Data-driven prediction and thermodynamic performance assessment of industrial cooling towers using advanced machine learning algorithms
Syed Rehman Jamil, Adeel Shehzad, Muhammad Usman, Muhammad Mujtaba Abbas, Omama Zainab Qaisrani, Muhammad Wajid Saleem, Hafiz Muhammad Musharaf, Jana Petrů · 2026
Read Data-driven prediction and thermodynamic performance assessment of industrial cooling towers using advanced machine learning algorithms by Syed Rehman Jamil, Adeel Shehzad, Muhammad Usman, Muhammad Mujtaba Abbas, Omama Zainab Qaisrani, Muhammad Wajid Saleem, Hafiz Muhammad Musharaf, Jana Petrů (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0351944.txt.
Description
Syed Rehman Jamil and seven colleagues present this 2026 PLOS One study using machine learning to predict how industrial cooling towers perform. Cooling towers dump waste heat for factories, and their efficiency and water use depend on inlet water temperature, air temperature, and humidity. The team trained four algorithms on operating data to forecast outlet water temperature, water losses, effectiveness, and thermodynamic efficiency.
A support vector machine proved most accurate of the four. The analysis showed that humid air sharply cuts evaporation losses and the makeup water a tower needs, while warmer air improved the tower's second-law efficiency. The authors present predictive modeling as a practical way to run towers with less water and better performance.
Catalog record
| CREATOR | Syed Rehman Jamil, Adeel Shehzad, Muhammad Usman, Muhammad Mujtaba Abbas, Omama Zainab Qaisrani, Muhammad Wajid Saleem, Hafiz Muhammad Musharaf, Jana Petrů |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 42356 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |