A Deep Learning Approach for Automated Fault Detection on Solar Modules Using Image Composites

Aerial inspection of solar modules is becoming increasingly popular in automatizing operations and maintenance in large-scale photovoltaic power plants. Current practices are typically time-consuming as they make use of manual acquisitions and analysis of thousands of images to scan for faults and anomalies in the modules. In this paper, we explore and evaluate the use of computer vision and deep learning methods for automating the analysis of fault detection and classification in large scale photovoltaic module installations. We use convolutional neural networks to analyze thermal and visible color images acquired by cameras mounted on unmanned aerial vehicles. We generate composite images by overlaying the thermal and visible images to investigate improvements in detection accuracy of faint features related to faults on modules. Our main goal is to evaluate whether image processing with multiwavelength composite images can improve both the detection and the classification performance compared to using thermal images alone. The hypothesis is that fusion of images acquired at different wavelengths (i.e., thermal infrared, red, green, and blue visible ranges) would enhance the multi-wavelength representation of faults and thus their histogram feature signatures. The results showed a successful detection and localization of faint fault features using composite images. However, the classification of the fault categories did not show significant improvements and needs continued investigation. This research represents a step towards the design of robust automated methods to improve fault detection from airborne images. Further work is still necessary to reach a classification accuracy comparable with the performance of human experts.