Design investigation on 100 μm-thickness thin silicon PERC solar cells with assistance of machine learning. (January 2022)

• Record Type: Journal Article
• Authors: Zhu, Heng; Yan, Wensheng; Liu, Yiming; Hu, Die; Tu, Yiteng; Huang, Zhengtao; Tan, Xinyu
• Is Part Of: Materials science in semiconductor processing. Volume 137(2022)
• Publication Date: 2022-01
• Subjects: Solar cells -- Passivated emitter and rear cell (PERC) -- Optical and electrical designs -- Machine learning -- Multilayer perceptron algorithm; Semiconductors -- Periodicals; Integrated circuits -- Materials -- Periodicals; Semiconducteurs -- Périodiques; Circuits intégrés -- Matériaux -- Périodiques; Electronic journals; 621.38152
• DOI: 10.1016/j.mssp.2021.106198
• Languages: English
• ISSNs: 1369-8001

Abstract

Abstract: Thin crystalline silicon passivated emitter and rear cell (PERC) solar cells are a very prospective technology for next-phase photovoltaic development due to the potential of high cost effectiveness. The reduction of silicon wafer thickness can significantly save the costs, but there is a loss of cell efficiency if cell design is not conducted. For the thinned 100 μm-thickness PERC solar cells without design, the efficiency loss is pronounced from commercial 180 μm-thickness. In this paper, we have designed and optimized SiO2 /SiNx /SiNx /SiOx thin films (here two SiNx layers have different refractive index) on the front surface and SiNx /SiOx thin films on the back surface for the standard front single-sided textured PERC cells. Based on this, we further design and investigate the case of double-sided textured PERC solar cells. Compared with the reference cell, the present designs can lead to the short-circuit current density increase by 0.6 mA/cm 2 and the open-circuit voltage enhancement by 10 mV for the front textured case, which causes the efficiency gain of 0.7% from 21.6% to 22.3%. For the double-sided textured cells, the efficiency has an extra increase of 0.6% from 22.3% to 22.9%. Finally, we have constructed the efficiency prediction model by using the multilayer perceptron algorithm in machine learning. It is found from the SHAP values that a significant effect of the front SiNx thickness is observed to predict the performance of the PERC cells. Highlights: Structural design of thin PERC solar cells. Optical and electrical designs to solve the efficiency loss problem. The efficiency is significantly improved to 22.9%. Use machine learning to investigate the efficiency prediction model.