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

Institutions

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
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Machine learning based prediction of thermo-hydraulic performance in solar air heaters with phase change material and polygonal ribs

Artūras Kilikevičius, Utku Kale, M. Gnanasekaran, Dhinesh Balasubramanian et al.
Journal of Thermal Analysis and Calorimetry
Heat Transfer Mechanisms
article

Machine learning based prediction of thermo-hydraulic performance in solar air heaters with phase change material and polygonal ribs

Artūras Kilikevičius, Utku Kale, M. Gnanasekaran, Dhinesh Balasubramanian, B. Varun Kumar, P. Venkata Reddy
article en

Abstract

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 .

Journal of Thermal Analysis and Calorimetry
Obuda University (HU), University of Dubai (AE), Vilnius Gediminas Technical University (LT), Thiagarajar College of Engineering (IN), Lithuanian Maritime Academy (LT)
Heat Transfer Mechanisms
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon