Machine Learning-Based Fault Detection and Multi-Class Classification in Transmission Lines

Project Code :TCMAPY2311

Objective

The main objective of this project is to develop a machine learning-based system that efficiently detects and classifies faults in electrical transmission lines. The system aims to leverage multiple machine learning algorithms, including CatBoost, Decision Tree, XGBoost, Random Forest, and Support Vector Machine (SVM), to accurately classify different fault types based on the operational data of the transmission lines. By utilizing these algorithms, the project seeks to build a robust system that can automatically identify faults such as line-to-line, line-to-ground, and no faults, without requiring manual intervention. In addition to fault classification, the project incorporates Explainable AI (XAI) through LIME (Local Interpretable Model-agnostic Explanations) to make the model's predictions transparent and interpretable, thus ensuring that operators and decision-makers can understand the reasoning behind the system's classifications. Furthermore, the project aims to develop a user-friendly web interface using Flask, HTML, CSS, and JavaScript, allowing users to easily interact with the system and access the fault detection results. The objective is to provide an efficient, scalable, and reliable solution for fault detection in transmission lines, with potential applications in power grid monitoring and automated maintenance systems.

Abstract

Electrical fault detection in transmission lines is crucial for maintaining the reliability and efficiency of power distribution systems. This project explores the application of machine learning algorithms to detect and classify various fault types in transmission lines. The system uses multiple algorithms, including CatBoost, Decision Tree, XGBoost, Random Forest, and Support Vector Machine (SVM), to analyze fault data. The dataset used for training the models consists of operational parameters of transmission lines, with different fault scenarios represented. The system utilizes LIME for Explainable AI (XAI) to provide transparency and interpretability in the model's decision-making process. By analyzing the input features and explaining the predictions, the system helps users understand the reasoning behind the fault classification, thereby improving trust in the results. The goal is to build an efficient and reliable model for automatic fault detection that enhances the safety and operation of transmission lines. The system is developed using Python, Flask, and front-end technologies such as HTML, CSS, and JavaScript. It is designed to be scalable, easy to use, and effective in classifying faults accurately. This approach enables early detection of faults and can contribute to the development of automated systems for power grid management.

Keywords: Machine Learning, Fault Detection, Transmission Lines, CatBoost, Decision Tree, XGBoost, Random Forest, SVM, LIME, Explainable AI.

NOTE: Without the concern of our team, please don't submit to the college. This Abstract varies based on student requirements.