Experimental results on stator inter-turn faults across multiple low-load operating conditions demonstrate superior reconstruction performance compared with representative recurrent, transformer-based, and graph-based autoencoder models while maintaining computational efficiency suitable for low-latency deployment.
Abstract
Early fault detection and fault severity assessment are essential for ensuring the reliable operation of induction motors. While stator winding faults can often be identified through current-based monitoring techniques, reliable characterization of fault severity remains challenging, particularly for incipient faults under low-load operating conditions. To address this problem, this study proposes a low-latency fault diagnosis framework that combines healthy-only anomaly detection with multi-level fault severity assessment. At its core, an Energy-Modulated Transformer Autoencoder (EM-TransAE) is developed to model healthy operating behavior by incorporating instantaneous current energy into the self-attention mechanism. The framework adopts a two-stage learning strategy. First, EM-TransAE is trained exclusively on healthy data within a one-class learning paradigm, where fault detection is performed through reconstruction-error-based anomaly assessment. The proposed model achieves a reconstruction error of 0.000484, indicating high-fidelity representation of healthy operating conditions. Second, encoder-derived latent features and reconstruction error are combined to form a diagnostic feature set for XGBoost-based multi-level fault severity assessment, achieving an accuracy of 96.93%. To support practical deployment, the framework is integrated within an edge-based streaming architecture for real-time operation. Experimental results on stator inter-turn faults across multiple low-load operating conditions demonstrate superior reconstruction performance compared with representative recurrent, transformer-based, and graph-based autoencoder models while maintaining computational efficiency suitable for low-latency deployment.
Rapid and accurate fault detection in high-voltage transmission networks is essential for grid reliability and equipment protection. Transmission fault datasets are frequently imbalanced, and certain fault types produce electrical signatures that fall within the normal operating envelope, causing single-model classifiers to fail on safety-critical cases. This paper proposes a hybrid two-stage machine learning pipeline that decouples detection from classification. Stage 1 combines an Isolation Forest anomaly detector with an optional supervised binary detector through an OR-fusion rule; the supervised branch is allocated automatically during training for any fault class the anomaly detector cannot resolve, and is omitted when no such class exists. Stage 2 applies a Random Forest multiclass classifier only to samples flagged by Stage 1. Feature engineering is expressed as a per-measurement-point operator mapping six raw channels to eighteen features, including zero-sequence symmetrical components derived from Fortescue's theorem, yielding 18L features for L measurement points. On the TLFaultDataset, the pipeline raises Line-fault end-to-end accuracy from 31.3% to 95.8%. On an independent single-point dataset, the same framework attains 97.25% end-to-end accuracy across all classes including normal operation, exceeding the TLFed federated benchmark of 94.84% without GPU or federated infrastructure, at 0.05 ms per sample on CPU. Ablation on both datasets shows zero-sequence features resolving the three-phase versus three-phase-to-ground ambiguity, raising the F1-score of that class pair from 0.39 to 0.997. The direction of the zero-sequence signature is found to be system-dependent, motivating a learned decision boundary in place of a fixed relay threshold.
Sahil Manikshete, A. Gujarathi, Thanh Long Vu et al.· 0 citations
Inverter-based resources and IEC 61850 process-bus measurements introduce new protection challenges, including nontraditional fault behavior and measurement-domain cyber-physical attacks. This paper evaluates DL-Xformer, an attention-based Transformer classifier for multi-class fault and cyberattack diagnosis, side-by-side with Dynamic State Estimation-Based Protection (DSE-EBP) on identical high-fidelity electromagnetic-transient (EMT) streaming measurements from an IBR-rich power grid. The evaluation uses an 18-class taxonomy covering normal operation, 11 physical faults, and six measurement-domain attacks, including CT/PT ratio manipulation and GPS spoofing, sampled at 4.8 kHz from synchronized upstream and downstream merging units. DSE-EBP detects all streaming anomalies in 0.417-1.660 ms, with a mean detection time of 0.756 ms, while DL-Xformer classifies the same events in 2.50-50.42 ms, with a mean classification time of 13.46 ms. The longest delay occurs in a deliberate stress case where a CT ratio attack is introduced while residual oscillations from a preceding DLG fault have not fully settled; the event-window accuracy drops to 76.1 %, but the stable final classification remains correct. Measurement-level feature attribution shows that the DL-Xformer decision is driven by physically meaningful current and voltage channels at the attacked measurement location. Together, the two methods motivate a layered protection architecture for next-generation inverter-dominated smart grids.
Emad Abukhousa, Saman A. Zonouz, A. P. S. Meliopoulos· 0 citations
Accurate and fast fault detection is essential to ensure the stability and reliability of High Voltage AC (HVAC) transmission systems. Conventional protection methods, including impedance-based and traveling wave techniques, may exhibit reduced performance under noisy operating conditions, system uncertainties, and complex fault scenarios while often requiring separate approaches for fault classification, location detection, and stability assessment. This paper proposes a unified Artificial Neural Network (ANN) based framework for simultaneous fault classification, location detection, and stability assessment using Critical Clearing Time (CCT) within a single HVAC transmission line model. A detailed MATLAB Simulink model is developed to generate a structured dataset comprising twelve fault scenarios, including single-line, double-line, three-phase, and ground faults at different locations along the transmission line. Three-phase voltages and currents, along with zero-sequence components, are used as input features. The ANN model is trained using the Levenberg–Marquardt (LM) optimization algorithm, which was comparatively evaluated against Bayesian Regularization (BR) and Scaled Conjugate Gradient (SCG) and demonstrated faster convergence, lower prediction error, and higher regression accuracy. To further evaluate the robustness of the proposed framework under high-impedance fault conditions, supplementary simulations were performed using fault resistance values of 10 Ω and 50 Ω in addition to the baseline 0.01 Ω case. The resulting datasets were combined to form an expanded training and evaluation dataset, enabling comprehensive validation of the proposed LM-trained ANN under varying fault resistance conditions. Using the baseline dataset, the proposed framework achieved a high regression coefficient (R = 0.9882) and low mean squared error (MSE = 0.1386), demonstrating accurate fault classification and precise per-kilometer fault location estimation. Furthermore, the integration of fault inception time and duration enables direct computation of CCT, allowing the model to distinguish between stability-critical and non-critical fault conditions. The results confirm that the proposed framework provides a comprehensive and efficient solution for real-time fault analysis by combining classification, localization, temporal analysis, and stability-aware decision support within a single model.
Nazmun Nahar Karima, M. Hazari, Shameem Ahmad et al.· Energies· 0 citations
Early and reliable diagnosis of inter-turn short-circuit (ITSC) faults is critical to maintaining the reliability, availability, and safe operation of doubly fed induction generators (DFIGs) used in wind energy conversion systems (WECSs). Incipient winding faults are particularly challenging to identify because their electrical signatures can be masked by the inherent spectral complexity of DFIG operation and variations in wind and operating conditions. This study proposes a hybrid Fast Fourier Transform-Adaptive Neuro-Fuzzy Inference System (FFT–ANFIS) diagnostic framework for the detection, localization, and severity assessment of ITSC faults in both stator and rotor windings. The proposed approach employs the FFT method to extract fault-sensitive harmonic components from stator-current signals, which are subsequently used as diagnostic features by an Adaptive Neuro-Fuzzy Inference System (ANFIS). By integrating spectral feature extraction with nonlinear neuro-fuzzy classification, the proposed framework provides an efficient and interpretable mechanism for distinguishing healthy and faulty operating conditions and assessing fault severity. The methodology is evaluated using MATLAB/Simulink simulations under healthy and multiple ITSC fault conditions with different fault locations and severity levels. The results demonstrate 100% classification accuracy for stator faults, rotor faults, and multiple short-circuit (MSC) fault conditions, together with near-zero prediction error in fault-severity estimation. These results confirm the high discriminative capability of the selected FFT-based spectral features and the effectiveness of ANFIS in establishing the nonlinear relationship between fault signatures and fault conditions. In addition, the proposed framework maintains low computational complexity and is therefore suitable for real-time condition-monitoring applications. Compared with existing diagnostic approaches, the proposed method provides a unified framework for multi-fault diagnosis while combining high diagnostic accuracy, computational efficiency, and interpretable decision-making. The proposed FFT–ANFIS framework consequently offers a practical approach for early fault detection and condition-based maintenance of DFIG-based wind turbines, with the potential to reduce unplanned downtime, maintenance requirements, and energy-production losses.
M. Abid, S. Laribi, M'hamed Larbi et al.· Algorithms· 0 citations
Arc faults in low-voltage smart-farm distribution systems are difficult to detect reliably because normal current waveforms vary with load composition and operating conditions. This paper presents a progressive three-stage time–frequency learning framework that identifies series arc faults directly from normalized current waveforms. In Stage I, fast Fourier transform (FFT)-based and wavelet-based learnable front-ends independently learn complementary global spectral and local transient representations. In Stage II, their representation spaces are structured using supervised contrastive learning with view-level and cross-spectrum alignment. In Stage III, the aligned feature extractors are frozen, and only the feature fusion block and final classifier are trained for 10-class classification. Current signals are acquired from a practical smart-farm distribution system and evaluated using a measurement-session-level group-wise split. The framework achieves 99.92% accuracy and 99.93% macro recall while maintaining 1.06 M parameters and a model-only inference latency of 8.70 ms. The results demonstrate that the proposed framework provides robust discrimination across unseen measurement sessions within the evaluated load categories and operating conditions.
Seoyoung Jeon, Won-Kyu Choi, Sungsoo Kwon et al.· Italian National Conference...· 0 citations
Induction motors are central to industrial processes, yet their unexpected failure incurs significant production losses and maintenance costs. Motor Current Signature Analysis (MCSA) is a well-established non-intrusive technique for identifying electrical and electromechanical faults via frequency-domain analysis of the stator current. However, manual spectral interpretation remains challenging under low signal-to-noise conditions and variable operating regimes. This paper presents a complete, reproducible framework integrating physics-based simulation, interpretable feature engineering, and lightweight machine learning for real-time supply-fault diagnosis. A three-phase squirrel-cage induction motor is modelled in MATLAB/Simulink to validate MCSA sideband signatures under healthy, phase-loss, and voltage-imbalance conditions. A cost-effective test bench equipped with an ACS712 Hall-effect sensor and an Arduino UNO microcontroller acquires stator current data from 15 independent acquisition runs, yielding a balanced dataset of 1440 fixed-length windows (480 per class). All experiments are conducted under no-load conditions (slip $\approx \mathbf{0. 0 2})$, which represents a conservative lower bound on in-service performance since sideband energy grows with load-induced slip. A 1024-sample Hann-windowed FFT extracts an eight-dimensional feature vector combining frequency-domain indicators and time-domain statistics. Random Forest and XGBoost classifiers are evaluated under random-window and leakage-controlled group-aware protocols. Under the group-aware split, XGBoost achieves 91.3% (±1.4%) accuracy and a macro-F1 of $\mathbf{9 0. 7 \%}(\mathbf{\pm 1. 6 \%})$; Random Forest achieves $\mathbf{8 9. 6 \%}(\mathbf{\pm 1. 8 \%})$ accuracy and a macro-F1 of 88.4% (±2.1%). A McNemar test confirms the performance gap between classifiers is statistically significant $(\mathbf{p}<\mathbf{0. 0 5})$. An explicit offline-real-time benchmark reports end-to-end latency (280-295 ms), fault-to-alarm detection delay (~1.8 s), and false-alarm behaviour under a persistence-rule controller, bridging the gap between dataset-level accuracy and embedded deployment constraints.
Sara Sghiouri, H. Sabir, Mohamed Bezza et al.· IEEE International Conferenc...· 0 citations