Optimizing red chili drying using machine learning modelling of solar vent and open-air drying with seasonal performance analysis
Case Studies in Thermal Engineering · 2025-11 · 75 · 107074
DOI: 10.1016/j.csite.2025.107074 ↗Kurz gefasst
Fachartikel in der Zeitschrift Case Studies in Thermal Engineering, 2025-11. Verfasst von N. Rajamurugu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
The increasing global energy demand, driven by population growth and industrial expansion, underscores the urgent need for energy conservation and sustainable alternatives to mitigate greenhouse gas emissions and climate change. This study investigates heat- and mass-transfer dynamics during the drying of red chillies in a cabinet dryer, analyzing drying kinetics at varying temperatures, evaluating effective moisture diffusivity, and identifying the optimal machine learning model for performance prediction. Experiments compared open-air drying (OAD) and solar vent drying (SVD), with SVD demonstrating superior efficiency, removing moisture two to three times faster than OAD. Notably, SVD achieved 15-40% higher moisture removal on early summer mornings and up to 95% during winter afternoons. Machine learning models, including Random Forest (RF), Multilayer Perceptron (MLP), and Radial Basis Function (RBF), were employed to predict drying performance, assessed using RMSE, MAPE, and R 2 metrics. RF emerged as the most robust model, outperforming MLP (R 2 : 0.91-0.94) and RBF (R 2 : 0.90-0.92), with superior generalization (R 2 : 0.93-0.94) for both moisture removal and drying efficiency. These findings highlight the potential of SVD combined with RF modeling to enhance sustainable drying practices.
Zitieren
APA
Rajamurugu, N., Srimanickam, B., Elangovan, K., Srividhya, S., Poorani, B., Krishnamoorthy, R., & Minh, N. V. (2025). Optimizing red chili drying using machine learning modelling of solar vent and open-air drying with seasonal performance analysis. Case Studies in Thermal Engineering, 75, 107074. https://doi.org/10.1016/j.csite.2025.107074
Vancouver
Rajamurugu N, Srimanickam B, Elangovan K, Srividhya S, Poorani B, Krishnamoorthy R, et al. Optimizing red chili drying using machine learning modelling of solar vent and open-air drying with seasonal performance analysis. Case Studies in Thermal Engineering. 2025;75:107074. doi:10.1016/j.csite.2025.107074
BibTeX
@article{Rajamurugu2025,
author = {Rajamurugu, N. and Srimanickam, B. and Elangovan, K. and Srividhya, S. and Poorani, B. and Krishnamoorthy, R. and Minh, Nguyen Van},
title = {Optimizing red chili drying using machine learning modelling of solar vent and open-air drying with seasonal performance analysis},
journal = {Case Studies in Thermal Engineering},
year = {2025},
volume = {75},
pages = {107074},
doi = {10.1016/j.csite.2025.107074}
}
EUVIMED