“Digital Twin” is one of the top strategic enterprise trends today. Digital Twin Builder system is designed to autonomously build digital twins directly from streaming data in the edge mission space. The system is built for the emerging AI network world in which real-world devices are not just interconnected, but also offer digital representations of themselves, which can be automatically created from, and continually updated by, data from their real-world counterparts.
Builder addresses these challenges by enabling any organisation with lots of data to create digital twins that learn from the real world continuously, and to do so easily, affordably, and automatically.
Digital twins are digital representations of a real-world object, entity, or system, and are created either purely in data or as 3D representations of their physical counterparts. For example, every component of large machines can be stored as a digital twin in the Builder system.
This allows engineers only know where everything is and what it looks like, but also how well components are performing and when they need upgrade, repair, or replacement. But for most organisations that kind of massive, programme isn't an option. They need something simpler, easier to deploy, and cheaper.
Digital Twin Builder system is designed to enable digital twins to assess, learn, and predict their future states from their own real-world data. In this way, systems can use their own behaviour to train accurate behaviour models. The important difference to other AI solutions is this ability is offered as a service in real-time, without centralised, batch-oriented big-data analysis.
Key challenges include how enterprises can implement the technology, given their investments in legacy assets. Limited skill sets in streaming analytics, coupled with an often poor understanding of the assets that generate data within complex AI network systems, make deploying digital twins too complex for some. Meanwhile, the prohibitive cost of some digital twin infrastructures puts other organisations off.
Digital Twins need to be created based on detailed understanding of how the assets they represent perform, and they need to be paired with their real-world pairs to be useful to stakeholders on the front line. "Who will operate and manage digital twins? Where will the supporting infrastructure run? How can digital twins be joined up with AI networks and other applications, and how can the technology be made useful for agile business decisions?"
The ability to add AI at the edge is an increasingly important element for networks as companies look to improve data processing and efficiency. Digital twins are digital representations of a real-world object, entity, or system, and can be enhanced with AI networks. Improvements can be made to digital twin technology to help AI networks.
Robots are replacing somemotor-drive-gear-operated systems. The robots perform the same processes, for example, cutting, bending, and sealing tasks for a shipping box, but their arms are driven by independently controlled servomotors. “The old machines are much cheaper to build, but they can only do one thing. So, if you had a new package, you either had to re-engineer your machine or scrap it. With robots, it’s simply a matter of changing the packaging profiles and the application parameters.”
Still, reprogramming robots takes time. In the past, an engineer might have used applications to simulate how the line would handle the new packaging, but then have to pull those robots off the line. Then the engineer would test and tweak the movement of materials through the machine and the ability of the robotic arms to make and package containers, all the while trying to shave time off each cycle.
A digital twin goes one step beyond conventional models. It models the robotic line with such high fidelity, the engineer can do all this in the virtual world. After adjusting the model profiles and operating parameters, the engineer simply exports the profiles and parameters to the control system of the physical equipment. So it should run perfectly the first time. “That alone will certainly disrupt the packaging machine industry,” “That’s the future, and it’s certainly where digital twins for large machines will end up.”
Yet this is clearly not all digital twin technology. is capable of. In fact, simulating individual machines is only the beginning. Because the real power of a digital twin is not that it optimises a single machine, but that it interacts with the digital twins of every piece of equipment in a factory and the digital twin of every product those machines make.
And it its not limited to optimising those production processes in the virtual world. Digital twins run in tandem with their highly instrumented physical twins, fed by data by from actual operations. By comparing the output of the digital and physical systems, engineers can quickly spot problems before they arise, avoid bottlenecks, and find new ways to boost throughput and reduce costs.
In short, digital twins are the foundation of tomorrow’s smarter workplace.
Digital twins may seem like the newest buzzword but the concept dates back two decades. Their premise was simple: A digitally modeled system is really composed of two systems, a physical system and a virtual system that contains all the information about the physical system. They can exist for products and for processes.
Engineers have used product models for decades, but only recently have they achieved the extraordinary fidelity needed for digital twins. “In industries like automotive, we can define a big chunk of our products geometrically such that it is almost impossible to determine whether a representation is virtual or physical. Product models slash development time by letting engineers build and test virtual prototypes to optimise design and cost. Now the same approach is used in manufacturing processes..
Conceptually, it is not much of a jump from testing product designs to simulating manufacturing processes. In fact, many application programs do something similar today. What makes digital twins different is their fidelity and their ability to handle large amounts of data in real time.
Even modest factories are complex, and they have far fewer constraints than any complex product designed to operate in a specific way. In a factory, operating procedures are always changing. Even a simple drill press might bore aluminum one day, then switch bits, speed, and coolant for steel the next. A modern factory might make many products, and the flow of materials from machines through assembly stations will change with them.
The digital twin of a factory must be robust enough to capture those changes, plus all relevant data from each operation. That takes massive AI horsepower. Fortunately, networks have grown more powerful and manufacturers can now tap the cloud to store and analyze factory data using cognitive computing programmes.
Modeling tools have also advanced, especially their ability to generate “lightweight” models. “We can select the geometry, characteristics, and attributes we require without carrying around unnecessary details,. This dramatically reduces the size of the models and allows for faster processing.”
Reducing data requirements lets digital twins visualise and simulate complex systems without drowning in a flood of extraneous real-time data. It takes highly instrumented equipment to supply that data. While manufacturers have been adding sensors to the shop floor for decades, digital networks are making it cheaper and easier to collect up-to-the-minute factory data for performance analysis.
New design and production sites are based on digital twins and the AI/Cloud data needed to feed those models. “Plants are always changing, people are moving around, machines break and lines slow down. The digital twin will only work if it reflects the reality of the shop floor.”
Smart job sites need both types of digital twins—product and process—to work.
Digital product models contain each component that goes into a product, from screws and welds to plastic shapes and machined metals. The digital twins that drive a factory have an associated bill of process for each of those components. This “instruction manual” describes the steps needed to produce and assemble those components into the final product. Product and process twins work together.
“The digital twin can provide the manufacturing execution system with step-by-step instructions for making that product. Builder system can reference that instruction manual and perform all the coordination tasks to guide the product through the factory, setting up machines on the fly, and check that each step is done correctly.”
The twins let engineers test-drive new processes. They could, for example, add a new machine to their virtual line and see how it affects output of specific products, or test whether relocating equipment or readjusting workflow between machines improves output. The result is not just an optimised machine, but an optimised process. It will be possible to do laser-scanning on an entire factory to model its infrastructure, then drop digital twins of machinery and logistics systems into it.
Builder does thousands of virtual production runs to see if product is designed with manufacturing in mind. Simulation can be run where workers put on gloves and see if they can still assemble the product, or create assembly cells that combine collaborative robots and people and see if that helps.
Once the physical line is up and running, its sensors will send operating and inspection data to the factory digital twins. These models provide a detailed view of factory operations. By looking for unexpected variances between actual and simulated data, engineers can probe for potential problems that might reduce operating rates or quality.
Digital twins support greater automation. As orders come in, the system will make sure the proper parts are in inventory, schedule machine time, and route components from workstation to workstation with only minimal human intervention. Each step of the way, the plant autonomously checks product and machine specs against their digital twins to ensure each operation is carried out correctly and that no equipment is drifting out of tolerance.
“Digital Twin” fully connected factory linked with internet sensors and cloud analytics is still a work in progress. Yet this has not stopped engineers and manufacturers from simulating some operations with existing tools. One team created a virtual model of the production line that would build its new vehicle while still designing the car digitally.
This interplay between product and process digital twins ensured the factory could produce and assemble the parts its designers had envisioned. It also helped work out problems before production. When manufacturers offer highly customised products, the virtual factory had to be flexible enough to create the parts needed for each combination without slowing down.
To be able to introduce the new models to the market as quickly as possible, engineers laid out the new lines while the vehicle was still on the drawing board. The Design engineers rapidly went through different modification scenarios of the new models over and over again.
Accordingly, the production facilities needed continuous adjustments . Fortunately, application tools are rapidly rising to the challenge of concurrently building and integrating digital twins. Builder analyzes how vehicle design changes affected production, so it shows where to focus their attention. As the technology evolves, those tools will grow more powerful and be able to handle more complexity.
AI enabled digital twins will become more tightly integrated into plant production processes, and far more capable. They will also become smarter, using machine learning programs, a type of artificial intelligence, to learn more about factory machines and improve the ability of digital twins to simulate and predict their behaviour.
“At the outset, there is a good idea of what operating parameters should be, but it is key to improve prediction capabilities by incorporating data as the machine is operating, and learn from that data.
As AI systems learn more about specific machines, they will use their digital twins to help engineers run plants more efficiently. A suspect sound coming from a machine? AI can analyze it to see if a screw is loose or a bearing is starting to fail. The better the AI knows the machine, the more accurately it can predict when that failure is likely to happen. And the more options—fix it now, run the machine to maintenance, or readjust production schedules and take the machine offline—it can offer a plant administrator.
Digital twins are evolving rapidly. Where will it end up? More economical manufacturing of small lots, or even lots of one? Maybe. Hyper-customised products? Perhaps. Fully programmed and optimised production lines that need only a few hours of shakedown before startup? That would be great. Machines managing and controlling other machines? Closer than we think. That is what a demo is used for to automate machinery with extensive digital product and process twins to keep everything on track. The results are stunning. By using digital instruction manuals and robots to move parts from one workstation to the next, it can produce products very quickly.
Digital twin simulations can be compared to physical machine and product data, so the factory can tune and retune its equipment. This achieves remarkable levels of quality: despite churning out huge lots of different products every day. This is very much what mass customisation looks like. Eventually plants may churn out customised products nearly as inexpensively as factories that make mass-produced models.
Digital twins will make that possible, as well as a whole lot more. Their future is still being written.
But difficult as it may be to accept, sometimes “Digital Twin” terminology can get in the way of innovation. A case in point is the “model-based” cluster of engineering design, manufacturing, and enterprise terminologies and methodologies.
While “Digital Twin” implementation can be beneficial, redundancies and overlaps foster long-running confusion in both traditional worker and digital context.
In recent years, many similar difficulties have been overcome with “Digital Twin” lifecycle management strategies reshaping how many enterprises handle their data, i.e., integrated from initial concept of a product to the end of the product life and often beyond that with nothing relevant left out. As digitalisation continues its rapid penetration of enterprises, the overall economy, and DoD transformation is all around us.
This “Digital Twin” transformation and its many innovations depend on visibility, connectivity, and traceability of data whether structured or unstructured. Significant parts of this transformation are being compromised by implementations with closed-system architectures and limited connectivity.
Overlaps and the confusion they foster tend to isolate capabilities from innovative processes and workflows that are required by the enterprise. The problem is routinely encountered in the aerospace and defense industries.
When one steps back a bit, it is as if “Digital Twin” terminologies and methodologies are fighting each other for dominance, market space, and behaviour. Given their history and how they are managed and mismanaged, this shouldn’t be a surprise. That this situation persists, however, is a surprise.
In short, it's time to clean up “Digital Twin” terminology and to take fuller advantage of is required end-to-end enablement-- challenging developers, marketers, and standards committees to sort out terminology and agree on common-sense definitions with minimal overlaps.
DoD must begin with recognising that there is a problem and that it can be fixed —that logical, everyday definitions of can be agreed on by all concerned. Until this is achieved, fundamental difficulties in enabling good practices will not be solved.
When viable “Digital Twin” terminology agreements are reached, benefits can be expected quickly: The all-important exchange of information between the factory floor and design engineers will be simplified and sped up.
Better connectivity will make workflows more visible across the enterprise, so they can be leveraged at many points in the lifecycle. With connectivity and visibility comes greater transparency of processes and potential for capabilities to become widely available across the enterprise and in the extended enterprise of partners, suppliers, and customers.
“Digital Twin” solution providers will put developers to work on better-enabled framework. To grasp these potential benefits, it helps to look into the generally accepted terminologies:
Model-Based Definition refers to 3D construction application models providing specifications for a component or assembly without additional 2D engineering drawings. These specifications include geometric dimensioning and tolerancing, bills of materials, technical data packages, engineering configurations, design intent, etc.
Collectively known as product manufacturing information, these data sets and their linked repositories contain the information to manufacture and inspect the product. Model-Based Definitions are also known as “digital product definitions.”
“Digital Twin” Model-Based Design is a mathematical and visual method of addressing problems in designing complex control, signal processing and communication systems. In Model-Based Design, models are developed in simulation tools for rapid prototyping, testing, verification, predictive signals, and record libraries.
Model-Based Design is also a communication framework to represent shape, behavioural, and contextual information throughout the design process and development cycle.
Model-Based Engineering is the use of models as the authoritative definition of a product or system's baseline technical details. Intended to be shared by everyone involved in a project, these models are integrated across full lifecycles and span all technical disciplines.
Model-Based Systems Engineering is a methodology to support system requirements, verification, and validation activities from conceptual design, throughout development and on into later lifecycle phases. Like other “Digital Twin” components, engineers use these simulations to exchange information.
Model-Based Enterprise refers to an organisational work space that leverages the model as a dynamic artifact in product development and decision-making. The Model-Based Enterprise focuses on the management of lifecycle feedback to create follow-on products and their iterations and variants.
Integration considerations always bring us back to DoD specification standards and, as we have seen, they are a big part of the problem. There are at many separate groups developing standards relevant to “Digital Twins“, which impact it or join it to related processes and information-constructs.
None of these standards is adhered to by all developers and solution providers. Practice workshop attendees noted that each solution provider defines “Digital Twin” in ways that best align with its marketplace stance and competitive advantage, i.e., they define “Digial Twin” to be what their solution can do. So it is useful to use cross-discipline standards that adhere to end-to-end, “system of systems” approaches.
There is another dimension to the “Digital Twin” problem: the difficulty of implementation .
It is time to fold “Digital Twin” methodologies and associated terminologies together to fully integrate them into enterprise information infrastructures. Only then can tech be enabled with the lifecycle data and process management it requires. When this is done, one of the goals of digitalisation will be realised.
Product Innovation Platforms enable “Digital Twin” to optimise everything from customer requirements, product behaviour and performance metrics using sensors through end of service life . Product Innovation Platforms let users collaborate and innovate more effectively with seamless and transparent data sharing throughout the entire lifecycle.
Our Product Innovation Platform model illustrates the enterprise product lifecycle functional domains, with Multidisciplinary Lifecycle Optimisation capabilities overlaying the center—the Blockchain Backbone—connecting and enabling collaboration among the functional domains, as well as enabling true lifecycle systems of systems product and process optimisation.
Modern DoD demands for data sharing require that integration be reliable, which is a core value fo “Digital Twin“. Must have capability to manage new-product data across billion-dollar operations—gathering, preserving, and updates cannot be used across the enterprise without “Digital Twin.”
For the good of innovative product development and the beefing up of enterprise competitiveness, we believe it is time for everyone responsible for “Digital Twin” to take an unbiased look at the gains to be won from implementation key part of digitalisation and the sweeping transformations accompanying digitalisation, all of which are inevitable.
Unless and until agreement is reached on the need for change in “Digital Twin” methodologies and associated terminology, they will continue to be a stumbling block. Knowledgeable experts from industries using “Digital Twin” must cross traditional engineering boundaries and integrate team work orders. Benefits of using Digital Twins include:
1. Helps you move validation processes into the virtual world – but still keep you connected to how your products act in the physical world. This virtual-physical connection lets you determine how a product performs under a number of conditions and make necessary adjustments in the virtual world to ensure the physical product will perform exactly as planned in the field, reducing risk. Digital twins help you navigate world of complex systems and materials to make best possible decisions with confidence.
2. Helps you validate how your production process will act on the shop floor before anything actually goes into production. By perfecting this performance using your digital twins, and understanding why things are happening using the digital thread, your prevent costly downtime to machines and robots on the shop floor. You can even predict when maintenance will be necessary to avoid unnecessary downtime.
3. Helps you save time and money in simulation, testing and assessments so you no longer have to rely on only physical constructs; instead, you can include information from physical performance in your digital twins to maintain a high version of fidelity and reality in the virtual world. This constant stream of accurate, updated information gives you the situational awareness you need to make decisions faster, increase your production speed and optimise your productivity to get to market faster.
4. Helps you develop intelligence to feed advancements and reduce risks in the future products. Machine data collected over a period of time can enable digital prototypes to sustain life of product and help human operators make better decisions to enhance product performance
5. Helps you generate production data in real time to reflect the current and future performance status of their physical counterparts to enable sharing with technicians or other interested groups remotely. Virtual representations will be able to predict faults and errors and help avoid costly implications.
6. Helps you generate value in the form of less maintenance costs, new revenue streams, and better management of assets. As technology improves and virtualisation options become more pronounced, you will be able to deploy digital twins with even less capital investment while deriving greater returns on investments in a shorter time period.
7. Helps you be able to provide an integrated outlook of any project, to any user, at any point of the product lifetime. This single source of validated information allows you to foster collaboration across various teams and departments, and even outside the organisation. Engineers can simulate the behaviour of complex systems to predict and prevent mechanical breakdowns.
8. Helps you advance existing processes, products and services and often lead to new market opportunities while significantly cutting operating costs, leading to real bottom-line improvements. Digital twins help you propel traditional manufacturing to a new competitive level via intelligent connected products.
9.Helps you improve product performance while mitigating both the cost and risk of a new product introduction. Digital twins can dramatically speed product realisation time as you decrease or eliminate the most time-consuming aspects of building products in the real world. Early discovery of system performance deficiencies uncovered by simulating results before physical processes and product are developed compresses time to value relationship
10. Helps you demonstrate product value proposition before build stage with opportunity to link organisational tools, skills and knowledge bases. It’s becoming increasingly apparent that different manufacturing concepts and methodologies are required to take a product idea to commercialisation. Continuous refinement of design models is possible through data captured and easily crossed referenced to design details.