Artificial neural network-based modelling of compensated multi-crystalline solar-grade silicon under wide temperature variations

In recent years, multi-crystalline solar grade silicon (mc-SoG-Si), instead of expensive electronic-grade Si, is being considered in photovoltaic industry for production of solar modules. These materials usually contain a comparable amount of acceptors (e.g. boron) and donors (e.g. phosphorus) and are therefore called compensated mc-SoG-Si. The electrical parameters, e.g. majority carrier mobility (μ), majority carrier density (p) and resistivity (ρ), of compensated mc-SoG-Si which affect performance of the solar cells vary non-linearly with temperature due to several complex mechanisms. In this study, the authors propose artificial neural network (ANN)-based models to predict the three electrical parameters of mc-SoG-Si material. Using a limited amount of measurement data, the authors have shown that the ANN-based models can predict the three electrical parameters of a given sample over a wide temperature range of 70-400 K and a specific range of compensation ratio. The authors have shown with extensive simulated results that these models can predict the three parameters with a maximum error of ±10%.