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 work, a mathematical computer simulation model is used to predict the possible energy generated from different Waves Energy Converters (WECs) in the Canary Islands. The Monte Carlo Method is the computer simulation model proposed to predict the generated energy. The Waves Energy Converter systems analyzed in the study were, the Aqua Buoy, Wave Dragon and Pelamis converters. The models were implemented and validated, with the dataset of Gran Canaria deep water buoy. This buoy belongs to a network of buoys belonging to Spain’s State Ports and they cover a dataset period of 22 years. The research has concluded that it is possible to affirm that the achieved model is a strong tool to compute the possible energy of any WECs, when the power matrix is known. The model based on the Monte Carlo simulation can be used in isolated islands of the Atlantic Ocean and can be extrapolated to other regions with the same characteristics.

In this paper, we studied the territorial, technical, and economic conditions for the potential installation of a wave energy converter plant (WEC) connected to the small power grid of the island of El Hierro (Canary Islands). To define the best location, the non-directional gross energy potential at the selected points was computed from long series of data of deep-water waves, propagated up to the coast using coefficients of refraction and shoaling calculated for the bathymetry of the island. The study concludes that the best location is the northeastern coast of the island “Llanos Blancos”, where the gross energy potential for the non-directional oscillating water column (OWC) plant used as a reference is 265.40 MWh/m per year. The methodology proposed in the work uses light computing means and affordable data series and is easily extrapolated by industry practitioners to other regions, particularly oceanic insular regions subject to waves potentially from any direction.

In this article, a study of characteristic vibrations of marine oils separation system is presented. Vibrations analysis allows for the extraction of representative features that could be related to the lifetime of their pieces. Actual measurements were carried out on these systems on Ro-Pax vessels to transport passengers and freight. The vibrations obtained were processed in the frequency domain and following this, they were used in a Genetic Neuro-Fuzzy System in order to design new predictive maintenance strategies. The obtained results show that these techniques as a promising strategy can be utilized to determine incipient faults.

In this research, a renewable energy hybrid system (PV-Wind) is modeled to compare different design options based on their economic and technical features. The energy requirements of a Reversible Osmosis desalination plant located on the island of Tenerife with a water production capacity of up to 20,000 m³/day was considered. The system is connected to the electricity grid. The HOMER software, version 2.75 was used to produce optimum strategies for renewable energy. The assumptions input into the model were: the technical specifications of the devices, electricity demand of the desalination plant, as well as the solar radiation and the wind speed potentials. Numerous arrangements were considered by the software, version 2.75. The optimal results were obtained based on the use of renewable energy. The data used in the study were recorded in Tenerife in the Canary Islands. The experience of this research could be transferred to other Atlantic islands with similar renewable energy sources (specifically the wind) and water scarce conditions.