Digital Shipyard - the age of the Digital Twin and the birth of Virtual Ship Maintenance

Digital Twin is yet another concept that seems to have a disproportionate number of "Doesn't this sound great" VS "This is how you make it real" articles. So I am going to have a good hard crack at the latter so you can figure out for yourself how valuable the concept might be in reality. I am also going to introduce you to a concept I'm calling the Virtual Maintainer. Bear with me and I will explain more.

Lets start by describing the former, a concept called Digital Twin that sounds great.

Digital Twin in its most simplest form is the digital (virtual) replication of a physical (matter) system, assembly, part or just about anything. In fact put enough sensors on a human being and you can make a digital twin of them. I firmly believe that the digital twinning of humans will actually be quite normal in another decade or two. It will provide us the ability to see events like heart attack happen hours, days maybe even weeks before it actually would. Not only will we have wearable sensors like smart devices (watches, rings, clothing, etc.) we will also have internal sensors that will provide a surprisingly detailed digital twin of ourselves. We could hook ourselves up to a laptop and view diagnostic information like a car. A little scary and a little exciting at the same time however I digress.

Because with all due respect our Australian shipyards are still a fair way behind on moving to a truly Digital capability.

For the purposes of this article I am going to concentrate on the application of Digital Twin with respect to a shipbuilding program. Why? Because with all due respect our Australian shipyards are still a fair way behind on moving to a truly Digital capability. In order to achieve the government's key shipbuilding objectives in Australia we need to get a little more radical with shipyard technology. So although this article is aimed at shipbuilding, the application of Digital Twin is as equally applicable to manufacturing in general and also to other industries such as Metals and Mining and Energy and Utilities.

When it comes to something like a submarine or a ship there are actually two types of digital twins that can be created. One is used before the platform is built and the other one afterwards. Both provide slightly different benefits however both are equally as valuable in de-risking and shortening the timeline of a ship build.

1. The Digital Prototype. This is the process of using Digital Twin technologies to design, simulate and optimise the build of a physical system before it is physically built
2. The Digital Twin. This is the process of replicating an existing physical system (Physical Twin) with a digital version. Data captured by the Physical Twin can replicate events seen in the Digital Twin

So let's take a closer look at each to understand how they can provide value and how shipbuilding organisations can use them with real industry problems.

The Digital Prototype

Some would suggest that the Digital Prototype is just an extension or a compilation of Digital Design. And although there is some truth to that in the fact that the Digital Prototype aims to glue together all the 3D designs of a platform, there is also much much more. A digital prototype at the scale of let's say an engine can provide some very valuable data. That data can help predict vital metrics such as mean time between failure based on sub-assembly failure rates and failure dynamics. For example an existing physical jet engine combustor being considered for inclusion in a prototype jet engine will have specific failure data. This data might suggest that the combustor has a mean time between failure of 68,735 hours. The data collected from failed combustors might also define failure dynamics such as the most probable location of material degradation leading to failure. This behavioural data can then be tagged to different parts of the engine's Digital Prototype and then used to simulate a failure. Artificial Intelligence can then be used on the Digital Prototype to determine the predicted outcome from the failure of that combustor. Image 1 shows that AI predicts that one minute and sixteen seconds after the combustor has failed the temperature on the outside of the turbine has increased from 164 degrees Celsius to 456 degrees leading to catastrophic failure.

Results from this engine simulation might lead to the installation of thicker combustor insulation in order to delay the heat increase for long enough that the engine can be safely shut down. So a Digital Prototype is not just a collection of 2D and 3D models, it also provides the ability to overlay other vital statistical and behavioral data to simulate functionality. It can literally act as though it is the real physical thing and has the advantage of being able to simulate scenarios that would be far too dangerous to simulate on a physical system or platform.

So it is easy to see how significant value in the design phase of a system such as an an engine can be delivered through a Digital Prototype. Now think about that value applied to the scale of a ship. Think about the potential of simulating all the different scenarios that can happen on-board a ship. The potential to avoid rework is enormous. Instead of learning design mistakes after the ship has been built, the Digital Prototype can discover those flaws long before the first piece of metal is cut. So let's look at an example of where this technology can help.

Fire Retardation and Suppression

It was hard to write this section and not think about the HMAS Westralia tragedy that took the lives of four Australian Naval personnel. So I'd like to momentarily pay my respects to those four brave individuals. Rest in peace.

That tragedy was caused by the use of improper fuel line hosing that burst, spraying fuel onto hot surfaces and igniting a large section of the engine room. And although a Digital Prototype could never have helped avoid the improper use of parts it could have helped with fire simulation had the technology been developed when Westralia was designed.

Through the use of a Digital Twin and the cognitive power of Artificial Intelligence, the subsequent spread of fire from an ignition like that which happened on Westralia can be predicted. This simulation is not just based on the physical layout of the ship but also on a number of other factors such as compartment materials, flammable substances, ventilation, installed fire suppression systems, etc. Physical and behavioural attributes are tagged to the twin so the AI layer can determine factors such as how long it will take to burn through different materials. At the bottom of Image 2 you can see that the application has determined there are eight walls that are vulnerable to fire and should be further insulated. It has also determined that there are four zones that are not protected by fire suppression (sprinklers) which should also be addressed.

Image 2. Simulation of fire spread and identification of weak points using Digital Twin and AI

3D Digital Twin views can also provide significant value by visually representing the potential impact of heat within a ship. Image 2 shows a colour-coded view inside a ship compartment and represents anything that has potential to get hot in red. This can give a valuable visual on two things, firstly a view on where insulation might need to be added and secondly, a view on how heating in a ship might impact the health and safety of crew.

Image 3. 3D view inside a ship compartment showing systems which emanate heat in red

So there are a couple of examples of how Digital Twin can help in the design / prototyping phase of a ship build. But there are so many other valuable applications of Digital Twin in this phase and like other capabilities such as Augmented and Virtual Reality it just comes down to imagination. Think it up and there is a really good chance it is possible. So let me entertain that challenge by dreaming up five other applications that would be possible:

Example 2: Ship Wi-Fi modelling with the ability to increase and decrease coverage to control cost.

Example 3: Block division optimisation to minimise the amount of work to consolidate and maximise hull integrity

Example 4: Optimising piping routes

Example 5: Analysing buoyancy and ship dynamics in different sea conditions

Example 6: Determining access size limitations for equipment to be stored in cargo areas

The Digital Twin and the birth of the Virtual Maintenance Engineer

So as we can see the Digital Prototype can accelerate the Design Phase of a ship-build by dramatically reducing rework and manual simulation. The Digital Twin on the other hand can be even more valuable as simulation based on predicted data and AI is no longer required as sensors are capturing real data from the physical platform. The entire Digital Twin can be lit up with information being collected across thousands of sensors on-board the platform. This can create a three dimensional dashboard of information and identify a vast number of events, interactions and issues happening on-board the physical vessel in real time. So in theory I could pop on a Virtual Reality headset and walk around the Digital Twin of that vessel and view the exact same events, interactions and issues virtually as they are happening in the physical world. That is insanely powerful as it can provide visual and dimensional context to a mechanical issue. If we wanted to simplify that result, we could just provide collected sensor data in the form of a dashboard on a PC. An individual could then drill down through sensor information from a web application. However in order to expedite root cause analysis we could overlay that sensor data onto the Digital Twin and through the use of VR provide a view that has the added benefit of visual context giving rise to the birth of the "Virtual Maintenance Engineer".

So in theory I could pop on a Virtual Reality headset and walk around the Digital Twin of that vessel and view the exact same events, interactions and issues virtually as they are happening in the physical world.

As you can see in Image 4, a Virtual Maintenance Engineer can use a VR headset to navigate the Digital Twin, in this case a 3D scan of a compartment, and view real-time data being collected from the Physical Twin. This can provide the engineer with visual context to understand what the issue might be, in this case a coolant flow issue raising the temperature of a diesel generator. Although there would most likely be an engineer attending to the issue on the Physical Twin, a virtual engineer who may have subject matter expertise could be in another location viewing the same interaction within the Digital Twin. Not only can the view provide key sensor data from systems and equipment within the compartment but the virtual engineer can also pull in sensor data from other parts of the ship as required.

Image 4: VR view (3D Scan) of a ship compartment within the Digital Twin showing real time sensor data overlay collected from the physical platform

Similar to the Digital Prototype, the use cases for Digital Twin are vast. In my previous article on Augmented Reality I highlighted an example that would use AR for quality inspections. To take that use case one step further, inspection data including Objective Quality Evidence (OQE) such as photos, videos and inspection reports, can be attached to the specific locations on the Digital Twin. That way an individual using an AR device such as a headset can walk into a ship compartment on the Physical Twin and instantly view locations of where OQE has been previously attached to the Digital Twin (seen as red dots in Image 5). That way they can view the various OQE and results of quality inspections as they view the physical system it relates to. Dots could be turned green when the issue has been addressed allowing for engineers to walk around the ship fixing red dot issues and making them green. Talk about gamification!

Image 5: View of the Physical Twin through an AR device showing locations of OQE attached to the Digital Twin

Digital Twin is so much more than a collage of pretty pictures. Digital Twins could actually be the most powerful assets an organisation owns however there are challenges to overcome in order to get it right. As you can see in Image 6, there is so much valuable data that can be captured in a Digital Twin. Operational history alone could quickly fill your IT department's servers. In fact when an F35 flies for one hour it can produce 2 Terabytes of flight information. That's enough to fill the average home backup drive.

Image 6: Information that can be captured in a Digital Twin

So the biggest challenge with a Digital Twin is extracting the important information from that data before loading into the Digital Twin. Data by itself is actually quite unuseful. However when data is processed, interpreted, organised, structured or presented so as to make it meaningful or useful, it becomes information. For the F35 example that means converting 2 Terabytes of data into 2 Megabytes of information. That would either mean manually looking through approximately 150 million pages of data to get the information required or using advanced technologies such as High Performance Computing, AI, Big Data and Analytics to extract it.

A conservative estimate on a $10B program could equate to a $50M saving from an effectively instantiated Digital Twin and a well architected Digital Thread.

So how does one even create and capture a Digital Twin? Unfortunately the answer isn't "Buy an application and it will magically appear". It does take some time and investment however the return will be significant especially when done early in the design phase. There are some tried and tested approaches to building Digital Twins such as DXC's "Digital Twin Runtime Starter Kit" seen below. The starter kit is more of a process than a single explicit technology and it requires a solid understanding of what it is the organisation wants to derive from the twin. i.e. What information is required to make valuable decisions?

So gone are the days when Digital Twin was just a "Great concept". It is real and is providing manufacturing organisations the ability to reduce significant cost through the minimisation of rework. Unlike a lot of other technologies it also provides value across the life of the program. The earlier it is deployed the more value it will provide. A conservative estimate on a $10B program could equate to a $50M saving from an effectively instantiated Digital Twin and a well architected Digital Thread. That's a lot of peanuts and well worth a serious discussion.

If you think your organisation could benefit from a Digital Twin and you don't know where to start then let me know and I can point you in the right direction.