(429g) Applications of Artificial Intelligence in Chemical Processes with Special Application in Heat Exchangers

Heat exchangers are used in refrigeration and air conditioning systems, automobiles, thermal power plants, chemical and textile processing industries, and other industrial applications. They are devices that allow effective heat transfer between two fluids that differ in temperature. Because of its shape and the physical events that occur during heat transfer between fluids, heat exchangers are difficult to study. Heat exchangers are studied theoretically and empirically using the first and second laws of thermodynamics [1]. Theoretical heat exchanger analysis necessitates more assumptions and complicated equations, whereas experimental heat exchanger analysis is more expensive owing to the initial expenditure in establishing an experimental equipment [2]. Heat transport is a complicated phenomenon that may be modeled using artificial intelligence. One of the artificial intelligence approaches that can give valuable tools for modeling and correlating actual heat transfer problems is artificial neural networks (ANN). Mohamedi et al. [3] utilized the ANN approach to forecast the transport and thermodynamic characteristics of water's saturated vapor and saturated liquid, which are also used to predict the transport and thermodynamic properties of water's saturated vapor and saturated liquid [4]. One of the major advantages of ANNs is their capacity to learn, generalize, or extract automatically rules from complicated data; nevertheless, the technique's main disadvantage is that it can only be utilized in the range in which it was trained because it is empirical in nature [5]. This study involves a comparison and contrast of a heat exchanger process using a programming code language and ASPEN Plus simulation to determine the results that will be used as a basis of the artificial intelligence approach on heat exchangers.

1. L. Cornelissen, G.G. Hirs, Thermodynamic optimization of a heat exchanger, Int. J. Heat Mass Transfer 42 (1999) 951-959.
2. K. Shah, D.P. Sekulic, Fundamentals of Heat Exchanger Design, John Wiley & Sons, New York, 2003.
3. Mohamedi, B., et al., Simulation of Nucleate Boiling under ANSYS-FLUENT Code by Using RPI Model Coupling with Artificial Neural Networks, Nuclear Science and Techniques, 26 (2015), 4, pp. 40601-040601
4. Ghalem, N., et al., Prediction of Thermal Conductivity of Liquid and Vapor Refrigerants for Pure and Their Binary, Ternary Mixtures Using Artificial Neural Network, Thermophysics and Aeromechanics, 26 (2019), 4, pp. 561-579
5. Haykin, S., Neural Networks: A Comprehensive Foundation, Prentice Hall PTR, Upper Saddle River, N. J., USA, 1998

EMMANUEL DADA

Dr. Dada currently serves as an Assistant Professor of Chemical Engineering at Prairie A & M University. His research interests include engineering design and optimization, chemical process and technologies, artificial intelligence, plastics waste, and clean energy.

SARHAN MUSA

Dr. Musa currently serves as Professor of the Electrical Engineering Department at Prairie View A&M University. His research interests are in the Network Security, Cryptography and Aeronautical Telecommunications Networks: Advances, Challenges, and Modeling, including artificial intelligence, multidiscipline advanced development technology management, and engineering software development.