Intelligent Design of an Ultra-Thin Near-Ideal Multilayer Solar Selective Absorber Using Grey Wolf Optimization linked to Deep Learning

Abstract

This study explored the development of an optimal effective solar absorber by leveraging recent advancements in artificial intelligence and nanotechnology. A predictive computational approach for designing a multilayer metal-dielectric thin film solar selective absorber, specifically the SiO 2 /Cr/SiO 2 /Cr/SiO 2 /Cu structure was proposed. The adopted approach integrates the transfer matrix method (TMM) as a predictive electromagnetic tool and combines it with the swarm-based heuristic algorithm grey wolf optimization (GWO) linked to machine learning algorithms, specifically the artificial neural network (ANN). Through dynamic modeling and rigorous testing against multiple static versions, the adopted approach demonstrates exceptional predictive performance with an value of 0.999. The results obtained using this novel GWO-ANN approach reveal near-perfect broadband absorption of 0.996534 and low emission of 0.194170594 for the designed thin film structure. These outcomes represent a significant advancement in photo-to-thermal conversion efficiency, particularly for a working temperature of 500 C and a solar concentration of 100 suns, showcasing its potential for practical applications across various fields. Additionally, the designed structure meets the stringent thermal stability requirements necessary for current Concentrated solar power (CSP) projects. This emphasizes its suitability for integration into existing CSP systems and highlights its potential to contribute to advancements in solar energy technology.