Feasibility study on heat recovery from gas turbine exhaust for absorption chiller operation and efficiency enhancement using neural networks

• Investigating the possibilities of cooling the inlet air using an absorption chiller. • Comparing gas turbine waste gases with and without cooling load to be used as a heat source. • Investigating the heat recovery from the exhaust gas of the Siemens V94.2 gas turbine through the heat exchanger caused by TIAC. • Calculating the maximum cooling load from the behavior of temperature versus relative humidity. • Multiplying a coefficient by the maximum cooling load with the help of neural network In this study, a heat recovery-based turbine inlet air cooling (TIAC) system was investigated to enhance the performance of a Siemens V94.2 gas turbine. The aim of this study is to improve the efficiency of the gas turbine using a cooling system based on exhaust gas heat recovery. The innovation lies in the combination of artificial neural network (ANN) modeling for accurate turbine performance predictions and the use of real-world power plant data to optimize cooling loads and provide an economic analysis of the system. A thermodynamic analysis was performed and key operating parameters, including temperature (from 18.3 °C to 45 °C), relative humidity (from 39 % to 80 %), air pressure, fuel consumption and efficiency, were collected from a study power plant over a year. By analyzing the relationship between temperature and relative humidity, the maximum cooling load was determined and an optimal cooling load factor was applied to achieve room temperature (15 °C) and relative humidity (100 %). The hybrid approach combined with ANN modeling improved the performance predictions. The results show that the implementation of TIAC leads to a 2.32 % increase in efficiency and a 10.63 MW increase in output power, resulting in an additional annual generation of 66,596 MWh of electricity. The payback period of the system is less than five months and the investment cost is $522,500. The increased electricity generation results in an additional annual revenue of $1.33 million. From an economic perspective, the system significantly improves the profitability of the power plant, making TIAC a cost-effective and scalable solution for gas turbine power plants in warm climates.

Authors

Institutions

Publication Details

Journal
Thermal Science and Engineering Progress
Published
2025-10-25
DOI
https://doi.org/10.1016/j.tsep.2025.104210
Citations
5
Primary Topic
Thermodynamic and Exergetic Analyses of Power and Cooling Systems
Type
article
Field-Weighted Citation Impact
3.57
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Feasibility study on heat recovery from gas turbine exhaust for absorption chiller operation and efficiency enhancement using neural networks

Ali Reza Tahavvor, Mohammad Javad A. Shirazi, Rahim Zahedi, Ali Naziri
5 citations
Thermal Science and Engineering Progress
Thermodynamic and Exergetic Analyses of Power and Cooling Systems
3.57
article

Feasibility study on heat recovery from gas turbine exhaust for absorption chiller operation and efficiency enhancement using neural networks

Ali Reza Tahavvor, Mohammad Javad A. Shirazi, Rahim Zahedi, Ali Naziri
article en
5 citations

Abstract

• Investigating the possibilities of cooling the inlet air using an absorption chiller. • Comparing gas turbine waste gases with and without cooling load to be used as a heat source. • Investigating the heat recovery from the exhaust gas of the Siemens V94.2 gas turbine through the heat exchanger caused by TIAC. • Calculating the maximum cooling load from the behavior of temperature versus relative humidity. • Multiplying a coefficient by the maximum cooling load with the help of neural network In this study, a heat recovery-based turbine inlet air cooling (TIAC) system was investigated to enhance the performance of a Siemens V94.2 gas turbine. The aim of this study is to improve the efficiency of the gas turbine using a cooling system based on exhaust gas heat recovery. The innovation lies in the combination of artificial neural network (ANN) modeling for accurate turbine performance predictions and the use of real-world power plant data to optimize cooling loads and provide an economic analysis of the system. A thermodynamic analysis was performed and key operating parameters, including temperature (from 18.3 °C to 45 °C), relative humidity (from 39 % to 80 %), air pressure, fuel consumption and efficiency, were collected from a study power plant over a year. By analyzing the relationship between temperature and relative humidity, the maximum cooling load was determined and an optimal cooling load factor was applied to achieve room temperature (15 °C) and relative humidity (100 %). The hybrid approach combined with ANN modeling improved the performance predictions. The results show that the implementation of TIAC leads to a 2.32 % increase in efficiency and a 10.63 MW increase in output power, resulting in an additional annual generation of 66,596 MWh of electricity. The payback period of the system is less than five months and the investment cost is $522,500. The increased electricity generation results in an additional annual revenue of $1.33 million. From an economic perspective, the system significantly improves the profitability of the power plant, making TIAC a cost-effective and scalable solution for gas turbine power plants in warm climates.

Thermal Science and Engineering ProgressVol. 67
University of Tehran (IR), Islamic Azad University of Shiraz (IR)
Openalex Percentile: Top 7%
Thermodynamic and Exergetic Analyses of Power and Cooling Systems
3.57
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.