Abstract
It is shown how at Q CELLS, interpretable machine learning algorithms are used to understand the energy conversion efficiencies of mass‐produced Q.ANTUM solar cells based on p‐type Czochralski silicon (Cz‐Si) wafers. For this end, the data of a 1 week ramp‐up of over half a million cells acquired utilizing our TRA.Q single‐wafer‐tracking system are used. These consist of over 300 single information points per cell and feature inline measurements, path‐ and tool‐related information, process data as well as the final I–V characteristics. In the analysis, using machine learning algorithms, it is focused on understanding how the many different input features influence the solar cell efficiency over time by using additive feature impacts. As sources of variation are spread over several features, special attention is paid to correlated features in a hierarchical clustering approach. Finally, with the model achieving a high Pearson's coefficient of correlation of 0.84 between true and predicted values for the holdout validation data set, subtle hourly cell efficiency fluctuations in the order of 0.01%abs are explained. Features are identified which are relevant for short‐term changes in the efficiency and others which influence the efficiency on a general level and do not show temporal changes.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.