首页|New Machine Learning Study Findings Recently Were Reported by Researchers at Zur ich University of Applied Sciences (Identifying Performance Limiting Parameters In Perovskite Solar Cells Using Machine Learning)
New Machine Learning Study Findings Recently Were Reported by Researchers at Zur ich University of Applied Sciences (Identifying Performance Limiting Parameters In Perovskite Solar Cells Using Machine Learning)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators publish new report on Ma chine Learning. According to news reporting originating in Winterthur, Switzerla nd, by NewsRx journalists, research stated, "Herein, it is shown that machine le arning (ML) methods can be used to predict the parameter that limits the solar-c ell performance most significantly, solely based on the current density-voltage (J-V) curve under illumination. The data (11'150 J-V curves) to train the model is based on device simulation, where 20 different physical parameters related to charge transport and recombination are varied individually." Financial supporters for this research include Horizon 2020, European Union (EU), ZHAW digital in the framework of a DIZH fellowship. The news reporters obtained a quote from the research from the Zurich University of Applied Sciences, "This approach allows to cover a wide range of effects tha t could occur when varying fabrication conditions or during degradation of a dev ice. Using ML, the simulated J-V curves are classified for the changed parameter with accuracies above 80%, where Random Forests perform best. It t urns out that the key parameters, short-circuit current density, open-circuit vo ltage, maximum power conversion efficiency, and fill factor are sufficient for a ccurate predictions. To show the practical relevance, the ML algorithms are then applied to reported devices, and the results are discussed from a physics persp ective. It is demonstrated that if some specified conditions are met, satisfying results can be reached. The proposed workflow can be used to better understand a device's behavior, e.g., during degradation, or as a guideline to improve its performance without costly and time-consuming lab-based trial-and-error methods. Machine learning (ML) methods are used to predict the most limiting parameter o f perovskite solar cells' performance, solely based on the current-voltage curve . With simulation tools, 20 different physical parameters related to charge tran sport and recombination are varied individually. The simulated current-voltage c urves are classified by ML for the changed parameter, with accuracies above 80% ."
WinterthurSwitzerlandEuropeCyborgsEmerging TechnologiesMachine LearningZurich University of Applied Sciences
NETL
NSTL
