Neuro-genetic approach for optimization of the water flowrates distribution on a hydrogen sulphide cooling system

DOI: https://doi.org/10.36909/jer.15157

Abstract

Efficient utilities usage and enhanced heat transfer are imperative in todays’ industrial and technological processes. Over these bases, a neuro-genetic procedure was proposed for optimization of the water flowrates distribution on a hydrogen sulphide gas coolers system. It relied on Genetic Algorithms, combined with an improved ɛ-NTU model for simulation of jacketed shell-and-tube heat exchangers. Artificial Neural Networks were furtherly applied to correlate the optimum water flowrates to predictive variables. The heat transfer incremental was estimated from 3695 to 10514 W, while reduction of the gas exit temperature was projected between 2.9 and 9.8 K. Calculated heat recovery averaged 12.44 %, varying from 3.90 to 22.16 %. The optimized water distribution scheme improved the system energy performance under a fixed network concept and unvaried overall feed water flowrate, thus effectively avoiding additional cost incurred if topology modification is applied. This research provided a technological solution to the studied problem, consisting on installation of automatic valves and programmable flow control-loops linked to a PLC.

Author Biography

Andres Adrian Sánchez-Escalona, University of Moa

Andres A. Sánchez-Escalona was born in Holguín, Cuba in 1978. He received a B.S. degree in Mechanical Engineering from the University of Holguín, in 2002, and the M.Sc. degree in Electromechanical from the Metallurgical Mining Higher Institute of Moa, in 2017. He is currently a student of the Doctoral Research (Electromechanical) Program at the University of Moa.

With over 17 years of experience in projects management and engineering services for chemical processing plants, he is presently Director of the Engineering Division at Moa Nickel S.A., a nickel plus cobalt mining and primary processing plant, located in the eastern region of Holguín, Cuba. He is the author of more than 20 articles and conference papers. His research interests include shell-and-tube heat exchangers and convective heat transfer, involving single-phase fluids, as well as industrial applications of artificial intelligence tools like Artificial Neural Networks and Genetic Algorithms.

Prof. Sánchez-Escalona is coworker of CEETAM (Centro de Estudio de Energía y Tecnología Avanzada de Moa), and member of UNAICC (Unión Nacional de Arquitectos e Ingenieros de la Construcción de Cuba).

Published
2021-11-21
Issue
Online First Articles
Section
Mechanical Engineering