A Review on Surface Defect Detection of Solar Cells Using Machine Learning

Solar cell, also known as photovoltaic (PV) cell, is a device that converts solar energy into electrical energy. A single solar cell produces approximately 2 watts of power, and by connecting multiple cells in an array, a solar module is formed which generates hundreds of kilowatts of power. However, if there is some defect in the solar module, then the power produced will be reduced. Therefore, it is very important to monitor the solar modules for any manufacturing defects or after installation faults as this may degrade the efficiency of the solar module. The manual inspection of the solar modules is a time-consuming process and is always not feasible, so there is a need of an automatic defect detection system for monitoring of solar modules. This review paper primarily focuses on the types of defects occurring in solar modules, different techniques based on machine learning for automated detection, classification of defective and non-defective solar cells, and performance comparison of the techniques employed.