July 2023 Edition
Welcome to the Summer edition of the Chart Room! We are thrilled to explore the exciting advancements brought about by Artificial Intelligence (AI) and Machine Learning (ML) in the shipbuilding industry. As vast as the uses and impact of AI & ML are, we will dive into the impact of a few these cutting-edge technologies uncovering how they have revolutionized ship design, robotic process automation, predictive maintenance, and shipyard planning.
Furthermore, discover SSI’s Publisher LT (PLT) – an Enterprise Platform product that provides a non-disruptive solution for easy access to engineering data in ShipConstructor MIM in a consumable format for any stakeholder, streamlining workflow.
For our Rhino 3D designers, we have shared Rhino3Dâs surface Curvature Analysis tip that leverages the Gaussian curvature radius.
Lastly, Innovmarine is embarking on a journey with our new partner Ennovia. Keep reading until the end to explore more about the QuickBrain application and feel free reach out to us if you wish to learn more.
AI and ML Impact on Shipbuilding Industry
So far, we have explored what digital transformation means in shipbuilding and the benefits of a mature digital thread that enables the transformation using I4.0 technologies. Of the various technologies that enable digital transformation, in this edition we are exploring Artificial Intelligence (AI) and Machine Learning (ML) which have been transforming various industries, and the shipbuilding industry is no exception. The integration of AI and ML in shipbuilding has led to significant advancements in ship design, robotic process automation, modeling future “what if” scenarios, predictive maintenance forecasting, and improved shipyard planning and decision making.
Ship Design Optimization
AI and ML have been instrumental in enhancing ship design processes. The development of AI-aided design tools, such as the artificial intelligence-aided design (AIAD) of ship hulls, has enabled more efficient and optimized designs. In this research paper by Ao et al, they developed a Deep Neural Network (DNN) model to improve accuracy in predicting ship hullâs total resistance during the initial ship hull design. It is generally accepted that 70% of manufacturing costs of a product can be derived from design decisions and Machine learning models can be used to create more efficient and innovative ship designs.
Robotic Process Automation
The shipbuilding industry has been increasingly adopting robotics for various operations such as cutting, welding, and painting. The industry is experiencing a lack of skilled welders making automation a necessity to keep up with growing production demands. Automated robots used for robotic welding can not only improve production quality but can also increase efficiency rates for large-scale manufacturing projects, the National Shipbuilding Research Program (NSRP) have been experimenting the computer aided robotic welding (car-w).
There are challenges with this however, as mentioned in this blog by Genesis systems, because the process involves non-repetitive tasks (each product is unique) and the fact that ship designs are becoming increasingly complex. However, there are ways to overcome these challenges, by linking the welding robots with 3D CAD models with offline programming software. Apart from improved capacity, quality, accuracy, and cycle time, robotic automation also enhances productivity and worker safety.
Unanticipated vessel downtime causes operational disruption and will be costly not only for the shipowners but for other key stakeholders in the supply chain as well. Predictive maintenance is a proactive approach that uses historical data, machine learning algorithms, and real-time monitoring to predict when equipment and machinery will fail. This approach helps ship owners and operators to schedule corrective maintenance before a failure occurs, reducing downtime, saving costs, and improving overall vessel performance.
This article on Enabling Predictive Maintenance by Anish Kumar talks about a predictive maintenance solution developed by Goa Shipyard called the Condition Monitoring System (CMS). The CMS system continuously monitored the equipment, enabling decision-making based on the equipment’s actual condition rather than a periodic maintenance strategy.
Keep reading until the end of this edition to explore QuickBrain; an advanced Computerized Maintenance Management System (CMMS).
Improved Shipyard Planning & Decision Making
AI and ML have been employed to enhance shipyard planning and decision-making processes. Tools like Floorganise’s Floor2Plan use AI and historical data to optimize shipbuilding processes, reducing person-hours, ensuring more effective use of skilled workers, and providing more control over the entire process. The earlier you can identify and resolve risks, the less impact they will have on the entire process. Thatâs the core idea behind the Floor2Plan tool,â explains Ronald de Vries of Floorganise.
Another AI application for process simulation is Promodel by BigBear.ai. It enables users to understand their current facility, equipment, and personnel systems, forecast infrastructure and equipment requirements, accurately predict production schedules, manage throughput and cycle time performance, and simulate real-world situations with digital twin visualization.
In conclusion, the integration of AI and ML in shipbuilding has revolutionized in many ways than the few we have explored in this article. These advancements alone have led to more efficient and innovative ship designs, increased productivity and worker safety through automation, optimized operational efficiency and reduced costs through digital twin simulations, proactive maintenance scheduling, and improved planning processes. The future of shipbuilding looks promising with the continued integration of AI and ML technologies becoming the foundation for accelerated digital transformation.
Problem? we have the solution
PROBLEM: Engineers and designers have expressed their challenge in providing engineering information in a product data model such as ShipConstructor Marine Information Model (MIM) to other stakeholders (planning, purchasing, production, shop floor, inspectors, etc.) in a consumable format causing much disruption in their workflow and thereby taking time away from their core design/modeling tasks. Additionally, it also poses the challenge of access to the most up-to-date information for other stakeholders in a format they can use when needed without waiting or interruptions.
SOLUTION: SSI Publisher LT (PLT), an Enterprise Platform product provides a non-disruptive solution that allows you to gather, convert and manipulate information in product data model, commonly the ShipConstructor MIM, and save it to another location. This solution allows any stakeholder to generate all the information required by themselves or multiple other stakeholders by selecting a single operation.
Load manager allows you to specify the SC item type to use in PLT. It allows the user to filter their search by almost any SC defined property. PLT can then do a multitude of operations depending on the item type loaded.
Some of the operations our clients use PLT regularly include, performing project wide drawings clean up, exporting into other software types (for example, creating DWGs of parts or creating Navisworks drawings), extracting parts BOM information in excel format, to name a few.
This edition product tip is for all our Rhino3D ship designers!
In the design and modelling of ship hulls, the designer must be able to navigate the complexities of compound curvature. As you probably know, a non-developable surface is a surface that has curvature along two different axes, also known as a ânon-zero gaussian curvatureâ surface. Rhino3Dâs surface Curvature Analysis is the tool for the preliminary analysis of non-developable shapes. In the link below, you will find a Rhino3Dâs surface Curvature Analysis tip that leverages the Gaussian curvature radius.
We at InnovMarine are thrilled to announce an exciting chapter in our journey as we join forces with ENNOVIA, becoming their official North American distributor of QuickBrain in Canada and USA.
This partnership sees more than a shared vision; it signals the dawn of a new era set to revolutionize the civil and military shipbuilding markets. Our president, Pierre-Charles Drapeau, beautifully encapsulates our mission: “We look forward to bringing the same success ENNOVIA has achieved with the French Navy and French shipyards to the industry here in Canada and the United States.”
Let’s take a moment to delve into the expertise of our partner, ENNOVIA SARL. Hailing from Toulon, France, ENNOVIA stands out in industrial maintenance engineering, known for developing cutting-edge technological solutions. They skillfully leverage technology to boost facility availability, facilitate maintenance planning, and forecast operations. Their team of 20 dedicated professionals ensures ENNOVIA’s impressive influence is felt both domestically and internationally.
QuickBrain is an advanced Computerized Maintenance Management System (CMMS) application. It streamlines maintenance processes with 3D visualization, predictive maintenance, asset tracking, and efficient work order management, enhancing overall maintenance efficiency and reducing downtime.
Merging InnovMarine’s commitment to digital shipbuilding transformation with ENNOVIA’s prowess in industrial maintenance engineering gives birth to a partnership poised for success.
China leads in AI adoption, with 58% of companies deploying AI and 30% considering integration. In comparison, the United States has a lower adoption rate, with 25% of companies using AI and 43% exploring its potential applications.