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

Air quality can be affected by merchant ships, so it is important to regulate emissions that are produced, as well as to use energy efficiently. In this sense, the cleanliness of the oil used in lubrication is essential to achieve a better use of energy and reduce losses in marine engines. For that, it is vital to carry out good maintenance strategies. Therefore, it is important to develop techniques that allow condition monitoring during engine operation. In order to detect potential problems as soon as possible, it is common to analyze vibratory signals, since sustainable changes in the rotating frequency and its harmonics can be detected, which was the objective of this work, by analyzing the time-frequency domain using wavelet packet transform. A methodology to select the optimal function (mother wavelet) and the best patterns to monitor, in order to determine the state of the purifiers of the marine lube oils, was carried out, including intelligent classification systems. Specifically, this document considers centrifugal oil lubricant separators systems, since the monitoring of these systems can determine the condition of different mechanical systems.

In this paper, an intelligent control approach based on neuro-fuzzy systems performance is presented, with the objective of counteracting the vibrations that affect the low-cost vision platform onboard an unmanned aerial system of rotating nature. A scaled dynamical model of a helicopter is used to simulate vibrations on its fuselage. The impact of these vibrations on the low-cost vision system will be assessed and an intelligent control approach will be derived in order to reduce its detrimental influence. Different trials that consider a neuro-fuzzy approach as a fundamental part of an intelligent semi-active control strategy have been carried out. Satisfactory results have been achieved compared to those obtained by means of vibration reduction passive techniques.