Solarix

Abstract

Solar panel efficiency is crucial for sustainable energy production, as any fault or obstruction in the panel can significantly reduce energy output. To ensure optimal performance and detect potential issues, real-time monitoring of solar panels is essential. Traditional methods often rely on manual inspections, which are time- consuming and prone to human error. Therefore, an automated system for detecting solar panel faults is necessary.This project proposes a machine learning-based solution for solar panel fault detection and classification using Convolutional Neural Networks (CNN). The system consists of two models: one for detecting the presence of solar panels and another for classifying faults into categories such as "Bird-drop," "Dusty," "Electrical-damage," "Physical-Damage," and "Snow-Covered." The solution is designed to process real-time video streams from a camera, continuously updating the predictions on the user interface. Additionally, detected faults are stored in a database for further analysis

KEYWORDS: Solar Panel Fault Detection, Convolutional Neural Networks (CNN), Machine Learning, Image Processing, Real-time Monitoring, Solar Panel Efficiency.