Machine Learning Models Applied to Manage the Operation of a Simple SWRO Desalination Plant and Its Application in Marine Vessels

In this work, two machine learning techniques, specifically decision trees (DTs) and support vector machines (SVMs), were applied to optimize the performance of a seawater reverse osmosis (SWRO) desalination plant with capacity 100 m3 per day. The input variables system pH, conductivity, three requirements: permeate flow rate, total energy consumed by plant. These requirements decided based on cost function that prioritizes water needs in vessel maximum possible savings. intelligent modifies actuators plant: feed rate control high-pressure pump (HPP) operating pressure. This tool is proposed for optimal use plants marine vessels. Although both techniques output satisfactory results, it was concluded DTs technique (HPP pressure: root mean square error (RMSE) = 0.0104; rate: RMSE 0.0196) more accurate than SVMs 0.0918; 0.0198) metrics used. final objective paper extrapolate implementation smart other shipboard their performance.