Thermal Image and Inverter Data Analysis for Fault Detection and Diagnosis of PV Systems

Abstract

The world’s energy demand is on the rise, leading to an increased focus on renewable energy options due to global warming and rising emissions from fossil fuels. To effectively monitor and maintain these renewable energy systems connected to electrical grids, efficient methods are needed. Early detection of PV faults is vital for enhancing the efficiency, reliability, and safety of PV systems. Thermal imaging emerges as an efficient and effective technique for inspection. On the other hand, evidence indicates that monitoring inverters within a solar energy farm reduces maintenance expenses and boosts production. Optimizing the efficiency of solar energy farms necessitates comprehensive analytics and data on every inverter, encompassing voltage, current, temperature, and power. In this study, our objective was to perform two distinct fault analyses utilizing image processing techniques with thermal images and machine learning techniques using inverter and other physical data. The results show that hotspot and bypass failures on the panels can be detected successfully using these methods.

Keywords

• PV panels
• diagnosis
• fault detection
• thermal image
• machine learning