Study on thermal-hydraulic performance of printed circuit heat exchangers with supercritical methane based on machine learning methods

Qian Li, Qi Zhan, Shipeng Yu, Jianchuang Sun and Weihua Cai

Energy, 2023, vol. 282, issue C

Abstract: In this study, a machine learning approach was used to predict thermal-hydraulic performance of supercritical methane flow in a printed circuit heat exchanger (PCHE). Local multiple physical parameters within the PCHE semicircular straight channel obtained from numerical simulations were employed and data of 6213 micro segments were obtained. Four machine learning models were used to predict local heat transfer coefficient and unit pressure drop at different operating conditions. By comparing the predicted results obtained after hyperparameter optimization, it shows that artificial neural network (ANN) can predict the parameters with higher accuracy. The ANN model can achieve a coefficient of determination (R2) of 0.9994 with mean absolute percentage error (MAPE) of 0.252% for the heat transfer coefficient, and R2 of 0.9996 with MAPE of 1.749% for the unit pressure drop. To verify the accuracy of machine learning model, a one-dimensional simulation model embedded with ANN model was built to calculate the temperature and pressure distribution in the entire PCHE channel. The results show the temperature and pressure distribution agree well with numerical results. This work provides an accurate machine learning approach to predict flow and heat transfer parameters, which is of great value for the simulation and design of the PCHE.

Keywords: Printed circuit heat exchanger; Supercritical methane; Artificial neural network; Machine learning; One-dimensional simulation (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (4)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544223021059
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:282:y:2023:i:c:s0360544223021059

DOI: 10.1016/j.energy.2023.128711

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().