Advance Research in Power Electronics and Devices https://matjournals.net/engineering/index.php/ARPED <p><strong>ARPED</strong> is a peer-reviewed journal in the field of Electronics Engineering published by MAT Journals Pvt. Ltd. ARPED is a print e-journal focused on the rapid publication of fundamental research papers on all areas of Power Electronics and Devices. Power electronics is the application of solid-state electronics for the control and conversion of electric power. It also refers to a subject of research in electronic and electrical engineering which deals with design, control, computation and integration of nonlinear, time-varying energy processing electronic systems with fast dynamics. The Journal aims to promote high-quality research, review articles, and case studies on semiconductors, fault-tolerant control strategies in power electronic converters, Diodes, Thyristors, Transistors, Analysing various types of converters, Understanding the Applications of power electronic circuits.</p> MAT Journals Pvt. Ltd. en-US Advance Research in Power Electronics and Devices Machine Learning-based Power Estimation and Fault Detection in VLSI Circuits https://matjournals.net/engineering/index.php/ARPED/article/view/2566 <p><em>This study explores the application of Machine Learning (ML) techniques in the domain of Very Large-Scale Integration (VLSI) circuits, specifically focusing on power estimation and fault detection. Traditional methods of power estimation and fault detection require extensive simulations and manual inspections, making them time-consuming and computationally expensive. This study proposes a data-driven approach utilizing ML models to predict power dissipation and classify faulty circuits efficiently. A dataset with key VLSI parameters, such as transistor count, clock frequency, voltage, temperature, current, power dissipation, propagation delay, fanout, and noise margin, is generated and analyzed. Two ML models, a linear regression model for power estimation and a decision tree classifier for fault detection, are implemented and evaluated. The results demonstrate that ML-based techniques provide an efficient and accurate alternative to conventional VLSI analysis methods. </em></p> K. Sujitha D. Arun Kumar Copyright (c) 2025 Advance Research in Power Electronics and Devices 2025-10-15 2025-10-15 1 7