Work

Machine Learning-Based Model Prediction of an Adsorption Desalination System and Investigation of the Impact of Parameters on the System’s Outputs

Year: 2024

Type: article

Abstract: Adsorption Desalination (AD) has emerged as a novel technique for desalination, offering a ‎‎significant reduction in energy consumption compared to conventional desalination ‎‎technologies. This paper uses Machine Learning procedures to present a ‎model predictive approach for adsorption desalination systems. The goal is to predict the ‎functional parameters of the system and investigate the ‎influence of different components of ‎the AD ‎system on the functional parameters of the plant. ‎The adsorption desalination system ‎will be modeled through the utilization of Multi-Layer ‎Perceptron (MLP) and Radial-Based ‎Function (RBF) neural network approaches. Hence, the ‎Specific Daily Water Production ‎‎(SDWP) and evaluation of other performance indicators, such as ‎the Coefficient of ‎Performance (COP) and Specific Cooling Power (SCP), are determined. ‎There are 55 ‎instances in the dataset, each with five input variables: evaporator and condenser ‎‎temperatures, adsorption beds, and hot water entering the system. Additionally, three output ‎‎variables are recorded: COP, SCP, and SDWP. The results of this investigation show that the ‎MLP is more effective for simulating the ‎AD system, and the Roots of Mean Square Error of COP, SCP, and SDWP are ‎‎0.002, 0.5921, and 0.0465, respectively. Then, the ‎impact of input factors on output parameters was examined. ‎Hence, the hot water temperature ‎parameter entering the system affected the output parameters the most. Subsequently, the ‎COP parameter is mainly affected by the absorption beds, evaporator, and condenser ‎temperature. The SCP ‎parameter is primarily influenced by the inlet hot water temperature, ‎condenser temperature, ‎temperatures of the two adsorption beds, and evaporator temperature.

Source: Water

DOI: 10.3390/w16243700

Authors: Taleb Zarei, Masoud Chatavi, Masoud Nazari, Amirhossein Amirfakhraei, Majid Amidpour, Mohsen Salimi

Institutions: University of Hormozgan, Amirkabir University of Technology, K. N. Toosi University of Technology, Niroo Research Institute

Language: English

Topic: Adsorption and Cooling Systems

Subfield: Mechanical Engineering

Field: Engineering

Domain: Physical Sciences

SDG: Clean water and sanitation

Open Access status: gold

Estimated APC paid: $2,955