Enhancing solar photovoltaic modules quality assurance through convolutional neural network-aided automated defect detection

Detecting cracks in solar photovoltaic (PV) modules plays an important role in ensuring their performance and reliability. The development of convolutional neural networks (CNNs) has introduced a game-changing dimension in the detection of defects in PV modules. This paper proposes an automated defect detection method for PV, by leveraging custom-designed CNN to accurately analyse electroluminescence (EL) images, identifying defects such as cracks, mini-cracks, potential induced degradation (PID), and shaded areas. The proposed system achieves a high level of validation accuracy of 98.07%, reducing manual inspection demands, enhancing quality standards, and saving costs. The system was validated in a case study for PV installations faulty with PID, where it identified all defective modules with a high degree of precision of 96.6%, surpassing existing methods. This methodology holds promise for revolutionizing PV industry quality control, improving module reliability, and supporting sustainable solar energy growth.