Pattern Recognition-Based Fault Detection in Power Systems Using Bayesian Neural Networks

Description:

This dataset contains electrical power system measurements for automated fault detection and classification.

It provides voltage and current signal patterns representing normal and fault.

The dataset supports the development and evaluation of machine learning models for power-system fault analysis.

It is suitable for pattern recognition, fault classification, and Bayesian neural network-based prediction.

Input: Three-phase voltage and current signals.

Output: Normal and fault classes.

Tags:

#PowerSystems #FaultDetection #FaultClassification #BayesianNeuralNetwork #PatternRecognition #DeepLearning

References:

1. Gunda, S. K. (2026, January). An exploration of adaptive ensemble approaches in software fault detection: Balancing accuracy and robustness. In AIP Conference Proceedings (Vol. 3345, No. 1, p. 020211). AIP Publishing LLC.

2. Bukhari, S. B. A., Albalawi, H., Wadood, A., & Alatwi, A. M. (2026). Deep learning-driven fault detection and classification in microgrids using Temporal Convolutional Network. Computers and Electrical Engineering, 129, 110777.