PhD Scholarship in AI-Assisted Monitoring and Inspection of Solar Photovoltaic Power Plants Using Aerial Imagery

This PhD scholarship focuses on developing autonomous methods for fault or anomaly detection and classification of photovoltaic (PV) power plants with high accuracy for monitoring large-size PV power plants. The research contributes to computer vision, machine learning, robotics and optimization methods for automating fault/anomaly detection and cleanliness checks for PV systems using visual and thermal images captured by drones. Objectives include various types of inspection such as detecting hot spots, glass breakage, soiling and cleanliness checks. The research will investigate techniques to obtain overall status of operational PV arrays and identify specific PV strings or modules for detailed analysis. Methods will be developed for fault detection and classification, automating inspection procedures including detecting soiling over panels, evaluating cleanliness conditions for efficient cleaning cycles, and detecting damage to solar panels like hot spots and large cracks. The research draws from state-of-art computer vision and machine learning methods to interpret photovoltaic solar farm conditions and perform various inspections and anomaly detection.