Cyber System Research Group
In recent years, Japan's shipbuilding industry has been facing an urgent need to strengthen its international competitiveness, and it needs further improvement in the productivity of shipyards. Besides, manufacturing revolutions, such as Industry 4.0 are underway to fully digitalize the entire business process. Our group proposes a new shipbuilding industry that combines digital technologies such as AI and AR in the process of shipbuilding design and construction. We are also engaged in research on the advancement of inspection technology after service.
Overview of our research
We are conducting research and development of the Digital Shipyard, which aims to build ships in a shorter period by creating a shipyard where everything is expressed numerically, everything is planned numerically, and everything is completed according to plan. In particular, we are focusing on information on the design and construction of shipbuilding, and are engaged in research to generate information related to the design and construction and to effectively transmit and display the generated information to designers and workers.
- R & D of production simulation technology that reproduces detailed movements of workers
- R & D of work support system for various shipbuilding works (bending, painting, etc.)
- R & D of AR technology and VR technology to shipbuilding
- R & D on shipbuilding robots (assistant work support robots, block surface plate management by drone, CFRP design CAD/CAM for shipbuilding, etc.)
We are conducting research and development on production simulation technology to reproduce the detailed movements of workers. Fig. 1 shows a production simulation that reproduces the detailed movements of the workers at a small assembly process. The practical application of such production simulation technology enables the shipbuilding process to be precisely reproduced and helps planning worker allocation, calculating costs, and planning facility maintenance.
Fig.1 Example of production simulation
Fig. 2 AR application to support bending process
Fig.3 Block surface plate management system
In today’s world of the third AI boom, research and development using deep learning and deep reinforcement learning, which have evolved neural network technology, is progressing. In the current shipbuilding industry, it is required to connect these AI technologies to social implementation. Therefore, research is being conducted to utilize AI technology in the early stages of shipyard design (the stage of basic design and basic planning).
- Onboard noise prediction using neural networks
- Nesting by reinforcement learning (steel placement planning)
In the design stage, predicting the noise level inside a ship has been determined empirically and numerically. Simple and flexible empirical methods have been required to select and place components through trial and error in the design process. Neural network predictions are close to empirical judgments, so we have applied them to shipboard noise predictions. As shown in Figure 4, a web application is created and all the sample data that will improve prediction accuracy is kept and controlled.
Fig. 4 Neural network based noise prediction web application and its operation image
Fig. 6 Nesting results by reinforcement learning
Visual inspection is the main form to detect structural defects and damage. Recently, drones have been used as one means to get easy access to inspection points. Our group has been working on the following research and development to apply them to the inspection of ship cargo tanks and offshore wind turbine blades.
- Image recognition of damage inside cargo tanks using deep learning AI
- An efficient method of inspecting offshore wind turbine blades
Assuming that drones are used to inspect the ship's internal structure, we studied utilizing image recognition using deep learning (Faster R-CNN) to find cracks. Fig. 7 shows the result of damage recognition based on the results of deep learning on the damage images taken by an inspector with a digital camera. It is not useful enough to employ the current deep learning method alone for the field. It is necessary to advance this research by utilizing knowledge related to important inspection points.
Fig. 7 Example of damage image recognition results by deep learning
Fig.8 Inspection method for offshore wind turbine blades
We have set up a "next-generation shipbuilding system study group", "ideal of next-generation design system based on lessons of shipbuilding CIMS", "recent trends of technological innovation such as digitalization", "future image of maritime industry", We had a discussion on "Trends in other industries" and "Latest trends in CAD and other systems".
Based on the discussions of this study group, we have compiled the following two recommendations.
- Recommendations for building an information collaboration platform
- Recommendations for building a digital twin at a shipbuilding factory
As one means of strengthening international competitiveness, we are considering an alliance concept between shipyards and related industries as shown in Fig.9. This concept envisions ad hoc development for each project. Currently, there are various CAD systems used at each shipyard, but unless the data and information necessary for design, planning, procurement and construction can be linked, the effect of the alliance will not be exhibited. We will work to create a system that can be flexibly constructed at various stages including sales, procurement, development, design, and construction.
Fig.9 Information Linkage System Concept
We will proceed with these research and development focusing on improving the productivity of shipyards in order to solve the issues for strengthening the international competitiveness of our shipbuilding industry.
Fig.10 Factory Digital Twin Concept