THERMAL IMAGE-BASED FAULT DETECTION IN SOLAR PV SYSTEMS USING MACHINE LEARNING FOR GRID EFFICIENCY ENHANCEMENT

In India, there are three major sources of power: wind, coal, and solar energy. Among these, solar energy is considered more efficient due to its renewable nature, vast availability, and low environmental impact. As India pushes for sustainable energy solutions, solar power that is increasingly being integrated into the national grid. Faults and Failures in solar PV cells cause major power issues. Traditional methods of fault detection involved manual inspections or basic thermal analysis, which were slow, error-prone, and not always effective at identifying problems before they worsened. So, to overcome above problems, this work adopted Machine learning-driven thermographic image classification is a modern approach that enhances the efficiency of solar photovoltaic (PV) systems by automating fault detection. This technique uses machine learning algorithms to analyse thermal images of PV systems, identifying issues like panel defects or overheating, which can reduce overall system performance. With this approach, the performance and lifespan of solar power systems can be optimized, ensuring they operate at their full potential and contribute effectively to India’s growing energy needs. Additionally, the use of this technology leads to cost savings by preventing major system.