RT info:eu-repo/semantics/doctoralThesis
T1 Application of Artificial Intelligence techniques to optimize the management of seawater reverse osmosis desalination plants with a particular interest in marine vessels
A1 Camacho Espino, Jorge
AB Water scarcity is a pressing global problem. Global population growth and climate change are two main reasons for increasing water stress in manycountries. Different solutions are being developed to solve this problem, such as rainwater harvesting, seawater desalination, wastewater treatment andreuse, and sustainable water management. Seawater desalination using reverse osmosis (SWRO) is a widespread membrane technology worldwide thatobtains fresh ocean water.This doctoral thesis is based on improving and optimizing the management and energy efficiency of seawater desalination plants and its application insmall marine vessels. Different Machine Learning (ML) and Artificial Intelligence (AI) techniques have been applied to create prediction tools to improveplant control. Through these AI techniques, it has been possible to predict the optimal values of the equipment actuators to fulfill different requirementsproposed by the author. Some of the variables considered in the thesis and used in the control systems have been conductivity, temperature, and flow ofseawater (SW), the pressure of the high-pressure pump (HPP), the flow and conductivity of permeate water and the consumption of energy, or specificenergy consumption (SEC) of the plant.Data from two different SWRO desalination plants has been collected. As a result of different studies carried out to solve the problems presented, threescientific articles have been published. These papers make up the compendium publications of this thesis.In each of the three articles, satisfactory results have been obtained, which have allowed the control of the desalination plants studied to be improved.These results have been possible due to the study and optimization of different operational parameters of interest in the desalination process. Thesepredictive tools could be extrapolated to other seawater desalination plants.
YR 2024
FD 2024
LK http://riull.ull.es/xmlui/handle/915/38837
UL http://riull.ull.es/xmlui/handle/915/38837
LA en
DS Repositorio institucional de la Universidad de La Laguna
RD 18-nov-2024