DEVELOPMENT OF FAULT LOCATION ON POWER SYSTEM TRANSMISSION LINE USING FUZZY LOGIC APPROACH

This study focuses on the development and implementation of an intelligent system for fault identification, classification, and location in power transmission lines using artificial intelligence techniques. The increasing complexity of modern power systems, coupled with the challenges of slow and inaccurate fault detection in conventional protection schemes, necessitates the adoption of more efficient and reliable methods. In this work, Artificial Neural Networks (ANN) combined with multi-resolution analysis (MRA) based on wavelet transform were employed to enhance the speed and accuracy of fault detection and localization. The study utilized data obtained from the simulation of the Nigerian 330kV Ikeja West–Benin transmission line model. Voltage and current signals generated under different fault conditions were processed using MATLAB software. These signals were decomposed into detailed and approximation coefficients through wavelet transform, and the extracted features were used as inputs for training, testing, and validating the neural network model. The dataset was divided into 60% for training, 20% for testing, and 20% for validation. Various fault types, including single line-to-ground, line-to-line, double line-to-ground, and three-phase faults, were analyzed. The developed ANN model demonstrated the capability to identify and classify faults effectively, although some limitations were observed in achieving the desired training performance threshold. Despite this, the results indicate that AI-based approaches, particularly neural networks, provide a more efficient alternative to conventional impedance-based fault detection methods. The study concludes that the integration of artificial intelligence techniques into power system protection can significantly improve fault detection speed, accuracy, and system reliability. It is recommended that further research be conducted on advanced neural network architectures and optimization algorithms to enhance performance and applicability in real-world power systems.