Enhancing photovoltaic cell design with multilayer sequential neural networks: A study on neodymium-doped ZnO nanoparticles

Abstract

Multilayer sequential neural networks, a powerful machine learning model, demonstrate the ability to learn intricate relationships between input features and desired outputs. This study focuses on employing such models to design photovoltaic cells. Specifically, neodymium (Nd)-doped ZnO nanoparticles (NPs) were utilized as a photoanode for fabricating dye-sensitized solar cells (DSSCs). A natural dye extracted from Spinacia oleracea was employed, while two types of electrolytes, liquid and gel (polyethylene glycol-based), were used for comparative analysis. Extensive material characterization of the photoanode highlights the impact of Nd content on the physicochemical properties of ZnO. Notably, when the doped photoanode and gel electrolyte were combined, a substantial 110% improvement in power conversion efficiency (PCE) was achieved. Building on these findings, the machine learning model in this research accurately predicts the current-voltage (I-V) curve values for such photoanodes, with an impressive accuracy of 98%. Additionally, the model illuminates the significance of variables like crystal distortion, texture coefficient, and doping concentration, underscoring their importance in the context of photovoltaic cell design.

Keywords

• Machine learning
• DSSC-type solar cells
• Nd-doped ZnO
• Optoelectronic properties
• Gel electrolyte