines multi-scale convolution, bidirectional temporal modeling, and attention mechanisms to fully extract the spatiotemporal features of vibration signals; in the inference stage, test-time noise augmentation and a multi-model weighted voting ensemble mechanism are introduced to enhance the robustness and generalization capability of the diagnosis. Experimental results based on the PU and CWRU public bearing datasets demonstrate that the proposed method significantly outperforms existing mainstream diagnostic approaches in core metrics, including accuracy, precision, recall, and F1 score. It achieves a diagnostic accuracy of 96.60% on the PU dataset and 98.58% on the CWRU dataset. This method verifies the feasibility of highly reliable diagnosis under few-shot conditions and provides an effective solution for the intelligent operation and maintenance of industrial equipment. Full article

Quantum error correction is a prerequisite for quantum computing; however, the performance critically depends on the accuracy of the decoding algorithm. To address these challenges, we propose a hybrid decoding architecture, BP + UF + BP. The protocol initiates with a truncated global BP stage to extract probabilistic gradients without requiring full convergence. This soft information guides a reliability-based Union-Find (UF) algorithm to prioritize high-likelihood error mechanisms. Finally, a local subgraph BP refinement maximizes correction accuracy. Numerical simulations on rotated surface codes under circuit-level depolarizing noise demonstrate a fault-tolerance threshold of approximately 0.72%. This significantly outperforms standard Minimum Weight Perfect Matching (MWPM) and Union-Find (UF) baselines. Notably, our method significantly reduces the logical error rate compared to the conventional decoders. With its empirically near-linear scaling under fixed iteration, the proposed architecture presents a scalable solution for real-time fault-tolerant quantum computing. Full article

Knowledge graph completion via link prediction is critical for intelligent equipment maintenance systems to support accurate fault diagnosis and maintenance decision making. However, existing approaches struggle to simultaneously capture local structural dependencies and perform effective multi-hop reasoning due to limited receptive fields or inefficient path exploration mechanisms. Traditional path-based methods implicitly assume path symmetry, treating all reasoning chains equally without considering their task-specific relevance. To address this issue, we propose a Graph Attention Network (GAT)-guided semantic path reasoning framework that breaks this symmetry through attention-driven asymmetric weighting, integrating local structural encoding with global multi-hop inference. The key innovation lies in a target-guided biased path sampling strategy, which transforms GAT attention weights into probabilistic transition biases, enabling adaptive exploration of high-quality semantic paths relevant to specific prediction targets. GATs learn importance-aware local representations, which guide biased random walks to efficiently sample task-relevant reasoning paths. The sampled paths are encoded and aggregated to form global semantic context representations, which are then fused with local embeddings through a gating mechanism for final link prediction. Experimental evaluations on FB15k-237, WN18RR, and a real-world equipment maintenance knowledge graph demonstrate that the proposed method consistently outperforms state-of-the-art baselines, achieving an MRR of 0.614 on the maintenance dataset and 0.485 on WN18RR. Further analysis shows that the learned path attention weights provide interpretable asymmetric reasoning evidence, enhancing transparency for safety-critical maintenance applications. Full article

Anomaly detection has been a challenging subject in many industrial fields. In industrial machinery such as hydraulic excavators, sensor data distributions are inherently multimodal because different operating conditions produce distinct sensor signatures, and conventional algorithms struggle to establish clear normal–abnormal boundaries when these conditions are mixed. We propose an action-state decomposition framework that partitions multimodal sensor data into homogeneous subsets based on discretized control inputs, thereby reducing the ambiguity of normal–abnormal boundaries by learning state-conditional distributions. The approach comprises a reactive method that evaluates each sample within its action state, and a history-based method that incorporates temporal context from previous action states. This decomposition is algorithm-agnostic and can improve detection performance across diverse anomaly detection algorithms. The framework is further extended to Bayesian fault diagnosis that identifies the root cause of failures using action-state-conditional detection probabilities. Experiments on simulated excavator data and two real-world benchmark datasets (UCI Hydraulic Systems and SKAB) demonstrate the generalizability of the proposed mode decomposition and provide insights into factors that may influence its effectiveness. The history-based method achieves a mean AUC of 0.89 across sensor fault types, outperforming all baseline algorithms, and the Bayesian fault diagnosis achieves 86.7% accuracy in identifying the root cause among six action fault types. For the proposed GMM-based methods, the decomposition also substantially reduces per-sample inference time by approximately 10× (from 8.68 μs to 0.75 μs), enabling real-time deployment in industrial settings. Full article

Nuclear power plant (NPP) fault diagnosis is critical to ensure the safe, stable and economic operation of nuclear facilities. Existing deep learning-based NPP fault diagnosis methods primarily extract features from the temporal and spatial domain. Given recent advances in frequency-domain learning and lightweight models for time-series modeling, this paper proposes a frequency-domain learning-based fault diagnosis method for multi-modular high-temperature gas-cooled reactor (mHTGR) modules. It extracts temporal and spatial frequency-domain features using a lightweight complex-valued neural network (CVNN), which are then applied for fault classification and severity estimation. Under typical fault detection tasks for an mHTGR, comparative experiments verify that the proposed method outperforms existing methods that utilize long short-term memory (LSTM) and graph neural networks (GNNs) for spatiotemporal feature extraction in terms of classification accuracy, mean squared error (MSE) loss, and inference time. Full article

Hydraulic systems are pivotal components in safety-critical aerospace and industrial applications, making reliable health monitoring essential. However, traditional data-driven diagnosis methods typically rely on static graph structures that fail to capture evolving sensor correlations during different fault modes. Furthermore, existing grid-based models often struggle to extract multi-resolution features and maintain performance under data-limited conditions. To address these challenges, this paper proposes a novel Dynamic Multi-Scale Graph Neural Network (DMS-GNN) for hydraulic system fault diagnosis. The framework integrates a hierarchical multi-scale feature extraction module to capture diverse fault signatures across different frequency bands. Crucially, a self-attention-based dynamic graph learner is introduced to adaptively infer latent sensor topologies end-to-end, eliminating the reliance on predefined physical connections. Experimental validation on a dedicated electro-hydraulic test bench demonstrates that the proposed DMS-GNN achieves a superior diagnostic accuracy of 98.47%, outperforming state-of-the-art baselines such as GraphSAGE, Static GCN, and GAT. The result confirms the efficacy of combining multi-scale temporal learning with dynamic spatial reasoning for robust multi-sensor fusion diagnosis. Full article

Real-time processing demands for massive IoT sensor data necessitate reliance on distributed microservice systems within edge clusters. However, pinpointing the root cause of anomalies within these edge microservice clusters poses a critical challenge for intelligent IoT operation and maintenance. To address the issue, a spatio-temporal graph propagation model ST-GraphRCA is proposed for root cause analysis in IoT edge environments. Our approach begins by resolving the fundamental issue of time-series asynchrony across distributed multi-source metrics. A PCA-DTW hybrid feature extraction method is introduced with a dynamic alignment strategy to mitigate the effects of random network delays and data deformation without requiring prior synchronization. Subsequently, ST-GraphRCA constructs a stream-based forward propagation graph based on the flow conservation principle. By integrating dynamic edge weights with node-level input–output anomaly scores, ST-GraphRCA precisely infers fault propagation pathways and identifies potential root cause candidates through causal reasoning. Finally, a topology-constrained high-utility mining algorithm filters these candidates. Using a constraint matrix, the algorithm filters out unreachable service combinations to locate low-frequency and high-risk root causes. Experimental results indicate that ST-GraphRCA achieves an F1-Score of 0.89, outperforming existing methods. In resource-constrained edge scenarios, its average localization time is merely 238.8 ms, representing a six-fold improvement over key benchmarks. Thus, ST-GraphRCA not only provides an efficient anomaly fault tracing solution for large-scale IoT systems but also offers technical support for the intelligent operation and maintenance of distributed microservice systems. 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

Photovoltaic (PV) systems nowadays represent an essential component of renewable energy production. However, undetected faults often compromise their reliability, leading to significant energy losses and high maintenance costs. Existing deep learning approaches for PV fault diagnosis have achieved high accuracy, but they require massive, labeled datasets and high computational resources, which make them unsuitable for real-time applications. This paper proposes a lightweight, self-supervised hybrid learning framework for real-time PV fault diagnosis to address these limitations. First, the dataset is split into training, testing, and validation subsets. Thereafter, weighted class calculation steps are performed to overcome the issue of imbalance in the data. Then, a self-supervised pre-training phase is established to enable the encoder to produce effective internal representations prior to the implementation of a supervised fine-tuning classifier, characterized as a lightweight feed-forward network (Dense–Dropout–Dense Softmax), which will be trained using categorical cross-entropy and fault-type labels. Finally, a supervised fine-tuning stage is employed based on the pre-trained hybrid CNN–transformer encoder to perform PV fault classification. The experimental results indicate that the proposed approach outperforms existing models by achieving an overall accuracy of 99.8%, a recall of 99.6%, and an outstanding specificity of 100%. The confusion matrix demonstrates that classification is excellent on all operating types. Runtime analysis indicates that the model processes each sample in 2.78 ms and requires 0.07 MB to store weights of 19,429 parameters, confirming its suitability for real-time deployment. These findings highlight that using a hybrid CNN–Transformer encoder with self-supervised learning can improve fault detection and classification performance while significantly reducing inference time, making it an effective and efficient solution for intelligent PV system monitoring. Full article