Fabrication, machine learning modeling, and operational sensitivity analysis of a Maisotsenko cycle-based water-cooling tower

Guiying Xu, Fengxia Dai, Cong Wang, Mingsong Li, Jiyuan Li and Xueyang Liu

Energy, 2025, vol. 331, issue C

Abstract: The working principle and objective of a dew-point M-cycle water cooling tower are fundamentally different from those of an M-cycle air cooler. While M-cycle air coolers have already been commercialized and are available on the market, M-cycle water-cooling towers have received extremely limited attention (despite their significant potential), even at the research level, in terms of prototyping, experimental sensitivity analysis, and machine learning modeling. This study addresses this gap by innovative designing and experimentally testing a dew-point water cooling tower under various operating conditions, incorporating machine learning techniques to enhance performance analysis and prediction. Unlike an M-cycle air cooler, an M-cycle cooling tower has no supply air, as all air from the primary dry channel is directed into the wet working channel, and the inlet water is typically warmer than the ambient air with a much higher mass flow rate. Any given M-cycle water cooling tower is capable of providing supply water at a temperature lower than the ambient air's wet-bulb temperature for a range of water and air fluid flow parameters as are explored in this research. To achieve the objectives of this study, a logical range of operational parameters, specifically the water inlet mass flow rate and its inlet temperature, were first experimentally tested under various climate conditions (cold, hot dry, and hot humid). The resulting data was then used to train a machine learning model, which was employed to generate output data across a much broader range of unseen inputs, enabling a more precise analysis of the tower's behaviour. The key output parameters include water outlet temperature, evaporation rate, dew point effectiveness, approach temperature, and overall cooling capacity.The results demonstrated sub-wet-bulb cooling performance with outlet water temperatures up to 5 °C lower than ambient wet-bulb temperature in hot dry climates. The key output parameters include water outlet temperature, evaporation rate, dew point effectiveness, approach temperature, and overall cooling capacity.

Keywords: Dewpoint water cooler tower; Maisotsenko; Experiment; Machine learning (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544225026349
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:331:y:2025:i:c:s0360544225026349

DOI: 10.1016/j.energy.2025.136992

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 ().