Onboard Ships Research Articles

Prediction of tidal-driven currents using convolutional neural network

Efficient forecasting models of coastal currents are required for the predictive control of smart vessels with autonomous or remote operating capabilities. Accurate physics-based numerical models demand computational resources that often are unavailable onboard ships; moreover, internet bandwidth at remote locations might not be sufficient to exchange the large computational files with onshore servers. In this case, light and efficient Data-Driven Models (DDM) may be developed to be used as a surrogate for a physics-based model.Currents and surface elevation are hydrodynamic variables driven by astronomic tide potential, allowing for harmonic analysis and synthesis of otherwise irregular solutions of Navier-Stokes equations. Once numerical solutions are obtained and analysed in the Fourier domain, the identified harmonics (tide constituents) can be used as a dataset to train the DDM. One approach to building a DDM is by utilizing a Convolutional Neural Network (CNN).CNN is mainly applied in image recognition processes, where it learns the spatial features of image matrices of pixels arranged in columns and rows and uses the learned features to predict an output. This approach can be applied to 2D or 3D fields of predominantly tidal-driven coastal currents. This paper extends the CNN framework to approximate and predict coastal hydrodynamic state variables in space and time. The depth-averaged Navier-Stokes equations were used to create the dataset necessary to train the adopted CNN autoencoder architecture.Two methods of CNN model development are explored. The first method assesses CNN’s capabilities for time forward prediction, using 2D time series of hydrodynamic variables. The second method investigates CNN’s parameter (using Manning number) prediction ability using 2D spatial plots formed by the top 20 most energetic tidal constituents that were obtained from the numerical solution. The hyperparameters of the CNN model for both methods were carefully optimized and tuned using the loss function, Root Mean Square Error (RMSE). The coefficient of determination, the relative error of the time series, and its amplitude and phase were used to gauge the performance of the CNN model for both methods at the final testing stage.Once accurate solutions are achieved, the trained DDM is almost instantaneous and uses negligible computational resources as compared to traditional fluid solvers. Therefore, trained DDM can be deployed onboard ships where global forecast information (e.g., from Global Forecast System) can be used to provide an accurate prediction of the current forcing. To generate the instantaneous current predictions for navigation and smart ship control, the global data can be pulled or pushed to the ship before the mission.

Situational Approach of Teaching Speaking Maritime English in Merchant Marine Polytechnic of North Sulawesi

English communication skills in the areas of speaking, listening, reading, and writing. However, in many students' minds communication means only interaction between the speaker and the listener. Teaching English at maritime universities and nautical colleges involves not only teaching the language and the sea-related terminology but also making the students aware of the cross-cultural issues and problems that they may encounter in their work onboard ships. The best way of teaching is, how the teacher, instructor, and lecturer can choose and use the right teaching method. FAIES is one of the unique and well-known methods in teaching which can adapt to many situations in the classroom and makes the students feel easy to understand and study comfortably during the lesson especially in speaking English. According to Freud in Wollheim (1981), FAIES (First Aid in English System) is the teaching method to emphasize or stress communication, which consists of a directional approach, functional approach, situational approach, and drilling technique. Maritime English is largely restricted to IMO Standard Marine Communication Phrases, which build basic knowledge of English and had been drafted in a simplified version of maritime English. In terms of maritime education, the current simulator-based studies can be divided into two areas: marine engineering and nautical science. In particular, human factor specialists work in these two fields addressing issues concerning the relationship between humans and technology, such as simulators (Lützhöft et al. 2017). A multitude of new methodologies has been explored and discussed in recent years in an attempt to approach the training and testing of the proficiency of maritime English that meets the international standards laid out in STCW.

Carbon footprint and cost analysis of renewable hydrogen-fuelled ships

ABSTRACT The International Maritime Organization proposes several strategies to eliminate the adverse effects of ship emissions. The most important is finding alternative fuels, such as hydrogen. The current paper aims to compare diesel and renewable hydrogen-powered ships using Life Cycle Assessment (LCA) and Life Cycle Cost Assessment (LCCA). As a case study, three different ships sailing in the Red Sea area are investigated. The environmental outcomes are presented in terms of global warming potential (GWP), photochemical potential, eutrophication potential, particulate matter and acidification potential. Producing hydrogen fuel onboard ships will increase the total carbon footprint by 10%–28% higher than the currently used diesel fuels. Economically, the cost-effective target will be achieved at the cost of hydrogen production by electrolysis below 5.15$/kg.

Solvents for Membrane-Based Post-Combustion CO2 Capture for Potential Application in the Marine Environment

Carbon capture on-board ships represents a powerful technological measure in order for the shipping industry to meet the very stringent GHG emission reduction requirements. Operation within the ship environment introduces a number of constraints associated mainly with space, energy supply, and safety which have to be addressed using compact yet efficient solutions. To this end, solvent-based membrane CO2 capture offers several advantages and has the necessary technological maturity for on-board installation. Solvent choice remains a critical issue both for reasons associated with process efficiency as well as on-board safety. In this paper, we present an up-to-date comprehensive review of the different solvents that can be used for post-combustion CO2 capture. Furthermore, we investigated the solvents’ performance as determined by their inherent characteristics, properties, and behavior for a range of operating conditions against the strict shipping requirements. A preliminary qualitative comparative assessment was carried out based on appropriately selected key performance indicators (KPIs) pertinent to the requirements of the shipping industry. The identified solvent classes were compared using the most critical KPIs for system integration with the ship. It was concluded that at present, no solvent category can efficiently address all the requirements of the ship. However, widely used solvents such as secondary amines showed relatively good compatibility with the majority of the introduced KPIs. On the other hand, more recently developed molecules, such as phase change solvents and ionic liquids, can easily prevail over the vast majority of the identified solvents as long as they are brought to the same level of technological maturity with benchmark solvents. Such a conclusion points toward the need for accelerating research on more tailor-made and performance-targeted solvents.

D-S evidence based FMECA approach to assess potential risks in ballast water system (BWS) on-board tanker ship

Ballast water is essential for cargo ships since it stabilizes vessels at sea. Most ships are equipped with a ballast water system (BWS) to maintain safe operating conditions. This paper attempts to perform a risk assessment for the BWS on-board tanker ship as it poses a major threat to the operational safety of the ship, marine environment, and cargo. To achieve this purpose, the paper utilizes a robust methodology integrating D-S evidence (Dempster-Shafer) theory and FMECA (Failure mode effects and criticality analysis). In the methodology, while the D-S evidence theory introduces a proper mathematical framework to handle epistemic uncertainty in the assessment of risk parameters and to prioritize failure modes as intended, the FMECA is capable of evaluating system potential failures and their causes. Hence, the risk priority number (RPN) can be calculated to assess potential hazards and their consequences in BWS on-board ships. Besides its theoretical insight, the paper contributes to marine safety inspectors, safety researchers, and HSEQ (Health, Safety, Environment, and Quality) managers to identify potential hazards, effects, and consequences in case of BWS failures on-board tanker ships.

0163 The Differential Relationship Between Berthing Habitability, Job Stress, and Workload on Self-Reported Sleep Deficiency in a Representative Sample of Sailors Attached to U.S. Navy Warships

Abstract Introduction Berthing habitability factors (e.g., noise, temperature, lighting) and workload are known to negatively impact sleep for Sailors serving onboard United States (U.S.) Navy warships. However, it is unknown what factors have the strongest relationship with sleep outcomes. Using data from a representative sample of warships, the relationships between berthing habitability, job stress, and workload on sleep were explored. Methods Participants (N = 3,313; 84% ≤ 35 yrs, 55% white) from 33 warships voluntarily completed an online survey. Using structural equation modeling, latent factors of workload, job stress, and berthing habitability were modeled to test relationships with self-reported sleep deficiency. Sleep deficiency was calculated by dividing the sleep obtained on their ship (“How many hours of sleep (to include naps) per day do you get when sleeping onboard your current ship?”) by their required sleep amount (“How many hours of sleep do you require to feel well-rested?”). Job stress was modeled with three scores from questions related to job stress (1=strongly disagree, 5=strongly agree). Habitability was modeled by the degree in which environmental factors disturbed sleep (1=not at all, 5=extremely). Workload was modeled by the hours completed performing job-related tasks (e.g., work center, watch team, training, meetings). Results On average, participants reported shorter sleep durations on their ship than they require (Ship: 5.2±1.4 hrs; Required: 7.0±1.3 hrs, mean±SD). Overall, habitability, job stress, and workload were negatively related to sleep deficiency (standardized βs=-0.16 to -0.26, ps < 0.001, CFI/TLI > 0.90, RMSEA=0.056). Among all latent constructs, larger coefficients were found for the direct path from workload to sleep deficiency than those from habitability (β1=-0.16 vs β2=-0.12). Additionally, watch team duties loaded most heavily onto the construct of workload, suggesting that it contributed most to the relationship of workload with sleep deficiency. Conclusion These results confirm that workload and berthing habitability are related to sleep deficiency in Sailors while serving onboard U.S. Navy Ships. Additionally, greater workload may have a stronger relationship with sleep deficiency than other factors such as habitability. Future research should utilize objective measures of sleep and workload to better estimate their relationships with sleep. Support (If Any) Military Operational Medicine Research Program (MOMRP) under work unit no. N2010.

“I am not considered much of a polygamist”: Sarah Peterson Lund Writes to Her Missionary Husband

“I am not considered much of a polygamist”: Sarah Peterson Lund Writes to Her Missionary Husband

증강현실 모델 위치 정합 활용을 위한 기계학습 기반의 선박 블록 윤곽선 검출 연구

As interest in autonomous ships is growing, research on augmented reality-based remote support systems that can be used onboard ships is being conducted. The markerless method is more suitable than the marker method because corrosion and damage can easily occur in the ship. However, in the case of the markerless method, a process of selecting a desired feature point is required, but it is not easy in a complicated ship. Therefore, in this study, the outline detection system was studied to utilize the outline as a feature point for augmenting the augmented reality model. Although many existing studies have preceded it, it is not suitable for detecting the contour of a ship block with many internal and external components. Therefore, in order to overcome the limitations of the previous method, in this study, to detect only the outline of a ship block, a model was built through CNN, GAN, and Segmentation algorithm, which are deep learning techniques widely used in image processing, and block outline detection was performed. It is also expected that these results will help automate and optimize the stockyard management system.

Authentic assessment and academic performance of Marine Engineering students: A correlational study

Authentic assessment can validate Marine Engineering students’ competency in academe to be fully equipped with knowledge, understanding, and skills needed onboard ship. This descriptive-correlational study aimed to ascertain Marine Engineering students’ authentic assessment and academic performance on professional courses and their relationships to formulate an intervention program. Utilized for data gathering was a self-administered structured questionnaire on Authentic Assessment aligned to the course syllabus of three (3) major courses. The computer-processed statistics used were mean, frequency, and rank for descriptive analysis; and Pearson Product-Moment Correlation or Pearson r for inferential analysis. Alpha level was set at 0.05. The study found that Marine Engineering students recalled lessons and performed well during validation of skills. In addition, there was a significant relationship between the authentic assessment results and the academic performance shown on professional courses. The performance of Marine Engineering students in the classroom is likely to affect their performance during skill validation in authentic assessment. Therefore, well-performing students in the classroom are likely to pass authentic assessment. Finally, an intervention program, “bUligAnay Kita: A Peer Tutoring Program,” aims to improve Marine Engineering students’ basic knowledge, understanding, and skills in all major courses in preparation for onboard ship training.

Lite-YOLOv5: A Lightweight Deep Learning Detector for On-Board Ship Detection in Large-Scene Sentinel-1 SAR Images

Synthetic aperture radar (SAR) satellites can provide microwave remote sensing images without weather and light constraints, so they are widely applied in the maritime monitoring field. Current SAR ship detection methods based on deep learning (DL) are difficult to deploy on satellites, because these methods usually have complex models and huge calculations. To solve this problem, based on the You Only Look Once version 5 (YOLOv5) algorithm, we propose a lightweight on-board SAR ship detector called Lite-YOLOv5, which (1) reduces the model volume; (2) decreases the floating-point operations (FLOPs); and (3) realizes the on-board ship detection without sacrificing accuracy. First, in order to obtain a lightweight network, we design a lightweight cross stage partial (L-CSP) module to reduce the amount of calculation and we apply network pruning for a more compact detector. Then, in order to ensure the excellent detection performance, we integrate a histogram-based pure backgrounds classification (HPBC) module, a shape distance clustering (SDC) module, a channel and spatial attention (CSA) module, and a hybrid spatial pyramid pooling (H-SPP) module to improve detection performance. To evaluate the on-board SAR ship detection ability of Lite-YOLOv5, we also transplant it to the embedded platform NVIDIA Jetson TX2. Experimental results on the Large-Scale SAR Ship Detection Dataset-v1.0 (LS-SSDD-v1.0) show that Lite-YOLOv5 can realize lightweight architecture with a 2.38 M model volume (14.18% of model size of YOLOv5), on-board ship detection with a low computation cost (26.59% of FLOPs of YOLOv5), and superior detection accuracy (1.51% F1 improvement compared with YOLOv5).

Contributing Factors and Strategies Applied Onboard Ship: Basis for Development of Booklet to Enhance Seafarers’ Mental Health

Contributing Factors and Strategies Applied Onboard Ship: Basis for Development of Booklet to Enhance Seafarers’ Mental Health

Mental Health of Filipino Seafarers: The Contributory Factors and the Strategies Applied Onboard Ship

Mental Health of Filipino Seafarers: The Contributory Factors and the Strategies Applied Onboard Ship

Response Surface Methodology for 30 kW PEMFC stack characterization

Hydrogen is a promising energy carrier to allow the reach of the zero-emission targets established for the next years. Polymeric Electrolyte Membrane FC are studied inside the HI-SEA laboratory of the University of Genoa, to assess the opportunities of this technology on marine applications. Here, 8 PEMFC stacks, sized 30 kW each for a total power installation of 240 kW, have been tested to draw guidelines for the best system design onboard ships and to deepen the know-how on the experimental management of the technology. During the tests, it was possible to observe the reciprocal influence of some parameters, which may influence the system efficiency. In this work, a statistical investigation is developed to quantify the cell voltage variation correlated to the values of temperature and current. This has been possible thanks to Design Expert (DE), a software developed by Stat-EASE, Inc. Through the Design of Experiment approach, it is possible to evaluate the significance of variables in the FC system, called factors. The experiment under consideration is also characterized by non-controllable factors, cause of disturbances that induce further variability in the response. Eventually, it was possible to analyse the significance of the parameters involved, to build a regression model by performing the analysis of variance with which the significant values are identified, and to assess the presence of outliers.

AN ICOR APPROACH TOWARDS SHIP MAINTENANCE SOFTWARE DEVELOPMENT

Ship maintenance is one of the key processes to improve system performance and reliability onboard. Maintenance onboard ships is required to be performed in a planned manner because safe and efficient operation of a ship is very much depending on equipment reliability in operational level. A planned maintenance system (PMS), mainly supported with software, is established to monitor the maintenance implementations on board ships. This study aims to assess the effectiveness of onboard maintenance and limited with the procedures and specific softwares employed for the maintenance on board. Specifically, the process analysis approach is developed to execute the existing ship PMS phases based on four dimensions such as input, control, output, resources (ICOR). Besides the critical points to be improved in ship maintenance, this research reveals recommendations to increase the functionality of selected software in terms of workload balance, smart scheduling and safe working environment. To demonstrate the functional improvements, an illustrative case study on an auxiliary diesel generator maintenance routines are conducted. The contributions of the study are expected in both ship operations management and marine software development.

Assimilation of shipborne precipitable water vapour by Global Navigation Satellite Systems for extreme precipitation events

AbstractWater vapour advection from the sea causes extremely heavy rainfall in Japan. Therefore, accurately describing the water vapour distribution over the sea in a forecast model's initial conditions should improve the prediction accuracy of heavy rainfall events. Thus, we assimilated the shipborne precipitable water vapour (PWV) observed by the Global Navigation Satellite Systems (GNSS) onboard ships to show its impact on a heavy rainfall event in July 2020. We obtained the GNSS observations during a continuous water vapour observation campaign conducted at sea, one of the few in the world. In this study, we applied the shipborne PWV, on the upwind side of the heavy rainfall, to the four‐dimensional variational data assimilation method and conducted assimilation–forecast cycles. Although the shipborne PWV is a point observation, it can be assimilated as observation data covering space and time because the ships conducting the GNSS observation sailed around Japan. In addition, in the assimilation–forecast cycle, the effect of assimilation spread widely over the forecast area. Although the ship motion affects the shipborne observations, we found that the impact on PWV assimilation is negligible for practical use. For the temporal thinning of the data assimilation slot for the shipborne PWV, an interval of 30 min is more effective than an interval of 1 hr. As a result of assimilating this shipborne PWV on the upwind side of the disastrous heavy rainfall of July 2020, the forecast accuracy of rainfall, especially rainfall amount, was improved. We also found that statistical improvements could be obtained from the water vapour profiles and wind velocity field in the lower atmosphere. We demonstrate that the assimilation of shipborne PWV observations can improve the prediction accuracy of heavy rainfall events.

Numerical study on modelling perforated elements using porous baffle interface and porous region

PurposeThis study aims to analyze simplified methods for modelling the flow through perforated elements (i.e. porous baffle interface and porous region), searching for a faster and easier way to simulate these components. The numerical simulations refer to a muffler geometry available in literature as a case study.Design/methodology/approachThe installation of scrubber onboard ships to satisfy the International Maritime Organization emissions regulations is a reliable and efficient solution. However, scrubbers have considerable dimensions, interfering with other exhaust line components. Therefore, scrubber installation in the funnels requires integration with other elements, for example, silencers. Perforated pipes and plates represent the main elements of scrubber and silencers. The study of their layout is, therefore, necessary to reduce emissions and noise. Numerical simulations allow evaluating the efficiency of integrated components.FindingsThe study highlights that velocity and pressure predicted by the simplified models have a strong correlation with the resistance coefficients. Even though the simplified models do not accurately reproduce the flow through the holes, the use of such models allows a fast and easy comparison between concurrent muffler geometries, giving aid in the early design phases.Originality/valueThe lack of general guidelines and comparisons in the literature between different modelling strategies of perforated elements supports the novelty of the present work and its impact on design applications. Study the flow inside scrubbers and mufflers is fundamental to evaluate their performances. Therefore, having a simple numerical method is suited for industrial applications during the design process.

A probabilistic risk assessment for asphyxiation during gas inerting process in chemical tanker ship

Gas inerting process is a great hazard for chemical tanker ships and utmost care is required considering the harmful effects to humans’ health. Most of the chemical tanker ship-owners face near-miss or accident (asphyxia/fire/explosion) during gas inerting process on-board ship. The consequences of the process may pose catastrophic results such as explosion, fire or asphyxiation. Therefore, a detailed risk assessment is required to enhance the process of safety during the carriage of chemical cargo and minimize potential consequences. To address this concern, the paper aims at conducting a systematic probabilistic analysis of asphyxiation risk during gas inerting process in chemical tanker ship. In the paper, a Bayesian belief network (BBN) method is used to deal with causality and uncertainty arising from the complex interdependence between variables in the probabilistic risk assessment of asphyxiation risk. While BBN enables us to calculate the conditional probability of each intermediate node and leaf node in the graph and perform probabilistic risk assessment with sensitivity analysis, fuzzy logic deals with the translation of linguistic expressions from expert opinion into probability values. The findings of the paper will provide the utmost contribution for chemical tanker ship owners, safety researchers, maritime safety professionals, and HSEQ managers (Health, safety, environment, and quality) to prevent the risk of asphyxiation during gas inerting process in maritime transportation.

Systems-Theoretic Accident Model and Processes (STAMP) approach to analyse socio-technical systems of ship allision in narrow waters

The operating environment of merchant ships is dynamic and complex. Particularly, their engine rooms and bridges have complex structures that contain various equipment. In addition, there is the human factor that manages all this complex structure. The systems on-board ships involve interactions between crew, hardware, and software (man-machine interfaces). As a consequence of the growing complexity of socio-technical systems, traditional accident analysis methods are getting inadequate to analyse the complex systems. The conventional analyses are focused on the chain of events and they have limited ability to overcome non-linear interactions among dynamic and complex system components in maritime transportation. The aim of this paper is to apply a Systems Theoretic Accident Model and Process (STAMP) model for the analysis of a ship allision accident occurring in narrow waters. This is to create a wider view of the accidents rather than a simple chain of events. With the help of detailed STAMP analysis, the dynamic nature of the system, errors in the entire structure, including the human, machine, and software interactions can be analysed. The model also identifies violations of safety constraints at all levels of the control structure, even though the accident involved a complex and dynamic process. The results demonstrate that complex system accidents are not a simple cause-effect chain of events, on the contrary, they are system-based, dynamic, and complex situations. Consequently, the paper tried to reveal all the causes of the Vitaspirit Allison, rather than just one component.

Wheel over point mathematical model

This research proposes an improved mathematical model which can be used to calculate wheel over point (WOP) for a ship's route optimisation. WOP is a marking made on the charted course to demonstrate where the ship must initiate the course alteration to guarantee that it follows the route. The advance transfer technique (ATT) was used to determine WOP. Through practical exercise, two gaps were identified in ATT. From there, an improved mathematical model, namely ATMM, were developed. A preliminary manoeuvring analysis was then carried out in this study using a ship simulator for ATMM and the existing ATT. Then, the cross-track distance produced by both methods were compared to verify the difference. It was found that the ATMM produced better result in maintaining a ship on its course. This research's mathematical model is expected to be used onboard ship and used in the Electronic Chart Display and Information System to aid navigator in making more effective course alteration.

Implementing the dynamic simulation approach for the design and optimization of ships energy systems: Methodology and applicability to modern cruise ships

To reduce the environmental impact of modern cruise ships, a crucial role is played by the recovery of waste heat from onboard diesel generators used to balance part of the onboard thermal energy demand. To maximize the recovered waste heat, this paper proposes a novel design methodology for ships energy systems based on the dynamic simulation approach, suitably enhanced to consider moving objects like ships. Through this approach, partial load regimes due to variable energy requirements and the relative response of innovative energy saving technologies are dynamically assessed by properly considering real cruising conditions as a function of the current ship position along its route. To this aim, 3-D ship envelope models, detailed energy ship-plant system layouts, and algorithms for deriving new customized hourly weather data files are suitably developed in MatLab and TRNSYS. To show the capability and potentials of the proposed methodology, a novel case study referred to an LNG-powered cruise ship traveling in the Norwegian fjords sea is presented. Different thermally and electrically activated technologies are coupled in 16 energy ship-plant system layouts, implementing novel controls strategies for optimizing the exploitation of the waste heat recoveries and cold-ironing. Encouraging results are achieved for the best layout, including primary energy savings of 18.1%, avoided pollutants emissions of 24.4 ktCO2/y, 40.0 tNOx/y, 90.0 tSOx/y, 84.0 tPM2.5/y, and a simple payback of 0.68 years. Finally, the proposed methodology represents a step forward toward the modern early design of onboard ship energy systems useful for ship designers, manufacturers, owners and operators.