To meet global market demands, it will remain important to further scale up photovoltaics (PV) production. During the production of solar cells, several defects can occur. Current approaches in quality inspection are reaching their speed limits. This thesis project evaluates the feasibility of faster quality inspection by using deep learning-based computer vision (CV) algorithms to detect production defects without human supervision at high speeds. The goal is to achieve this while reducing the necessary manual efforts to label (annotate) defects in the training data of such algorithms.

The second goal of the project is to investigate in which ways and to which extent this innovation can impact the sustainability performance of the solar cell production process. Multiple scenarios are investigated using a Life Cycle Assessment (LCA) model. The results are used to estimate the potential large-scale impact of increasing solar cell production throughput.