TY - JOUR
T1 - Techno-economic-environmental assessment and AI-enhanced optimization of a gas turbine power plant with hydrogen liquefaction
AU - Hai, Tao
AU - Dahan, Fadl
AU - Mohammed, Amin Salih
AU - Chauhan, Bhupendra Singh
AU - Alshahri, Abdullah H.
AU - Almujibah, Hamad R.
AU - Ahmed, A. N.
N1 - Publisher Copyright:
© 2023 Hydrogen Energy Publications LLC
PY - 2024/1/2
Y1 - 2024/1/2
N2 - Most of the power plants in the world are based on gas turbines and many researchers tried to improve their efficiencies. This goal can be attained by the optimum utilization of heat losses. The authors of the present study aim to design, model, and optimize a gas turbine-based multigeneration power plant that uses the maximum possible of input energy to boost the products capacity and improve the efficiency. To decline the hydrogen storage and transportation costs, a hydrogen liquefaction process is applied to liquified the produced hydrogen at the same time. Besides, the power plant stack containing a substantial amount of energy is employed to operate a multi-effect desalination unit. To solve the main functions of the model, a programming code is developed. Then, the objective functions of the model are optimized using a machine learning model coupled with a genetic algorithm. Sensitivity analysis reveals that the fuel mass flow rate plays a pivotal role on total cost rate and hydrogen production rate; however, does not affect the exergy efficiency. Applying such a design for heat recovery, leads to 3.27% improvement in exergy efficiency rather than similar studies. The optimization results indicates that the LCOE is declined by 8.16% and normalized emission of CO2 is mitigated by 5.82 kg/GJ.
AB - Most of the power plants in the world are based on gas turbines and many researchers tried to improve their efficiencies. This goal can be attained by the optimum utilization of heat losses. The authors of the present study aim to design, model, and optimize a gas turbine-based multigeneration power plant that uses the maximum possible of input energy to boost the products capacity and improve the efficiency. To decline the hydrogen storage and transportation costs, a hydrogen liquefaction process is applied to liquified the produced hydrogen at the same time. Besides, the power plant stack containing a substantial amount of energy is employed to operate a multi-effect desalination unit. To solve the main functions of the model, a programming code is developed. Then, the objective functions of the model are optimized using a machine learning model coupled with a genetic algorithm. Sensitivity analysis reveals that the fuel mass flow rate plays a pivotal role on total cost rate and hydrogen production rate; however, does not affect the exergy efficiency. Applying such a design for heat recovery, leads to 3.27% improvement in exergy efficiency rather than similar studies. The optimization results indicates that the LCOE is declined by 8.16% and normalized emission of CO2 is mitigated by 5.82 kg/GJ.
UR - http://www.scopus.com/inward/record.url?scp=85169446433&partnerID=8YFLogxK
U2 - 10.1016/j.ijhydene.2023.07.083
DO - 10.1016/j.ijhydene.2023.07.083
M3 - Article
AN - SCOPUS:85169446433
SN - 0360-3199
VL - 49
SP - 130
EP - 149
JO - International Journal of Hydrogen Energy
JF - International Journal of Hydrogen Energy
ER -
