SYSTEMATIC REVIEW article
Front. Mech. Eng.
Sec. Fluid Mechanics
This article is part of the Research TopicData-Driven Thermo-Fluids EngineeringView all articles
A Systematic Review of Thermodynamic Modeling and Machine Learning Integration for Optimizing Plate Heat Exchanger Performance in Uganda's Brewing Industry
Provisionally accepted
Byamanywoha Edgar
Val Hyginus Udoka Eze*Saadelnour Abdueljabbar Adam SaadelnourSanusi YinkaBubu Pius Erheyovwe- Kampala International University - Western Campus, Bushenyi, Uganda
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Plate Heat Exchangers (PHEs) are pivotal in industrial thermal systems, particularly in the brewing industry, where precise temperature control is essential for fermentation efficiency. In Uganda's brewing sector, the use of PHEs faces challenges such as fouling, fluctuating thermal loads, and resource constraints, which limit optimal performance. This systematic review analyzes the integration of thermodynamic modeling and machine learning (ML) to optimize PHE operation. A total of 199 studies were initially reviewed, of which 112 met the quality standards for inclusion. Hybrid models that combine physical thermodynamic principles with ML algorithms, including Artificial Neural Networks (ANN), Particle Swarm Optimization (PSO), and Genetic Algorithms (GA), demonstrated substantial performance improvements. Specifically, these models demonstrated superior predictive performance compared to traditional methods, although the degree of improvement varied across studies due to differences in datasets and evaluation metrics. Additionally, real-time fouling prediction using machine learning techniques led to a 22% reduction in maintenance costs and a 15% decrease in operational downtime. The integration of digital twin technologies and adaptive control strategies showed an 18% improvement in energy efficiency, and up to 30% in response time to dynamic thermal loads. Despite these advances, there remain significant challenges in adapting these solutions to tropical climates and achieving cost-effective integration with renewable energy sources. This review highlights the transformative potential of thermodynamic and AI synergy, emphasizing a pathway toward the development of self-optimizing PHE systems capable of improving energy efficiency, product quality, and sustainable industrial growth in regions like Uganda.
Keywords: Plate heat exchangers (PHEs), machine learning, Fouling mitigation, hybrid optimization, energy efficiency, and Adaptive Control
Received: 04 Sep 2025; Accepted: 03 Nov 2025.
Copyright: © 2025 Edgar, Eze, Saadelnour, Yinka and Erheyovwe. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Val Hyginus Udoka Eze, udoka.eze@kiu.ac.ug
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.