Performance enhancement of a C-shaped printed circuit heat exchanger in supercritical CO2 Brayton cycle: A machine learning-based optimization study

Muhammad Saeed, Abdallah S. Berrouk, Yasser F. Al Wahedi, Munendra Pal Singh, Ibragim Abu Dagga, Imran Afgan

Research output: Contribution to journalArticlepeer-review

13 Downloads (Pure)

Abstract

The present work is focused on enhancing the overall thermo-hydraulic performance of a previously proposed C-shaped printed circuit heat exchanger
(PCHEs) using Machine Learning (ML) Algorithms. In this context, CFD analysis is
carried out on 81different channel configurations of the C-shaped channel geometry, and computed data is used to train three ML algorithms. Later, C-shaped channel geometry is optimized by coupling the trained ML model with
the multi-objective genetic algorithm (MOGA). Finally, the optimized channel geometry (called optimized) is investigated numerically for a wide range of Reynolds numbers. Its performance is compared with the zigzag geometry, C-shaped base geometry, and previously optimized C-shape channel geometry
using response surface methodology (RSM). The findings showed that the multilayered approach combining MOGA, CFD, and machine learning techniques is beneficial to accomplish a robust and realistic optimized solution. Comparing the thermo-hydraulic characteristics of the optimized channel geometry with zigzag channel geometry shows that the former is up to 1.24 times better than the latter based on the performance evaluation criteria (PEC). Furthermore, the
overall performance of the optimize ML ML channel geometry was found up to 21% and 16% higher than the optimized RMS geometry on the cold and hot sides, respectively
Original languageEnglish
Article number102276
JournalCase Studies in Thermal Engineering
Volume38
Early online date8 Aug 2022
DOIs
Publication statusPublished - 1 Oct 2022

Fingerprint

Dive into the research topics of 'Performance enhancement of a C-shaped printed circuit heat exchanger in supercritical CO2 Brayton cycle: A machine learning-based optimization study'. Together they form a unique fingerprint.

Cite this