Machine Learning for Prediction of Heat Pipe Effectiveness
This paper details the selection of machine learning models for predicting the effectiveness of a heat pipe system in a concentric tube exchanger. Heat exchanger experiments with methanol as the working fluid were conducted. The value of the angle varied from 0° to 90°, values of temperature varied...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-04-01
|
Series: | Energies |
Subjects: | |
Online Access: | https://www.mdpi.com/1996-1073/15/9/3276 |
_version_ | 1797504999561887744 |
---|---|
author | Anish Nair Ramkumar P. Sivasubramanian Mahadevan Chander Prakash Saurav Dixit Gunasekaran Murali Nikolai Ivanovich Vatin Kirill Epifantsev Kaushal Kumar |
author_facet | Anish Nair Ramkumar P. Sivasubramanian Mahadevan Chander Prakash Saurav Dixit Gunasekaran Murali Nikolai Ivanovich Vatin Kirill Epifantsev Kaushal Kumar |
author_sort | Anish Nair |
collection | DOAJ |
description | This paper details the selection of machine learning models for predicting the effectiveness of a heat pipe system in a concentric tube exchanger. Heat exchanger experiments with methanol as the working fluid were conducted. The value of the angle varied from 0° to 90°, values of temperature varied from 50 °C to 70 °C, and the flow rate varied from 40 to 120 litres per min. Multiple experiments were conducted at different combinations of the input parameters and the effectiveness was measured for each trial. Multiple machine learning algorithms were taken into consideration for prediction. Experimental data were divided into subsets and the performance of the machine learning model was analysed for each of the subsets. For the overall analysis, which included all the three parameters, the random forest algorithm returned the best results with a mean average error of 1.176 and root-mean-square-error of 1.542. |
first_indexed | 2024-03-10T04:12:25Z |
format | Article |
id | doaj.art-b38d78a71b35434f8fbf8c94175d01f2 |
institution | Directory Open Access Journal |
issn | 1996-1073 |
language | English |
last_indexed | 2024-03-10T04:12:25Z |
publishDate | 2022-04-01 |
publisher | MDPI AG |
record_format | Article |
series | Energies |
spelling | doaj.art-b38d78a71b35434f8fbf8c94175d01f22023-11-23T08:09:01ZengMDPI AGEnergies1996-10732022-04-01159327610.3390/en15093276Machine Learning for Prediction of Heat Pipe EffectivenessAnish Nair0Ramkumar P.1Sivasubramanian Mahadevan2Chander Prakash3Saurav Dixit4Gunasekaran Murali5Nikolai Ivanovich Vatin6Kirill Epifantsev7Kaushal Kumar8Mechanical Engineering, Kalasalingam Academy of Research and Education, Krishnankoil 626126, IndiaMechanical Engineering, Kalasalingam Academy of Research and Education, Krishnankoil 626126, IndiaAutomobile Engineering, Kalasalingam Academy of Research and Education, Krishnankoil, 626126, IndiaSchool of Mechanical Engineering, Lovely Professional University, Phagwara 144411, IndiaPeter the Great St. Petersburg Polytechnic University, 195251 Saint Petersburg, RussiaPeter the Great St. Petersburg Polytechnic University, 195251 Saint Petersburg, RussiaPeter the Great St. Petersburg Polytechnic University, 195251 Saint Petersburg, RussiaSaint-Petersburg University of Aerospace Instrumentation, 190000 Saint Petersburg, RussiaDepartment of Mechanical Engineering, K. R. Mangalam University, Gurgaon 122103, IndiaThis paper details the selection of machine learning models for predicting the effectiveness of a heat pipe system in a concentric tube exchanger. Heat exchanger experiments with methanol as the working fluid were conducted. The value of the angle varied from 0° to 90°, values of temperature varied from 50 °C to 70 °C, and the flow rate varied from 40 to 120 litres per min. Multiple experiments were conducted at different combinations of the input parameters and the effectiveness was measured for each trial. Multiple machine learning algorithms were taken into consideration for prediction. Experimental data were divided into subsets and the performance of the machine learning model was analysed for each of the subsets. For the overall analysis, which included all the three parameters, the random forest algorithm returned the best results with a mean average error of 1.176 and root-mean-square-error of 1.542.https://www.mdpi.com/1996-1073/15/9/3276heat pipeexchangermachine learningeffectiveness |
spellingShingle | Anish Nair Ramkumar P. Sivasubramanian Mahadevan Chander Prakash Saurav Dixit Gunasekaran Murali Nikolai Ivanovich Vatin Kirill Epifantsev Kaushal Kumar Machine Learning for Prediction of Heat Pipe Effectiveness Energies heat pipe exchanger machine learning effectiveness |
title | Machine Learning for Prediction of Heat Pipe Effectiveness |
title_full | Machine Learning for Prediction of Heat Pipe Effectiveness |
title_fullStr | Machine Learning for Prediction of Heat Pipe Effectiveness |
title_full_unstemmed | Machine Learning for Prediction of Heat Pipe Effectiveness |
title_short | Machine Learning for Prediction of Heat Pipe Effectiveness |
title_sort | machine learning for prediction of heat pipe effectiveness |
topic | heat pipe exchanger machine learning effectiveness |
url | https://www.mdpi.com/1996-1073/15/9/3276 |
work_keys_str_mv | AT anishnair machinelearningforpredictionofheatpipeeffectiveness AT ramkumarp machinelearningforpredictionofheatpipeeffectiveness AT sivasubramanianmahadevan machinelearningforpredictionofheatpipeeffectiveness AT chanderprakash machinelearningforpredictionofheatpipeeffectiveness AT sauravdixit machinelearningforpredictionofheatpipeeffectiveness AT gunasekaranmurali machinelearningforpredictionofheatpipeeffectiveness AT nikolaiivanovichvatin machinelearningforpredictionofheatpipeeffectiveness AT kirillepifantsev machinelearningforpredictionofheatpipeeffectiveness AT kaushalkumar machinelearningforpredictionofheatpipeeffectiveness |