An existing initiative to connect data on experiments, methods and teaching from a Southern hemisphere university (Stellenbosch) and Northern hemisphere (NTNU) is presented. The work supports open access and common technologies with the catch of fieldwork in the proximities of the Antarctic and Artic poles. The paper discusses the motivations and existing experiments that will be openly available, other sources of data and lastly an architecture for the C-Room – a cyber-physical classroom where separate and remote activities can be digitally merged to benefit stakeholders across the globe. It closes with a call for peers to join the initiative.

Facing the increasing quantity and richness of data related to modeling and simulations of maritime systems, advanced solutions that can maintain data coherence and traceability are becoming increasingly beneficial. In the context of modeling complex systems, such as ship design, retaining connections of systems data, whether quantitative or qualitative, helps to provide a traceable and comprehensive view of the vessel at various stages of its development. This paper explores the use of graph databases to help provide such connections and introduces various domains of systems data that would be advantageous to link via graph theory. Additionally, this paper explores how graph databases compare to current flat file databases in a practical sample case of multi-domain data related to ship concept design.

We present, here, a compilation of attempts to use computer vision technology in the maritime field. The scope is mostly in reverse engineering, that is, get- ting information about an existing physical system and modelling it digitally, extracting information from images and videos. The paper starts with a broad defi- nition of computer vision, and how it can be adapted to reverse engineering. It is followed by a modest lit- erature review of cases in the maritime sector, namely photogrammetry, inspection and. Later, it describes a recent project supervised by the first author, using commercial software to re-model digitally the hull of a small sailing boat. The use of open-source tools is later mentioned, exemplified by the research con- ducted by the second author on the use of cameras as sensors for acquiring dynamic data, closing the dig- ital twin loop. A proposal for the use of image data extraction is presented at the end, as a substitute for the expensive re-sensoring of vessels in operating, in the current hype of remote operation and digital twins. We conclude by emphasizing the potential of this tech- nology for the transition from conventional to remote and autonomous operations.

This paper presents an overview of a CFD Opensource tool and its applications in industry and academia. A study case of a cruise ship flooding simulation is presented to show its capacity. To ensure the reliability of the results, a grid convergence analysis was performed and compared with benchmark data provided by FLARE, a European consortium that provided open data on flooding benchmarks. Additionally, general arrangement layout modifications were tested. The main corridor width was changed, and water elevation probes were placed in different rooms to evaluate the change in the corridor width. Results showed that when the corridor width increases, the time to flood reduces for the rooms far from the breach. This behavior was opposed to the room near the breach, requiring a longer time to fill the room as the corridor width increased. The study case showed that studies with small variations could be important for ship design purposes, for instance, and doing that in experimental facilities is expensive, showing the necessity of good numerical free and open-source tools, such as OpenFOAM.

This paper describes how application of Machine Learning (ML) in Product Lifecycle Management (PLM) system results in reducing time of engineering change order (ECO), i.e., implementation of the design change’s effects, and thus, improving the responsiveness of the manufacturing system. A current challenge in PLM system is the long duration of engineering change process from when a component in product’s design is changed until when the change is reflected in the manufacturing operation in which the component is consumed. This paper proposes that application of supervised ML, using classification method and a basic neural network algorithm, on 3D graphic design of a product, helps PLM system to predict and locate the placement of the design change in corresponding manufacturing operation faster than the current manual status quo. The model-based structure of such application highlights the practical steps in data preparation, training process, and evaluation of the model in PLM system environment. Throughout the way, the feature, extracted from the digital format of the product design, i.e., 3D graphics, is labelled by its correspondence to the operation in which it is consumed, and sent through the neural network algorithm to train it over such correspondence. The satisfactory result of the evaluation is reflected by learning curve and confusion matrix. With use of data from offshore wind turbine’s (OWT’s) hub in Siemens Gamesa Renewable Energy’s (SGRE’s) PLM system, this study denotes the logic behind such application, the methodologies, and frameworks, which are reusable in any typical manufacturing system supported by PLM system. Although, for the utilization of the trained model, there are still some hurdles to overcome. The paper concludes with highlights of challenges, risks and limitations of the model helping other industries to predict potential challenges and realistically estimate the required budget for such implementation.

Hydrodynamic simulation of marine structures is a complex and time-consuming task that requires large, refined models to accurately estimate the behavior of ships. During the conceptual phase, therefore, these estimations may be more efficient if done with a mix of surrogate models and simplified simulations. We believe that AI and the web environment can contribute to providing a more precise answer and fast solution, especially when the design domain can be narrowed and properly estimated. This paper shows an attempt in this direction, describing a web-based real-time flow simulator that is composed of a Tenforflow.js-based convolutional neural network model with an image-based hull form representation. Some case studies demonstrate the advantages of a novel web-based prototyping environment in the conceptual and initial design of ships. The image-based hull form representation method with a convolutional neural network enables the design of not only main dimensions but also local shapes in an interactive web-based concurrent engineering environment. Our approach extends the neural network model of wake flow estimation to models of the prediction of resistance and pressure distributions on the hull surface and develops a novel web-based prototyping environment for the conceptual and initial design of ships.

This paper highlights technical and practical challenges that the authors have faced to create a digital twin (DT) of a piece of manufacturing system, that is production process (i.e., assembly process) to serve system responsiveness (i.e., agility) in an offshore wind turbine manufacturing. It discusses the elements and architectural parameters in development of an agile manufacturing system, where DT of shopfloor and its practical setup is seen as a design element enabling agility in an industrial system. Currently, there is no detailed framework to describe how industries can practically benefit a DT of their production process in a way that their manufacturing systems becomes responsive to perturbations, and ultimately agile. More importantly, there is no detailed study to show potential challenges and their implications during deployment of such a DT. In absence of such a study, this paper proposes a configuration and practical architecture, customized for Siemens Gamesa Renewable Energy’s (SGRE’s) offshore wind turbine (OWT) manufacturing system, that denotes the logic behind such framework for reuse of DT in any typical manufacturing system along with its practical implications, helping other industries to predict potential challenges and estimate realistically the required budget for such implementation. The proposed model-based structure is built up based on the benchmark commonalities and differences of the known developed DT models in manufacturing and production context, incorporating the existing physical and virtual spaces in SGRE’s OWT manufacturing system, complemented by supplementary systems and software applications from existing technologies in market. The paper concludes with thoughts on a pilot project in production line of an OWT’s generator unit that is under development to verify such a design.

A case on rapid prototyping is presented in this work to exemplify the use of learn, make and share activities to promote maritime studies. SMARTBOAT is an initiative from the Escola Superior Náutica Infante D. Henrique, in Portugal, where students are invited to interact with computer-aided design modelling, additive manufacturing and programming. Such initiative is paramount to instigate and promote higher education studies in science, technology, engineering, art, and mathematics (STEAM). The initiative is presented and discussed, with its main steps and schemes. A step forward is later discussed by the ongoing collaboration with the Norwegian University of Science and Technology (NTNU, Norway), which intend to combine the Portuguese case with recent advancements in robotics and digital twin, such as remote operation via internet of things protocols and web-based tools. The work ends with a discussion on the results and future works on autonomous shipping, as well as a call for the development and sharing of similar initiatives.

This paper presents an initial study on the task of automating the sorting of crates. It was paramount in the study that the technology used for the automation process is already existing and available to the client in Norway; therefore an existing pallet sorting system was used as state of the art. The simulation was performed via a stepwise approach, that is, first we simulated the process as it is now. Based on this manual case we simulated the same system under a new automated task at time, until the final case (close to) fully automated. A set of KPIs was defined and used in the assessment of all cases, including the manual one. These are Opex [NOK], Capex [NOK], Reliability [Stops over time], Robustness [%, Probability of consequence], and Efficiency [crates per hour]. Our finding overall is that the time it took to sort a given number of crates decreased with increasing implementation of automation through the various change cases. With reduced time consumption the efficiency and number of crates per hour increased, from 300 in the manual case, to 1200 in the fully automated case. The increase in automation also resulted in increased costs, both capital- and operating costs. If we look at the cost increase in relation to the capacity increase, the cost per sorted crate decreases by about 50%. The manual process sorts 300 crates per hour, and if we look at the cost per sorted crate, the fully automated case must sort 600 crates per hour to breakeven and justify the automation.

We propose the use of existing data standards and web technologies to modeling and development of digital twin ships. Our research provides an open framework that can be linked to services such as visualizations, simulations and remote control. The case study applies the standards-based framework to an experiment that involved a scale model ship equipped with a dynamic positioning system under artificial waves. The digital twin prototype illustrated the capability of mirroring and controlling the model’s position in real-time, and predicting motion responses across wave conditions via a web application. Thus, it closes the loop between test and design in the life cycle by allowing validation of results in comparison to empirical data during operation. The results from these experiments are used to discuss an expanded version of the digital twin for validation and optimization of motion response, as well as its implications to the system’s (ship) taxonomy and data management. The conclusion summarizes lessons when using the adopted standards, as well as challenges when scaling the approach to real life operations. Future research is proposed toward extending the standardization to more complex cases.

This paper discusses how Product Life-cycle Management (PLM) tools can benefit the ship design process. Primarily, the concept of PLM applied to ship design will be decomposed in six key elements: database, modeling and simulation tools, value chain processes, product hierarchy management, product management and project management. Some of these elements rely heavily on the use Virtual Prototyping to be achieved. The next step applies these concepts to the ship value chain. This will be done through the development of a simplified scenario, where it is discussed how a vessel can be conceived and designed using an integrated design platform, applying PLM methods. Most of the information previous to product finalization is obtained through simulation of virtual models, using virtual prototype concepts. Our assumption is that combining PLM techniques with virtual prototype concepts enables a good control over the ship design project as a whole, through means of efficient modelling and simulation management. That way, the time and cost necessary for the product development can be reduced.

This paper proposes a modular approach as a technique to enhance Virtual Prototype (VP) in conceptual ship design. The methodology proposes a preliminary modular ship division, which is made according to the ship systems functionality. The modules obtained from ship division are analyzed in relation to how they interact among themselves (compatibility) as well as how relevant they are for the efficient performance of a mission (performance). An entity model is virtually assembled and evaluated, feeding an application that is able to simulate all possible module’s arrangements and list the better ones regarding the customer requirements. In doing so, we ended up having a ship modularization methodology, an application to handle the assemble process using VP, and a methodology to evaluate how suitable an entity model is for accomplishing a mission. The approach is exemplified through a preliminary offshore support vessel case, where the methodology is implemented in a preliminary virtual prototype application, which enables the parameters and requirements set, assisting the assembly process, visualizing the modules as well as the entity, electing the most suitable arrangement for the initial conditions established by the user.

The ship design activity often requires handling and storage of large amounts of data related to different systems inside the vessel, demanding for a structured way to organize it. This article suggests an object-oriented approach to handle virtual prototyping data during conceptual ship design. We start presenting some of the basic concepts related to objects, such as name, property and value. A proposal based on the entity, state and process models is addressed for the virtual prototyping, related to the object-oriented approach. Later, we use the SFI group system as hierarchy structure to represent the ship as an entity and state model. We finish by presenting some simple examples of the proposed approach with a modular ship models and introducing one suggestion of a virtual prototyping model using the concepts presented thorough the paper.