Improving efficiency and stability of improved circular solar photovoltaic structures via multi-directional functionally graded materials: A computer simulation validated by hybrid machine learning algorithm and experimental datasets

The enhancement of solar photovoltaic (PV) structures remains a critical area of research for improving energy efficiency and structural stability. This study investigates the role of multi-directional functionally graded materials (FGMs) in optimizing the performance of circular solar PV systems. A...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Materials today communications Ročník 46; s. 112816
Hlavní autori: Han, Simeng, Li, Jialing
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier Ltd 01.06.2025
Predmet:
Circular solar photovoltaic structure
Computer simulation
Hybrid machine learning algorithm
Multi-physics simulation
Poroelasticity
Zigzag theory
Circular solar photovoltaic structure
Computer simulation
Multi-physics simulation
Poroelasticity
Zigzag theory
Hybrid machine learning algorithm
ISSN:2352-4928, 2352-4928
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:The enhancement of solar photovoltaic (PV) structures remains a critical area of research for improving energy efficiency and structural stability. This study investigates the role of multi-directional functionally graded materials (FGMs) in optimizing the performance of circular solar PV systems. A computational simulation approach is adopted to model the impact of FGMs on thermal, mechanical, and electrical properties. To ensure the reliability of the simulation outcomes, a hybrid machine learning (ML) algorithm is employed, integrating experimental datasets for validation. The ML framework refines predictive accuracy by combining supervised learning techniques with experimental data-driven optimization. The results indicate that the application of FGMs significantly improves power output, enhances thermal resistance, and reinforces structural integrity under varying environmental conditions. Additionally, the hybrid ML validation demonstrates strong correlation with empirical findings, reinforcing the feasibility of the proposed material design approach. This research highlights the potential of FGMs in next-generation solar energy systems, offering a pathway for the development of high-performance PV structures with enhanced operational lifespan. The study contributes to advancing computational modeling and machine learning integration in renewable energy research, providing a robust methodology for optimizing solar PV technologies. Future work will focus on further experimental validation and scalability assessments for industrial applications. The findings provide valuable insights into the design of more efficient and durable solar PV systems, paving the way for innovative advancements in sustainable energy technologies. [Display omitted]
ISSN:2352-4928
2352-4928
DOI:10.1016/j.mtcomm.2025.112816