Journal of Research in Electrical Circuits and Systems ISSN: 3139-2059 (Online)

Abstract

Fault detection in electrical circuits is crucial for maintaining system reliability and preventing catastrophic failures. Traditional fault diagnosis methods are often slow and inefficient, especially in complex electrical systems. This paper explores the use of machine learning (ML) techniques for fault detection and diagnosis in electrical circuits. A variety of supervised and unsupervised ML algorithms, including decision trees, support vector machines (SVM), and neural networks, are applied to identify and classify faults in various circuit topologies. The study provides a detailed comparison of these algorithms in terms of accuracy, computational efficiency, and scalability. Real-time data from sensors embedded in circuits are used to train and test the ML models. The results demonstrate that ML techniques can significantly enhance fault detection accuracy and reduce diagnostic times.

Keywords: Fault detection, machine learning, decision trees, support vector machines, neural networks