Feasibility and environmental assessments of a biomass gasification-based cycle next to optimization of its performance using artificial intelligence machine learning methods. (15th February 2023)

• Record Type: Journal Article
• Authors: Hai, Tao; Ashraf Ali, Masood; Zhou, Jincheng; A. Dhahad, Hayder; Goyal, Vishal; Fahad Almojil, Sattam; Ibrahim Almohana, Abdulaziz; Fahmi Alali, Abdulrhman; Twfiq Almoalimi, Khaled; Najat Ahmed, Ahmed
• Is Part Of: Fuel. Volume 334(2023)Part 1
• Publication Date: 2023-02-15
• Subjects: Biomass gasification -- Reverse osmosis -- Machine learning -- Optimization -- Exergy -- Environmental impacts; Fuel -- Periodicals; Coal -- Periodicals; Coal; Fuel; Periodicals; 662.6
• DOI: 10.1016/j.fuel.2022.126494
• Languages: English
• ISSNs: 0016-2361

Abstract

Highlights: Simulation of a biomass-gasification system. Proposal of an integrated energy system for electricity production. Techno-economic assessment of the system for the feasibility study. Machine learining-based optimization of the proposed system. Abstract: Though bioenergy still emits some emissions, they are a lot lower than fossil fuels. Besides, the increase in water and power consumption keeps pace with the earth's growing population. Therefore, many studies have been conducted on multi-purpose cycles. Utilizing the biomass gasification process to produce the fuel needed for a gas turbine is a novel technology. The additional heat from the outlet gases is used to produce higher power in the Rankin cycle and cooling in the double-effect absorption chiller. The net power produced in this cycle will be used to empower the desalination system using reverse osmosis (RO) to increase the inlet pressure of the salty water so that it passes the water treatment membranes. Since the outlet water pressure is high, a water turbine is used to generate electricity. The genetic algorithm, along with machine learning methods, is used to achieve the optimal performance conditions and reduce the calculational time; because the time and calculational costs for modeling every cycle are high, and the optimization process will be prolonged. The results revealed that the proposed system is capable of producing a power of nearly 400 kW, with an exergy efficiency of 41 % and CO2 emission rate of 0.59 ton/MWh. Besides, the desalination rate and cooling capacities are 1.7 kg/s and 310 kW, respectively.