Jul 2026· International Conference on Control, Decision and Information Technologies· pp. 879-885· 0 citations· 17 references
Abstract
This study develops a low-complexity data-driven method for real-time fault classification, and localization on a 20 kV radial feeder, while accounting for the computational and memory constraints of embedded hardware. The proposed approach is motivated by the changes introduced by distributed generation (DG), which alters fault-current behavior and reduces the reliability of conventional impedance-based protection. These limitations are mainly caused by reverse power flows and the additional infeed contribution from DG units during fault conditions. The proposed hybrid architecture processes time- and frequency-domain features, including symmetrical components and wavelet energy, through a dual-stage inference chain. The first stage uses a Random Forest classifier for fault-type identification, while the second stage uses a Multi-Layer Perceptron (MLP) distance estimator for fault localization. Evaluation on 23,778 MATLAB/Simulink fault scenarios, was performed using a grouped scenario-level holdout split to reduce overlap between training and test cases. The proposed approach reduces the localization error compared with the conventional impedance method, which produced errors exceeding 14 km under DG operation. The Random Forest classifier achieved 99.44% fault-type accuracy, and the MLP estimator reached a Mean Absolute Error (MAE) of 93.8 m, with localization accuracy of 99.51% within 1 km. Analytical resource profiling estimates less than 300 KB Flash and under 50 µs execution time, assuming a Cortex-M4F/M7-class target, pending hardware-in-the-loop validation.
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
The findings demonstrate that the proposed intelligent protection framework provides accurate and reliable fault detection, classification, and location through optimized DWT-based feature extraction and SVM-based decision making under the investigated simulation scenarios.
E. M. Shalby, A. Abdelaziz, Eman S. Ahmed et al.· Scientific Reports· 0 citations
This study proposes an artificial neural network-based approach for the detection and classification of faults occurring in high voltage alternating current (HVAC) power transmission lines. The study considers 12 classes comprising 11 fault types and one healthy state. Unlike traditional approaches that rely on extensive feature-extraction procedures, this study directly employs measured three-phase voltage, current, and phase-angle quantities as ANN inputs, thereby avoiding computationally intensive signal decomposition and handcrafted feature extraction stages. The model was evaluated using regression-oriented metrics, including mean squared error (MSE) and correlation coefficient (R). Furthermore, 5-fold cross-validation showed that the proposed ANN achieved better regression performance than GPR, SVR, and Kernel Regression models. Additional robustness analyses performed under different loading conditions and fault resistance values further demonstrated the generalization capability of the proposed ANN models under varying operating conditions. To evaluate the practical contribution of phase-angle information, a classification-based ablation study compared a 6-input ANN using only three-phase voltage and current measurements with a 12-input ANN including phase-angle measurements. Under identical test conditions, the 6-input and 12-input classifiers achieved accuracies of 88.51% and 84.73%, respectively, with macro F1-scores of 0.8789 and 0.8374. Repeated-training analysis further showed that the six-input configuration achieved higher mean performance and lower variability. The results indicate that phase-angle information provides supplementary and class dependent discriminative value, but does not consistently improve all fault classes. Conventional voltage and current measurements alone therefore represent a simpler and more stable alternative, whereas phase-angle measurements may be incorporated when synchronized phasor information is already available.
Zeynep Bala Duranay, İsmail Anıl Avcı, Mohammed Bushra Mohammed et al.· Symmetry· 0 citations
A practical, real-time arc fault detection system that integrates a comprehensive two-branch household dataset, lightweight handcrafted features, and classical machine learning for deployment on an STM32F407 microcontroller (MCU) and confirms its feasibility for low-cost, real-time protection devices.
Tan Tong Sy, Toan Le Duc, Dao Le Xuan et al.· E3S Web of Conferences· 0 citations
This paper presents a simulation-based analysis of fault detection in alternating current microgrids through data-driven methods. A detailed simulation-based microgrid model is created for conducting the fault analysis, including single phase ground fault, line fault, two phase fault and three phase fault situations. Simulations were carried out under different loading conditions and fault impedance values to obtain an extensive set of data containing voltage, current, and signal characteristics. This data was used to test the performance of various machine learning techniques for fault classification. The results show that the ensemble methods perform better than standalone models, with Random Forest (RF) demonstrating the highest classification performance. This findings of this research underscore the potential of data-driven techniques in improving the robustness and flexibility of AC protection systems in contemporary microgrids. Future work will focus on extending the analysis to more complex fault conditions and validating the proposed approach through real-time implementation.
Abdul Basit Taj, Sarosh Ali Shah Syed, Adnan Umar Khan et al.· International Journal of Ene...· 0 citations
With the large-scale integration of inverter-based resources (IBRs), the types and operating characteristics of power sources on both sides of transmission lines have changed significantly, rendering traditional fault-type selection methods inadequate. To address this, this paper proposes a neural network-based multi-parameter fault type identification strategy. The method constructs a 16-dimensional feature vector from local three-phase voltage/current magnitudes, phase angles, and zero-sequence components, and designs a lightweight fully-connected neural network with two hidden layers to learn the complex nonlinear mapping between these comprehensive inputs and fault types. Extensive training and testing data are generated using the PSCAD/EMTDC simulation platform, covering multiple scenarios including double-ended synchronous generator (SG), single-ended IBR, and double-ended IBR. The results show that the proposed strategy achieves identification accuracy exceeding 95% across all scenarios, significantly outperforming traditional current-based methods, especially in IBR-dominated cases. Moreover, the method exhibits strong robustness against variations in fault location, transition resistance, and source type, providing a reliable and adaptive protection solution for evolving hybrid power grids.
Luyun Zhang, Rui Xiong, Rui Hou et al.· International Conference on...· 0 citations