Related Experiment Video
Updated: Jul 4, 2026
10:36
Optimization of An Air-Based Heat Management System for Dusty Particulate Matter-Covered Lithium-Ion Battery Packs
Published on: November 3, 2023
Data-driven prediction and thermodynamic performance assessment of industrial cooling towers using advanced machine
Syed Rehman Jamil1, Adeel Shehzad2, Muhammad Usman1
1Department of Mechanical Engineering, University of Engineering and Technology, Lahore, Pakistan.
Plos One
|July 2, 2026
Summary
Machine learning models accurately forecast cooling tower performance, optimizing industrial operations. Support Vector Machine (SVM) showed the best predictive accuracy, reducing water use and improving efficiency.
Area of Science:
- Industrial Engineering
- Environmental Engineering
- Data Science
Background:
- Cooling towers are crucial for industrial thermal management and machine performance.
- Accurate forecasting of cooling tower performance is essential for operational efficiency and resource conservation.
Purpose of the Study:
- To develop and compare machine learning models for predicting cooling tower performance.
- To assess the impact of operational parameters on cooling tower efficiency and water usage.
Main Methods:
- Implemented four machine learning algorithms: Random Forest, Support Vector Machine (SVM), Decision Tree, and AdaBoost.
- Utilized operational parameters including inlet water temperature, ambient air temperature, and relative humidity.
- Evaluated model performance using statistical indicators like R², RMSE, and MAPE.
Main Results:
- The SVM algorithm demonstrated superior predictive accuracy (R² = 0.985, RMSE = 1.25 kg/s).
- Increased relative humidity significantly reduced evaporation losses (55-70%) and makeup water demand (58-68%).
- Higher ambient temperatures improved second-law efficiency by approximately 65-75%.
Conclusions:
- Machine learning provides a powerful tool for optimizing cooling tower operations.
- Predictive modeling can lead to substantial water savings in industrial systems.
- Understanding the influence of environmental factors is key to efficient cooling tower management.
