DESIGN OF A SOLAR PANEL INSPECTION AND ANOMALY DETECTION SYSTEM
Abstract
ABSTRACT
The wide adoption of Solar energy through photovoltaic (PV) technology highlights the need for efficient maintenance and fault detection systems to ensure optimal performance and longevity of solar panels. This project presents an autonomous system leveraging deep learning and Internet of Things (IoT) technologies for inspection and automated detection of anomalies in solar panels. A deep learning model is trained to classify solar panels such as clean, cracked, electrically damaged, and hotspot affected. The system employs an ESP32 microcontroller interfaced with high-resolution and infrared cameras to capture real-time images of the panels. These images, along with geolocation data, are transmitted to the cloud for further processing. Utilizing a Python-based environment and the SqueezeNet deep learning model, the images are analysed for defects. The results are then transmitted back to a local display interface for immediate visualization of the panel's condition. This system offers a cost-effective, scalable solution for real-time monitoring and fault detection in PV arrays, aiming to reduce downtime and maintenance costs while enhancing the overall efficiency of solar energy systems.
Full-Text Access Notice
In accordance with the NERD Policy on promoting peer-reviewed publication, public access to the full text of a project, thesis or dissertation is restricted for three years, allowing the author and supervisors sufficient time to pursue peer-reviewed publication.
During this period, researchers with legitimate academic or research purposes may request authorisation directly from the author to enable NERD to release the indexed full texts of the work using the form below.