This Final Report outlines key lessons learnt from the project which looked at cost-effective ML-based approached to increase luminescence image spatial resolution. The project supports the development of cost-effective silicon solar cells through the development of automated inspection methods aimed at improving and speeding up fault classification and sorting processed currently used in solar cell manufacturing.
The overall aim of this project was to reduce the cost of characterisation tools and increase their throughput as traditional characterisation tools are slow and expensive to maintain. To overcome these problems, innovative techniques were developed. These methods are based on machine learning (ML) and luminescence images of solar cells. Since luminescence imaging systems are expected to be installed in >80% of production lines by 2029 and ML algorithms can be easily incorporated into inspection systems, the developed techniques can be efficiently installed in almost any production line.