Machine learning based prediction of thermo-hydraulic performance in solar air heaters with phase change material and polygonal ribs
This study presents a machine learning (ML) framework to predict the thermal and airflow efficiency of solar air heaters (SAHs) enhanced with a polygonal ribbed absorber plate and phase change material (PCM). Using experimental data from varied mass flow rates of 0.062 kg s −1 , 0.028 kg s −1 , and 0.01 kg s −1 , an XGBoost model was trained to forecast thermo-hydraulic performance to achieve an R 2 of 95% precision against experimental test results. By replacing complex physical experiments with rapid ML predictions, this approach offers a cost-effective tool for optimising SAH designs, cost and simulation duration. The integration of PCM for heat storage (paraffin wax) and rib (Polygonal rib) induced turbulence improves energy retention while minimising pressure drops. The model demonstrates potential for rapid prediction capability, enabling dynamic adjustments to operating parameters, enhancing system thermal efficiency under fluctuating ambient conditions. This synergy of geometric innovation, thermal storage, and data-driven modelling underscores a scalable strategy to advance solar thermal technology, bridging thermal performance, affordability, and sustainability. The work aligns with global renewable energy targets by accelerating the deployment of efficient, low-carbon heating solutions through intelligent design optimisation .
Authors
- Artūras Kilikevičius (ORCID: https://orcid.org/0000-0002-4039-7300)
- Utku Kale (ORCID: https://orcid.org/0000-0001-9178-5138)
- M. Gnanasekaran
- Dhinesh Balasubramanian (ORCID: https://orcid.org/0000-0003-2687-9095)
- B. Varun Kumar
- P. Venkata Reddy
Institutions
- Obuda University (HU)
- University of Dubai (AE)
- Vilnius Gediminas Technical University (LT)
- Thiagarajar College of Engineering (IN)
- Lithuanian Maritime Academy (LT)
Publication Details
- Journal
- Journal of Thermal Analysis and Calorimetry
- Published
- 2026-11-21
- DOI
- https://doi.org/10.1007/s10973-026-16544-7
- Primary Topic
- Heat Transfer Mechanisms
- Type
- article
- Field-Weighted Citation Impact
- 0.00