Experimental investigation of solar PVT collector with the dryer on mass and temperature of dried red chili with Machine Learning Models

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27230%2F25%3A10258967" target="_blank" >RIV/61989100:27230/25:10258967 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.sciencedirect.com/science/article/pii/S2590123025018985?via%3Dihub" target="_blank" >https://www.sciencedirect.com/science/article/pii/S2590123025018985?via%3Dihub</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.rineng.2025.105827" target="_blank" >10.1016/j.rineng.2025.105827</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Experimental investigation of solar PVT collector with the dryer on mass and temperature of dried red chili with Machine Learning Models

Popis výsledku v původním jazyce

The growing demand for efficient drying methods in agricultural processes has motivated researchers to explore hybrid systems using photovoltaic and thermal systems. One challenge faced in this research was the limited amount of drying days and dealing with one crop (red chilies), which could limit the potential application for other crops. The kinetics of drying red chilies with a photovoltaic thermal (PVT) system were in combination with a dryer, and the objective was to enhance the drying process of red chilies under various environmental conditions of surface glazing temperature, solar radiation, the temperature of the outflow fluid, and ambient temperature. Three drying techniques open sun drying, forced convection drying, and natural convection drying with varying flow velocities served as the foundation for the research. Using this controlled case-study method, 3 kg of red chilies were dried under standard sun radiation from an ambient temperature of 31 degrees C to a high of 58 degrees C. The moisture content reduction process was measured by starting with 79 % moisture content by weight after drying the red chilies for a total of six days conducting the experiments between 9am and 4pm during Mars, April, and May 2023, each time on clear days with direct sunlight. The drying process was stop at 11 % moisture content after 6-day testing round of red chilies drying. Machine learning (ML) models, namely the Multilayer Perceptron (MLP), Radial Basis Function (RBF), and Decision Tree (DT), were used to forecast the temperature and mass dryness variables.The RBF model showed the best performance with 0.98, 0.95, and 0.92 for temperature dryness, above MLP and DM. The research finds that the RBF model had the highest capacity to forecast drying efficiency and that forced convection drying is more effective than open solar drying.

Název v anglickém jazyce

Experimental investigation of solar PVT collector with the dryer on mass and temperature of dried red chili with Machine Learning Models

Popis výsledku anglicky

The growing demand for efficient drying methods in agricultural processes has motivated researchers to explore hybrid systems using photovoltaic and thermal systems. One challenge faced in this research was the limited amount of drying days and dealing with one crop (red chilies), which could limit the potential application for other crops. The kinetics of drying red chilies with a photovoltaic thermal (PVT) system were in combination with a dryer, and the objective was to enhance the drying process of red chilies under various environmental conditions of surface glazing temperature, solar radiation, the temperature of the outflow fluid, and ambient temperature. Three drying techniques open sun drying, forced convection drying, and natural convection drying with varying flow velocities served as the foundation for the research. Using this controlled case-study method, 3 kg of red chilies were dried under standard sun radiation from an ambient temperature of 31 degrees C to a high of 58 degrees C. The moisture content reduction process was measured by starting with 79 % moisture content by weight after drying the red chilies for a total of six days conducting the experiments between 9am and 4pm during Mars, April, and May 2023, each time on clear days with direct sunlight. The drying process was stop at 11 % moisture content after 6-day testing round of red chilies drying. Machine learning (ML) models, namely the Multilayer Perceptron (MLP), Radial Basis Function (RBF), and Decision Tree (DT), were used to forecast the temperature and mass dryness variables.The RBF model showed the best performance with 0.98, 0.95, and 0.92 for temperature dryness, above MLP and DM. The research finds that the RBF model had the highest capacity to forecast drying efficiency and that forced convection drying is more effective than open solar drying.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

20301 - Mechanical engineering

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Results in Engineering

ISSN

2590-1230

e-ISSN

—

Svazek periodika

27

Číslo periodika v rámci svazku

Neuveden

Stát vydavatele periodika

NL - Nizozemsko

Počet stran výsledku

9

Strana od-do

nestránkováno

Kód UT WoS článku

001523253700015

EID výsledku v databázi Scopus

—