What question did this study set out to answer?

To estimate and classify fault resistance in 11kV distribution networks using machine learning while ensuring noise robustness.

June 20, 2026Open Access

Fault Resistance Estimation and Classification in 11kV Distribution Networks with Noise Robustness: A Machine Learning-Based Multi-Fault Analysis

Key Points

To estimate and classify fault resistance in 11kV distribution networks using machine learning while ensuring noise robustness.
Developed a high-fidelity Simscape Power Systems model in MATLAB/Simulink for fault simulations.
Conducted a Monte Carlo simulation generating 5000 fault scenarios with varying resistances.
Trained and benchmarked Gradient Boosting, Random Forest, and Support Vector Machine models for regression and classification tasks.
Gradient Boosting regressor achieved an RMSE of 0.0276 ohm and R² of 1.0000 on a test set of 1000 samples.
Random Forest classifier demonstrated 99.90% accuracy for fault severity classification.
Multi-fault-type extension achieved 100% fault-type identification accuracy across seven fault configurations with R² > 0.996.

Abstract

This paper presents an exhaustive machine learning model for fault resistance estimation and classification in 11kV distribution networks. In MATLAB/Simulink, a high-fidelity Simscape Power Systems model is built around an 11kV, 30 MVA source connected to two 100km PI-section transmission lines, a midpoint-fault bus, and a downstream 1 MVA, 11kV/0.4kV transformer—Monte Carlo simulation. An automated Monte Carlo simulation is used to generate a dataset of 5000 Phase-A single-line-to-ground fault scenarios, with fault resistances uniformly distributed from 0.01 to 50 ohm. Three-phase voltage and current waveforms are extracted and converted into 20 physical, interpretable time-domain features. Three machine learning models — Gradient Boosting (GB), Random Forest (RF), and Support Vector Machine (SVM) — are trained and benchmarked on both regression and classification tasks. The Gradient Boosting regressor achieves a root mean square error (RMSE) of 0.0276 ohm and an R 2 of 1.0000 on a held-out test set of 1000 samples. In contrast, the Random Forest classifier achieves 99.90 per cent accuracy for fault severity classification. The noise-robustness analysis at signal-to-noise ratios (SNRs) between 10 and 50 dB shows that RF is more favourable for use in noisy environments, with an RMSE of 0.96 ohm and 96.72 per cent accuracy at SNR = 50 dB. A multi-fault-type extension to seven fault configurations (AG, BG, CG, ABG, BCG, AB, ABCG) over 3500 simulations demonstrates 100% fault-type identification accuracy and per-type regression R-squared exceeding 0.996 for all fault types. These results establish a robust, simulation-driven machine-learning pipeline suitable for deployment in adaptive protection and fault-management systems.

Read Full Paperexternally

Ask AI

Mark Helpful

Bookmark

Relay

View Full Paper