Marine Operations Research Articles

Sea surface reconstruction from marine radar images using deep convolutional neural networks

The sea surface reconstructed from radar images provides valuable information for marine operations and maritime transport. The standard reconstruction method relies on the three-dimensional fast Fourier transform (3D-FFT), which introduces empirical parameters and modulation transfer function (MTF) to correct the modulation effects that may cause errors. In light of the convolutional neural networks’ (CNN) success in computer vision tasks, this paper proposes a novel sea surface reconstruction method from marine radar images based on an end-to-end CNN model with the U-Net architecture. Synthetic radar images and sea surface elevation maps were used for training and testing. Compared to the standard reconstruction method, the CNN-based model achieved higher accuracy on the same data set, with an improved correlation coefficient between reconstructed and actual wave fields of up to 0.96-0.97, and a decreased non-dimensional root mean square error (NDRMSE) of around 0.06. The influence of training data on the deep learning model was also studied. Additionally, the impact of the significant wave height and peak period on the CNN model’s accuracy was investigated. It has been demonstrated that the accuracy will fluctuate as the wave steepness increases, but the correlation coefficient remains above 0.90, and the NDRMSE remains less than 0.11.

Electrification of fishing vessels and their integration into isolated energy systems with a high share of renewables

Decarbonization is among the most important research topics in the maritime sector, where different technical and operational measures are being examined to enhance the sustainability of marine operations. Electrification of fishing vessels stands out as a solution towards reducing emissions and operating costs. However, sustainable decarbonization of fishing vessels requires a high share of renewable energy sources (RES) in the power sector. It is also challenging to achieve the sustainable decarbonization of fishing vessels operating in an isolated energy system (IES) in remote areas. The novelty of this study is to demonstrate the opportunities arising from the nexus between fully electric fishing vessels and photovoltaic (PV) power systems in the IES of an island. The study highlights the economic and environmental benefits of integrating all-electric fishing vessels in the IES with 100% RES. The energy modelling of the IES was simulated in the EnergyPLAN. The paper confirms that charging battery-powered electric fishing vessels in the fishing port can reduce the critical excess of electricity production (CEEP), operating IES costs, and the emissions of CO2. The presented mathematical model is applicable to other ship types and renewable-based IESs if the input data required for such simulations are known.

Novel Ocean Wave Height and Energy Spectrum Forecasting Approaches: An Application of Semi-Analytical and Machine Learning Models

Accurate and reliable wave forecasting is crucial for optimizing the performance of various marine operations, such as offshore energy production, shipping, and fishing. Meanwhile, predicting wave height and wave energy is crucial for achieving sustainability as a renewable energy source, as it enables the harnessing of the power of wave energy efficiently based on the water-energy nexus. Advanced wave forecasting models, such as machine learning models and the semi-analytical approach, have been developed to provide more accurate predictions of ocean waves. In this study, the Sverdrup Munk Bretschneider (SMB) semi-analytical approach, Emotional Artificial Neural Network (EANN) approach, and Wavelet Artificial Neural Network (WANN) approach will be used to estimate ocean wave parameters in the Gulf of Mexico and Aleutian Basin. The accuracy and reliability of these approaches will be evaluated, and the spatial and temporal variability of the wave field will be investigated. The available wave characteristics are used to generate hourly, 12-hourly, and daily datasets. The WANN and SMB model shows good performance in the daily prediction of the significant wave height in both case studies. In the SMB model, specifically on a daily time scale, the Nash–Sutcliffe Efficiency (NSE) and the peak deviation coefficient (DCpeak) were determined to be 0.62 and 0.54 for the Aleutian buoy and 0.64 and 0.55 for the Gulf of Mexico buoy, respectively, for significant wave height. In the context of the WANN model and in the testing phase at the daily time scale, the NSE and DCpeak indices exhibit values of 0.85 and 0.61 for the Aleutian buoy and 0.72 and 0.61 for the Gulf of Mexico buoy, respectively, while the EANN model is a strong tool in hourly wave height prediction (Aleutian buoy (NSEEANN = 0.60 and DCpeakEANN = 0.88), Gulf of Mexico buoy (NSEEANN = 0.80 and DCpeakEANN = 0.82)). In addition, the findings pertaining to the energy spectrum density demonstrate that the EANN model exhibits superior performance in comparison to the WANN and SMB models, particularly with regard to accurately estimating the peak of the spectrum (Aleutian buoy (DCpeakEANN= 0.41), Gulf of Mexico buoy (DCpeakEANN = 0.59)).

SEASNAKE: Impact - Marine operations modelling for evidence-based results detailing the impact of using a new fully dynamic cable design for ocean energy devices.

The SEASNAKE project - an OceanERA-NET project – is aiming for developing fully dynamic cables for ocean energy. Through new design and application of novel coatings the project is designing a dynamic cable that better suits the conditions and user requirements. In order to fully understand the benefits, the Wave Venture TEMPEST™ techno-economic analysis software will be used to simulate the performance of a proposed wave energy farm with a special focus on the contribution of the dynamic cable subsystem. The results obtained from the simulations will not only provide a deep understanding of the reliability and cost-risk areas regarding the use of dynamic cables, but will also allow a comparison with a baseline scenario consisting of a more traditional cabling system. The latter will be key to identify the advantages of the SEASNAKE project and its commercial viability. KPIs (Key Performance Indicators) will include farm availability and power production downtime as a direct result of cable related issues. The reliability, maintainability and survivability of the cabling subsystem will be tested and the KPIs will give clear indication on the performance benefits and ultimately the impact on the LCOE will be of greatest consideration.

Principles of ADCP deployment methodologies

ADCPs are regularly used for resource characterization in wave and tidal energy sites; however, methodologies and best practices are entirely dependent on the site characteristics and the assets available. EMEC have used their widely varied experience at multiple sites and locations to develop a review of methodologies and the pros and cons of different deployment styles for data acquisition.When deploying ADCPs there are a number of site criteria that must be assessed, such as seabed type, bed flow speeds, surface flow speeds, recovery windows (slack and weather), and water depth and range. These criteria can significantly affect the success or failure of marine operations, not necessarily for deployment but certainly for recovery. When recovery operations fail then projects lose assets (ADCP units and bed frames), data, and money (in hire/unit costs, and vessel hire for example). When the data is not recovered then this can jeopardise project success, wasting time, effort and funding.Different deployment configurations and recovery techniques have been used for ADCP deployments. Equipment such as ground lines, acoustic releases, USBLs, and surface buoys are used to mark, locate, and/or recover devices. These are varied depending on a number of factors. Ground type, for example, can affect systems used since a ground line cannot be effectively used in delicate ecosystems since the dredging required to recover may disturb local flora and fauna. Also, for example, flow speed and vessel traffic will determine whether a surface buoy can be used.Based on multiple ADCP deployments to characterize resource for wave and tidal energy projects in Scotland, England, France and other sites, EMEC have reviewed different deployment methods and recovery techniques. There is a proposed set-up for deployments suitable for a number of active marine energy sites and suggestions for edits based on site characteristics and target data requirements.

A social sustainability model for maritime labour force based on card sorting, fuzzy AHP & QFD method

Within the context of the ongoing implementation of the 2030 Agenda for Sustainable Development-Sustainability Development Goals (SDGs), actions toward economic, environmental, and social sustainability were aimed to be promoted. As a key stakeholder, the maritime industry's role in handling global sustainability is increasingly recognized. Social sustainability, one of the components of sustainable development, is a major concern in the maritime field for protecting the crew and providing a safe working environment. However, it is surprising to note the lack of research addressing the social sustainability of the maritime labour force in the literature. This study aims to propose a social sustainability model for the maritime labour force. The model was constructed using Card Sorting, Fuzzy Analytic Hierarchical Process (FAHP) & Quality Function Deployment (QFD) Methods. Because it discloses the expectations of the maritime labour force and the requirements that can meet these expectations, the authors have been prompted by the QFD method's frequent use in the literature and the fact that it generates the best answers to customer expectations. With the QFD method and House of Quality (HoQ) used to determine the requirements that can meet customer expectations, the requirements that can correspond to the expectations of the maritime labour force have been determined. The use of the card sorting program during the determination of the indicators has been an important point in terms of displaying a scientific approach. In addition, it is aimed to eliminate linguistic ambiguities by using the FAHP method of weighting expectations in the House of Quality method. The results revealed that work-life balance, social benefit, education and training, safety and healthy working environment at sea were the most critical expectations of seafarers, and the wage policy was less important among other expectations from the social sustainability perspective. Moreover, health and safety of people, social insurance and benefits, medical coverage and medical benefits, repatriation, understandable contract, quality and quantity of food, setting up a land-sea-land career management system, short deployment and flexible working time and, establishment of a crew welfare department were found to be the most critical requirements. The study highlights possible implications on managerial aspects and can be used as a practical guideline for decision-makers seeking to implement sustainable development in their organizations. This paper is among research studies' first to apply a hybrid approach and propose a social sustainability model for the maritime labour force. Due to the positive social and environmental effects this study will have, it will not only help seafarers, marine operators, the maritime sector, national and international economy, but also all world societies.

Developments in Unmanned Surface Vehicles (USVs): A Review

Unmanned Surface Vehicles (USVs) have witnessed significant advancements in recent years, revolutionizing various domains that require marine operations. This abstract presents a review of the developments in USVs, focusing on their applications, technological advancements, and associated benefits. USVs have emerged as invaluable tools for data collection studies, particularly in environmental monitoring and marine production policies. They offer a cost-effective and efficient means of gathering critical data, aiding decision-making processes in these fields. Additionally, USVs have proven instrumental in the surveillance of territorial waters, safeguarding offshore systems, and supporting oil and fuel activities in the Arctic regions. These capabilities have resulted in improved security, enhanced operational efficiency, and reduced risks for personnel involved in these operations. Technological advancements in USVs have played a pivotal role in their evolution. Enhanced autonomy, sensor integration, and communication systems have enabled USVs to operate autonomously or in collaboration with manned vessels, expanding their capabilities and versatility. Moreover, improvements in navigation systems, obstacle avoidance mechanisms, and power management have significantly enhanced the reliability and endurance of USVs, allowing them to undertake extended missions with minimal human intervention. In conclusion, the developments in unmanned surface vehicles have transformed the way marine operations are conducted. With their wide-ranging applications, technological advancements, and associated benefits, USVs have proven to be indispensable assets in various domains. As research and innovation continue to propel the field forward, USVs are poised to play an even more significant role in the future of marine operations, further improving efficiency, safety, and sustainability.

Flue gas cleaning approach based on jet reactor prototype research

The motivations for developing innovative jet ejector scrubbers, which meet the contemporary requirements for reducing sulfur oxide emissions in marine engineering, are presented in this paper. The proposed jet ejector scrubber was equipped with a cylindrical mixing section. The selected operating conditions enabled the development of a mixing shock process that afforded favourable conditions for sulfur oxide absorption. The first series of experimental investigations were carried out on a laboratory scale for a 40-kW diesel engine equipped with jet ejector scrubbers at a sulfur mass content of 0.35% in the fuel. The tests were conducted for various applied motive nozzles, as well as a nominal mixing section length-to-diameter ratio (L/D) of 25. These tests confirmed the complete reduction of SO2 using the jet reactor, as well as the reduction of other chemical compounds in the exhaust gas without using additional filters, e.g., reduction of heavy metals and transition metals by 85–98% and 71–74%, respectively, and the removal of total organic carbon (TOC) from exhaust gas at a level greater than 46%. The second series of experiments investigated a diesel engine with a maximum power of 250 kW under marine operating conditions. In this case, the effect of the mixing section length was tested. For fuels with 1.0% and 1.5% sulfur mass contents, full reduction of sulfur oxides was obtained for various loads of the engine. A maximum SO2/CO2 ratio of 0.18 was obtained for the ejector with an L/D of 25 and an engine load of 200 kW. However, this is significantly lower than the required limit of 4.3 according to the IMO.

Underwater Object Detection Based on Improved Transformer and Attentional Supervised Fusion

Underwater object detection is one of the important technologies for improving the efficiency of underwater inspection, but the existing methods still suffer from the problems of missed detection and insufficient target localization capability of targets. To address these problems, an improved Transformer and multi-scale attentional supervised feature fusion-based underwater object detection method is proposed. In our method, the underwater objects are preprocessed by prior knowledge first. Then, a new coordinate decomposition window-based (CDW) Transformer block is proposed to extract spatial location information more accurately, and scaling factors are introduced to reduce the intermediate computation. Finally, an attentional supervised fusion (ASF) method is proposed to strengthen the link between feature extraction and feature fusion, and further improve the detected performance by using compound attention weights. The cascade detection head is improved, where the information flow is reversed to enhance the prediction of coordinates. The average accuracy of the proposed method on the URPC and DUO datasets is 3.7% and 3.8% higher than that of the baseline network through the cross-test, and outperforms the state-of-the-art methods. This study can provide a reference for engineering applications such as automated marine operations and biodetected fishing techniques.

Bubble and particle dynamics in a thin rectangular bubbling fluidized bed under emulated marine instabilities

Floating fluidized beds are affected by swell/sea waves, limiting their effectiveness in seagoing applications as an alternative to fixed beds for the removal of exhaust pollutants. To address this, experiments were conducted using a rectangular fluidized bed mounted on a hexapod to emulate marine operation. The bed was subjected to dynamic perturbations, and Digital Image Analysis and Particle Image Velocimetry were used to analyze the effects of motion on fluidization, bubble growth/shape, void/velocity fields, and gas/solids circulations. Our investigation showed that non-vertical orientations resulted in a decrease in minimum fluidization velocity, but the most significant effect was seen in the trajectory and shape of the bubbles near both static and dynamic walls. This resulted in a slug regime with a high degree of gas bypass. These outcomes have important implications for the design/operation of marinized fluidized beds, and for process intensification solutions to address the constraints associated with ship emissions.

Methodological bases for assessing the quality of transport and logistics customer service of a marine terminal operator

The purpose of this article is to develop a methodology for assessing the quality of transport and logistics services for operators of sea terminals. The paper identifies the factors influencing the formation of the quality of transport and logistics services in the activities of marine operators of sea terminal in modern conditions. As a result of the conducted research, a system of comprehensive quality assessment has been formed, which allows assessing the degree of customer satisfaction. A new approach to quality assessment is proposed, involving the involvement of customers in the formation of quality criteria, as well as a method for calculating and evaluating the normative level of the generalizing indicator of the quality of transport and logistics customer service of the operator of the sea terminal. The practical significance of the developed methodology is that on its basis it becomes possible to assess the consequences of implementing various management decisions to improve the business processes.

Spaceborne SAR-Based Detection of Ships in Suez Gulf to Analyze the Maritime Traffic Jam Caused Due to the Blockage of Egypt’s Suez Canal

With the convenience and connectedness of the oceans in recent years, there has been an increase in naval traffic, which has prompted maritime surveillance to attract special attention due to its significant application in marine operations. Ships, because of their uneven and rugged design, appear as a brighter patch, which aids in their identification by the Synthetic Aperture Radar (SAR), an active remote sensing technique. In this study, Sentinel-1 and Sentinel-2 datasets are used to detect vessels in the Gulf of Suez in order to examine the increasing maritime traffic induced by the Suez Canal blockage caused by the Ever Given ship becoming stranded in the canal on 23 March 2021 and being freed after 6 days on 29 March 2021. The usefulness of dual-pol spaceborne SAR datasets in ship detection is also determined. The analysis was performed within a time window spanning before, during, and after the blockage event. On the basis of the experimental results, Sentinel-1 images proved to be more effective compared to Sentinel-2 images for ship detection due to the all-weather capability of the Sentinel-1 dataset. Furthermore, the ship detection results obtained in dual polarization were substantially more accurate than the results obtained in a single polarization.

Autonomous boundary inspection of Posidonia oceanica meadows using an underwater robot

Monitoring provides important information for the planning and execution of marine environment preservation operations. Posidonia oceanica is one of the principal bioindicators in Mediterranean coastal areas and regular monitoring activities play a crucial role in its conservation. However, an efficient observation of vast areas colonised with P. oceanica is extremely challenging and it currently requires tedious and time consuming diving activities. Autonomous Underwater Vehicles (AUVs) endowed with optical sensors could represent a viable solution in carrying out visual inspection surveys. Nevertheless, AUVs are usually programmed to perform pre-defined trajectories, which are not effective for seagrass monitoring applications, as meadows may be fragmented and their contours may be irregular. This work proposes a framework based on machine learning and computer vision that enables an AUV equipped with a down-looking camera to autonomously inspect the boundary of P. oceanica meadows to obtain an initial estimate of the meadow size. The proposed boundary inspection solution is composed of three main modules: (1) an image segmentation relying on a Mask R-CNN model to recognise P. oceanica in underwater images, (2) a boundary tracking strategy that generates guidance references to track P. oceanica contours, (3) a loop closure detector fusing visual and navigation information to identify when a meadow boundary has been completely explored. The image segmentation model and the visual part of the loop closure detection module were validated on real underwater images. The overall inspection framework was tested in a realistic simulation environment, using mosaics obtained from real images to replicate the actual monitoring scenarios. The results show that the proposed solution enables the AUV to autonomously accomplish the boundary inspection task of P. oceanica meadows, therefore representing an effective tool towards the conservation and protection of marine environments.

Обеспечение экологической безопасности акваторий Российского арктического шельфа и повышение безопасности морских экосистем за счет снижения шумового загрязнения

Object and purpose of research. Ensuring the environmental safety of the Russian shelf waters requires constant development of methods and technologies related to monitoring, quantitative assessment and reduction of the harmful effects of pollution sources. During the industrial and transport development of the water area of the Northern Sea Route (NSR), an intensive increase of underwater noise is observed. Obtaining an adequate picture of the impact of underwater noise sources on representatives of the marine ecosystem creates a need to involve more and more modern and accurate measurement techniques. The article describes the draft methods for measuring the self-noise of carrier vessel and underwater noise of a selected marine equipment object, which were developed in order to identify the degree of impact of noise pollution over to the ecological situation in the considered water area. Materials and methods. An hydro acoustic signals contains the self-noise of measuring vessel, the noise of an object of marine industrial equipment (OMIE) and the noise of the water area where acoustic tests are going on. This acoustic signals are perceived by combined sound pressure and sound pressure gradient transducers, as well as by an omnidirectional hydrophone, located in the receiving system , and are converted into electrical signals transmitted via the main cable to the onboard post of the measuring vessel. Signals are sent to the hydro acoustic guidance beacon via the same cable to control the operation of this beacon. The information processing procedure is set out in the SIGAK VP Operation Manual (MGFK.411711.327 RE). The main purpose of the primary processing is to obtain 1/3-octave spectra and levels of underwater noise generated by the tested carrier vessel or OMIE, as well as the noise of the water area where these tests are carried out. In accordance with the accepted classification, the method of measuring sound pressure levels using a hydro acoustic complex according to this technique refers to indirect methods with single observations. Main results. In the course of the work, preliminary methods for measuring the self-noise of measuring vessel and underwater noise of a selected marine industrial object were developed. To measure the levels of underwater noise in 1/3-octave frequency bands in the range from 5 Hz to 10,000 Hz, within the framework of the draft methods, it is planned to use a stationary measuring hydro acoustic complex with a vector receiver from the GIK-VP. The signal processing algorithms are based on the spatial-frequency filtering of the acoustic power flux density components, which makes it possible to protect the measurement information from interference signals whose propagation direction does not coincide with the direction to the measured object. Conclusion. The results obtained in the form of implemented preliminary methods are important for the creation of regulatory documentation for the regulation of technogenic underwater noise in the waters of the Russian jurisdiction, reducing the intensity of noise pollution and the detrimental impact over to marine ecosystems. The article targeting the support at the stages of acoustical marine technical design, construction and operation of offshore industrial facilities and ships of various types, acoustic monitoring of the compliance of marine equipment with international standards for underwater noise.

Statistical modeling of the space–time relation between wind and significant wave height

Abstract. Many marine activities, such as designing ocean structures and planning marine operations, require the characterization of sea-state climate. This study investigates the statistical relationship between wind and sea states, considering its spatiotemporal behavior. A transfer function is established between wind fields over the North Atlantic (predictors) and the significant wave height (predictand) at three locations: southwest of the French coast (Gironde), the English Channel, and the Gulf of Maine. The developed method considers both wind seas and swells by including local and global predictors. Using a fully data-driven approach, the global predictors' spatiotemporal structure is defined to account for the non-local and non-instantaneous relationship between wind and waves. Weather types are constructed using a regression-guided clustering method, and the resulting clusters correspond to different wave systems (swells and wind seas). Then, in each weather type, a penalized linear regression model is fitted between the predictor and the predictand. The validation analysis proves the models skill in predicting the significant wave height, with a root mean square error of approximately 0.3 m in the three considered locations. Additionally, the study discusses the physical insights underlying the proposed method.

Link Adaptation Strategy for Underwater Acoustic Sensor Networks: A Machine Learning Approach

AbstractDue to growing concerns regarding their use in fields including oceanography, commercial marine operations, and military surveillance, demand in the exploration of underwater sensor networks for marine studies has developed. Network channels for underwater sensor network (USN) rapidly change (spatially and temporally) depending on the surroundings. To increase system efficiency by adjusting transmission parameters to channel fluctuations, it is alluring to utilize adaptive modulation and coding (AMC) for USNs. In order to determine the best link adaptation method based on the channel quality, this article focuses on evaluating a measured sea trial dataset utilizing a rule-based approach (i.e., three-dimensional evaluation, modulation-wise analysis, and a fixed-SNR strategy). To determine the optimum AMC combinations in terms of channel adaptively, we draw a situation of the measured USN data rate versus Bit Error Rate (BER) and Signal to Noise Ratio (SNR). The work further extends to apply machine learning (ML) methods to identify the MCS levels by looking into the channel characteristics due to the non-reversibility limitation of the rule-based strategy. One of the ML methods we used for the investigation, gradient boosted regression tree (GBRT), exhibits impressive accuracy of 99.988% in classifying MCS levels. The MCS levels are related to channel statistics and signal characteristics, particularly those that are susceptible to SNR and BER limitations, using an ensemble of trees that learns from the buoy and base station’s uplink data.

Assessment of expected production of a deep‐sea mining system: An integrated model‐based systems engineering and discrete event simulation approach

AbstractIn this paper, model‐based systems engineering (MBSE) and discrete event simulation (DES) are combined to assess the performance of an offshore production system at an early stage. Various systems engineering tools are applied to an industrial case concerning the retrieval of deep‐sea minerals, and a simulation engine is developed to calculate the annual production output. A mean production of 1 Million tonnes of ore per year is estimated for an operation in the Norwegian Sea using Monte Carlo simulation. Depending on the limiting design wave height of the marine operations, the estimated production output ranges from 280,000 tonnes to 1.8 Million tonnes per year. The constrained parameter of the production system is particularly the wave height operational limit of the ship‐to‐ship transfer operation. We present the learning outcome from applying MBSE and DES to this case and discuss important aspects for improved performance.

Evolution Wave Condition Using WAVEWATCH III for Island Sheltered Area in the South China Sea

Wave conditions around islands in the South China Sea (SCS) are of significant interest due to their importance for marine operations and coastal engineering. Understanding and accurately predicting wave characteristics in this region are crucial. In this study, the third-generation wave model WAVEWATCH III is employed to examine wave conditions around islands in the SCS. According to the water depth and significant wave height, the sea state around the island was classified into two categories: typhoon sea state and moderate sea state. Several popular wind input–dissipation source terms (ST2, ST4 and ST6) are used to assess the typhoon sea state and the moderate sea state separately. The results are validated by field wave data. ST4 and ST6 show good performance in significant wave height for moderate sea states, while ST2 is good at the mean wave period. For the typhoon sea state, ST2 gives the best results in significant wave height with larger correlation coefficients and a smaller RMSE. The above results provide valuable insights into the effects of different source terms on the accuracy of wave simulations for different sea states. The spatial distribution of the significant wave heights is also demonstrated with ST2, which may be useful for assessing the wave conditions of marine structures from the large scale of the SCS to the island scale of the Yongle Atoll.

Motion control for an open-frame work-class ROV in current using an adaptive super-twisting disturbance observer

Remotely operated vehicle (ROV) plays an important role in marine operation and maintenance for offshore facilities. Motion control design is one of the major challenges in the development of ROV, especially when the ROV is subjected to unstable sea currents, parametric uncertainty, hydraulic delay, and thrust saturations. In this study, an open-frame work-class ROV used for offshore structure surface cleaning is considered. The dynamic model of the ROV is established, based on the hydrodynamic properties obtained from CFD simulations. A sliding mode controller is designed for the ROV trajectory tracking, which is developed by the command filtered backstepping method. An adaptive super-twisting disturbance observer is employed to estimate and compensate the loading disturbances and modeling uncertainties. Stability analysis is performed and proves Lyapunov stability of the proposed controller. The effects of current, dynamics of the hydraulically-driven propellers, and thrust saturation are rigorously taken into account in this study. Various simulation cases are conducted using the Simulink software. The results have demonstrated that the superior robustness of the proposed control design against thrust saturation, modeling errors, and external disturbances.

Design of a decision support system to achieve condition-based maintenance in ship machinery systems

A decision support system is proposed for the condition-based maintenance of ship machinery systems based on the adaptive neuro-fuzzy inference system (ANFIS) approach. A case study is conducted for a container ship's main diesel engine. Within the scope of the methodology, the main engine power is predicted based on exhaust gas outlet temperatures of cylinders and the main engine shaft RPM. In this regard, firstly, two different strategies such as the creation of the cylinder-basis model and the development of the overall system model are developed to determine the ANFIS model structure for the analysis. Then, comparative analyses are carried out to select a suitable ANFIS structure and its specific membership functions. In addition, the estimation process is also performed by the artificial neural network (ANN) model, and its results are compared with the findings of the best ANFIS structure. The success of the constructed models is evaluated by some error metrics. The overall ANFIS model with 5 membership functions is determined as the best approach by scores of 0.9806 for R2, 1.6588 MW for RMSE, and 3.2703 for MAPE. As a result of the estimation procedure, a decision support system to assist marine operators in maintenance operations is developed. The proposed strategy can be applied to different types of systems in the ship engine room such as the fuel oil system and can be improved by including more parameters obtained from the system's significant points in the analysis.