Thermal anomalies detection in a photovoltaic plant using artificial intelligence: Italy case studies

Abstract

This paper proposes the application of artificial intelligence techniques for the identification of thermal anomalies that occur in a photovoltaic system due to malfunctions or faults, with the aim to limit the energy production losses by detecting faults at an early stage. The proposed approach is based on a Thermographic NonDestructive Test conducted with Unmanned Aerial Vehicles equipped with a thermal imaging camera, which allows the detection of abnormal operating conditions without interrupting the normal operation of the PV system rapidly and cost-effectively. The thermographic images and videos are automatically inspected using a Convolutional Neural Network, developed by an open-source tool. The developed system was applied to 4 PV plants in northern Italy, with a total size of 1.2 MWp, detecting the layout of thermal anomalies with an accuracy ok 100% thanks to the pre-processing procedure used by the authors. The proposed methodology enables non-expert users to inspect the PV modules and results in a 98.3% reduction in manual image inspection time.