Digital twins: bridging the physical and virtual worlds
June 2022
What?
Digital twins are dynamic virtual replicas of physical objects, processes and systems that enable risk-free testing and prototyping, improved efficiency, productivity, and safety, as well as accelerated time-to-market.
Why?
As virtual laboratories, digital twins enable forecasting and predictive maintenance to reduce downtime, waste and costs while promoting greater efficiency in supply chains and effective remote collaboration that reduces the need for carbon-intensive travel.
How?
The product of innovation in connectivity, cloud computing, AI, and remote sensing, digital twins rely on a constantly updated flow of real-world data to synchronize with their physical counterparts.
Jon Gamble, Ericsson, Imagine Studio, asks you to imagine a digital world beyond the screen.
The takeaway
Digital twins improve productivity, safety and quality, and support sustainability targets by removing travel requirements and wastage
Digital twins play an important role in Ericsson's factories, reducing unplanned downtime by around 50%
The global digital twin market is predicted to be worth US$48.2 billion by 2026
Lead times from ‘survey complete’ to ‘design complete’ for antenna/site installation are reduced by 50%
Digital twins will create a ‘cyber-physical continuum’ which means events in either reality will influence the other, blurring the distinction between the virtual and the real
Digital twins give us the power to see what’s around the corner.
Virtual replicas of real life will enable individuals to create simulations of places, objects and systems, and experiment with them without risk or disruption.
Imagine you’re a wind turbine engineer who wants to try a new design. Better to test this in a virtual world than on an object which is in a remote location, right? What if you’re responsible for a series of remote factories, and you want to compare how each is performing? It would be incredibly useful to visit every site without leaving your desk, wouldn’t it?
Digital twins offer a testbed, or a virtual viewpoint, to explore the impact of changes or improvements before you commit to them in the real world. Now you see why they’re so exciting.
It is only recently that this technology has become usable on a broad scale, due to the convergence of technologies, including 5G, sensors, and extended reality devices becoming more widespread. That said, in the 1960s NASA introduced duplicate systems for space missions, to test the equipment in a controlled environment, and finally to support the launch of Apollo 13 in 1970. It wasn’t until 1992 when David Gelernter, in his book, Mirror Worlds (Oxford University Press, USA), outlined a broader view of what could be possible by describing a future in which computer systems are interconnected, and the images they created could be interacted with to control the real world.
The actual concept of digital twins is credited to Dr. Michael Grieves who, in 2002, introduced it through his research into product lifecycle management. Since then, steps to make digital twins a reality have already allowed the visualization and automation of complex systems in places such as ports and factories. It is predicted that this will be one of the most promising technological trends, with a potential global market value of US$48bn by 2026 (source: MarketsandMarkets).
Modelling and simulation
But what defines a digital twin? If you were to do an internet search, there is an overwhelming variety of definitions. For example, a digital twin can be defined as software representation of assets and processes, which is enhanced with capabilities that are not present in the real-world entity. Or, more briefly, it is described as a virtual copy of something, and processes associated with it, that can be used to predict or interact with reality.
In the simplest terms, think of entering a virtual replica of your living room, everything is exactly where you know it but in a digital format. When a family member switches the TV on at home the digital equivalent in your virtual room would also switch on almost in real time—in other words, actions can be transferred between the two different realities. Having the ability to replicate many physical elements in a virtual world that constantly adapt and learn based on real-world events is the basis of a digital twin.
It’s also important to distinguish a digital twin from a simulation—they do share common characteristics, but also some important differences.
Simulations are created by the imagination of the designer, who will use them to analyze the cause and effect of different scenarios, mostly offline. In most cases, a simulation is a snapshot of a one-time task, which is then used to support design and analysis studies. Digital twins, on the other hand, are driven by timely synchronization of information between the real and virtual worlds, and therefore adapt with changes in either world. Simulations are predominantly theoretical, whereas digital twins are specific and actual.
Similarly, digital twins share some similarities with metaverses—they’re digital spaces where people can interact virtually. But once again, metaverses are built from the ground up by developers and, typically, represent virtual realms (such as a futuristic landscape or a fairytale castle), whereas digital twins live and die by data (for example, through constant transfer to and from virtual and physical spaces) to create a replica of the real world. You may think of a digital twin as a reflection of the real world, which is regularly updated to keep the two worlds synchronized, while the worlds represented in a metaverse may have no or partial resemblance to the real world.
Digital twins have four primary characteristics:
- Data models and data structures to represent the observations, state, and relations of the real-world objects of interest.
- Transfer of data from the real-world objects to create the digital twin. Typically, this is done continuously to enable an accurate and up-to-date view in the twin.
- Data analytic tools to unlock the capabilities and insights of the digital twin. This could be a simple data retrieval from one or more sensors to complex algorithms used to predict future behavior, simulate different scenarios and other analytics tasks.
- Techniques to interact with the twin through different APIs, GUIs, or other human interfaces. The insights from these are used to make better decisions in the real world, either directly or by actuation through the digital twin.
With such a broad range of capabilities, there are numerous different applications and types of digital twins that can be created and evolved over time, starting with the simplest element of a major system such as a temperature sensor or a flow detector. As a number of different components are combined, digital twins evolve further to provide insights to show how they interact with each other or new information not available by looking at each component individually. For example, when there is a full digital representation of a specific location, the digital twin has the capacity to indicate how to improve productivity, quality, and safety.
In every case, the digital twin can be accessed regardless of location, and in collaboration with others. Limitless connectivity between different digital twins will enable learning between systems and provide further insights from, for example, other locations or similar industrial segments.
Digital twins and industry
Much of the current research within Ericsson has been prompted by the increasing interest in realizing the full potential of mobile connectivity in the ongoing digital transformation. There is an overwhelming consensus that digital twins play a major role in this transformation. Within our own factory in Texas, and as part of our own digital transformation program, a digital twin of the Surface Mount Assembly (SMA) line led to a 50% decrease in unplanned downtime and a 30% reduction in waste.
In partnership with the Port of Livorno, Italy, Ericsson used digital twins to examine how technological innovation could optimize operations, and to identify what economic, social, and financial benefits could be realized. This was achieved through continuous monitoring of the port activities through cameras, GPS, and other sensors attached to objects. Changes made in the real word as a result of this exercise have had a measurable impact:
- It is estimated that the time for vessel operation completion has reduced by 13% and forklift usage by 17%, which has led to a reduction in carbon emissions of more than 8%.
- Cost savings are estimated at around US$60m per year for this mid-sized port cargo terminal.
- The Port of Livorno study also gave strong evidence that 13 direct and indirect benefits relating to environmental sustainability and personnel safety were achieved as a direct consequence of greater connectivity.
- Assets and performance trends can be monitored across the entire site, to allow for predictive, proactive, and, in some cases, remote maintenance.
In car manufacturing, digital twins have been used to enable greater collaboration between design, engineering, and manufacturing teams—based in different locations across the world—to accelerate the pace of development.
For a consortium of BT, Ericsson, NVIDIA, and Hyperbat (a vehicle battery manufacturer), 3D life-size replicas of devices are visualized on the factory floor, enabling people to work on them in a shared, virtual, and controlled space. This has enabled Hyperbat to build efficiency into its manufacturing processes, while also removing complexities as a result of different teams using different products and project management systems.
Urho Konttori, Founder and CTO of Varjo, a leading-edge headset manufacturer, has seen immense benefits for his teams.
"Teams no longer feel like satellites to the main office or factory, but are a singular item, fully connected within a common virtual space, negating the need for business travel."
Urho Konttori, Founder and CTO, Varjo
Urho Konttori, Varjo CTO, discusses the challenges of manufacturing human-eye-quality headsets.
Benefits observed across various industry segments
| Benefit | Overview |
|---|---|
| Risk Management | Scenario modelling, forecasting, decision making |
| Improved Productivity | Performance analysis, reduced downtime |
| Predicative Maintenance | Reliability, reduced costs |
| Remote Collaboration | Design customisation, reduced need for business travel |
| Real-time monitoring | Improved customer service, enhanced product insights during lifecycle, more efficient supply chain |
| Remote operations | New techniques to support critical mission operations (requiring very low latency) remotely, increased employee safety |
What's next?
As more devices and applications are connected, and more industries and businesses use digital twins, the possibilities of connecting systems become limitless.
In parallel, the collective potential incorporating AI algorithms with digital twins will become increasingly important to the industry, providing new techniques and solutions for all kinds of applications or services. To achieve this, however, the demands on the networks will be raised even further due to the volume and frequency of data transfer.
In some cases, when there is not sufficient data to draw from, digital twins could be considered as gaining further intelligence and have the ability to be trained. In these cases, AI algorithms would be used so that the decision-making of the digital twin can continue and compensate for any limitations linked to the location of the sensors or the network.
For now, there is still some work to be done to raise awareness of the potential of what digital twins can offer. A recent Industry Lab report from Ericsson shows that awareness of the benefits that digital twins can offer is “the capability that manufacturers were least aware of”, although those that have introduced them immediately see the benefits.
Discover how digital twins are making the construction industry and medical learning more effective.
A peek into the future
Network performance and customer satisfaction
Network upgrades and build-out are central to maintaining network quality, enabling new services, and using new technologies, and are major contributors to investment decisions. It is therefore essential to ensure the correct timing and choose the most optimal solutions.
Gathering data from a multitude of sensors and locations within a network to create a digital twin could facilitate scenario planning to optimize investments or adapt operational activities. For example, it would be possible to evaluate in greater detail both fulfillment of customer expectations and financial risks from SLA breaches and target areas that would give the best return on investment and customer satisfaction.
Healthcare
By 2030, digital twins could play a role in supporting healthcare. Digital representations of the body could enable continual diagnosis and preventative actions to take place. Philips Healthcare believes there could be “personalized, lifelong patient models that are continuously updated with each measurement, scan or examination, and that includes behavioral and genetic data as well.”
If this could be extended with new forms of wearables, equivalent to the sensors used for diabetes, for example, this would allow further insights into mobility, environmental variations, and daily routines. Your digital twin would enable doctors and surgeons to have a more holistic view of your health, to leverage their knowledge on a much greater scale than was ever thought possible. With cognitive capabilities, such as pattern recognition and a multitude of related simulations, the information available to a doctor would be many orders of magnitude greater than it is today.
Sustainability
Beyond sustainability benefits as a result of increased efficiency, reduced travel, and wastage, the introduction of ‘Games for Good’ could have a profound impact on society too.
Games for Good is where the interaction between a physical and virtual world is supported through gamification and awareness of personal habits. In one example, a child could collect litter from their school grounds and, as they place it in the trash, the network would calculate its weight and then reward the child with a digital merit that they could use within their favorite game.
Conversely, a gamer could navigate around a virtual world that is an adapted replica of a physical location. In doing so, they could control a device that removes rubbish from beaches. In this case, the beach and the objects on the beach would be captured digitally and updated in real time. To ensure complete safety in that situation, a further dimension of SLAM (simultaneous localization and mapping) and deep learning could also be put in place to prevent any real-world collisions or damage.
The European Commission believes that by 2030 a digital twin of the earth, called DestinE, will exist to support climate action. Through real time, continuous, in-situ monitoring supported by AI, it is suggested that it will help to forecast natural and human activity. The University of Edinburgh can already track important variables of the environment and geography in Antarctica, such as the possible whereabouts of meltwater on or under the ice. Connectivity would play a major role in enabling the collection of data from multiple different sources and locations.
Ericsson’s role in making digital twins an integral part of industry and society
In the near future, digital twins will influence most aspects of our life in some way. Ericsson is therefore constantly exploring how it can work with others to create specialized solutions, and to determine how digital twins will become part of an evolved network architecture.
Ericsson also has an active role in industry collaborations and helps to spearhead consistent standards in vocabulary, architecture, security, and interoperability of digital-twin technology. Specifically, Ericsson is focused on five areas:
Exposure
Digital twins rely on software on the virtual side, and sensors on the physical side. The mobile network brings these together, providing efficient and reliable connectivity as well as network-embedded compute capabilities for digital twin application software, often partially powered by AI. In addition, the network itself has data, which is of value to digital twins, for example, positioning and sensing, as described below.
A digital twin is able to adjust the network service to match how it is being used. For example, when a low-latency channel is needed for real-time replication in the digital twin, the network would be adjusted to match this demand dynamically, both for the connectivity and the location of software components in the most suitable edge data.
Positioning
A fundamental aspect of digital twins is the ability to associate information to a spatial and temporal context. Location accuracy varies and has different performance levels and limitations. For instance, a GPS can’t work indoors unless repeaters are used, and cameras provide high accuracy but in a limited operational range of about 50 to 60 meters. With cellular connectivity, positioning and timing data is already available and is gradually being evolved and improved.
With new generations, the network can enable enhanced sensing to allow observations of passive devices. Within a factory environment, for example, the location of devices or authorized network applications can be validated with other independent positioning information. Network validation is important to ensure resilience in these critical communication environments against spoofing, jamming and malicious software.
This is especially true in the digital twin domain when there is the need to track objects, like vehicles and freight, or to provide AR content to moving subjects in real time. Accuracy in the positioning depends on the task.
For instance, for freight in a port storage area the accuracy must be in the range of 20 to 30 centimeters, whereas tracking a forklift during shuttling operations in the digital twin can be in the range between 0.5 and 1 meters. When AR is used, the position accuracy depends a lot on the field of application. If there is the need to get additional information about a detailed part of an object, such as a switch or button, the accuracy must be in the range of millimeters to a few centimeters.
Sensing
New generation networks will allow a further level of sensing, to increase the level of data available.
Digital twins require input data to be truly beneficial. Such input can come from a wide range of sources—external sources as well as from the network itself—often referred to as joint communication and sensing (JCAS). By collecting information on the received signal strength from communication nodes, detailed input on the local weather situation, for example, is obtained for free and used to improve the weather forecast accuracy.
Another possibility is to use the communication nodes to create a radar-like function, exploiting the large number of nodes already deployed for communication purposes. With this capability a digital map of the environment can be created and used for all sorts of applications such as traffic management, healthcare, and security.
In all these examples, sensing is a value-adding service offered on top of a deployed network. This allows for cost-efficient sensing and broader coverage that can complement, or even replace, dedicated sensing systems. To achieve this more efficient use of radio resources, scalable mechanisms for distributing the results and AI-based interpretation of results are essential. Of course, mechanisms to ensure the privacy of the information collected are of utmost importance.
Cognitive networks
There are many layers of intelligence that will bring further benefits to the industry as the network becomes more autonomous. Facilitated by cognitive capabilities, a system can carry out actions, changes, and decisions with little human involvement, but with support from digital twins.
Over time, these capabilities will expand and take on responsibilities and decisions only humans can carry out today. Digital twins can provide important input to this cognitive decision-making process, to ensure the best options are chosen. To give a flavor of the different possible applications:
- The cognitive system can ask a digital twin to evaluate different configuration options and scenarios to operate safely with little or no human input; or can determine how best to reach performance targets for different services.
- A digital twin can use knowledge and predictions from other intelligent systems to make better choices. For example, by using a diverse set of real-time data, information could be captured from various moving objects within a location, and this information can be used to enable the most optimal use of network resources—for example, scheduling mechanisms.
- AI algorithms can be trained in the digital twin environment in a safe way, where it is also possible to generate enough training data. This would enable the combined system to learn more efficiently, building on past feedback and experiences to generate options for the most optimal solution to assist with productivity, quality, or safety.
Vicknesan Ayadurai, Master Researcher, Ericsson Research, discusses what a network reality really looks like
Visualization
Visualization remains a challenge for a human user. Extended reality (XR) techniques, and specifically VR and AR, are the ideal visualization and interaction tools to bring the digital twin information into view, by leveraging 3D geometry, spatial computing, audio, video, text, and other media from multiple sources. Specifically:
- With VR, a user can manipulate objects or collaborate with remote colleagues, without risk of injury or damage to equipment.
- With AR, elements of the digital twin can be blended into a person's perception of the respective physical counterpart. The AR experience, powered by the twin's digital content, is therefore placed at the intersection between reality and its digital representation.
Today, both VR and AR devices have spatial accuracy in the order of centimeters. When mechanical precision is critical, this granularity can limit the use cases. However, these visualization technologies will keep evolving as new products are continuously introduced in the market. With better accuracy in visualization, the digital twin will reach its full potential soon.
Discover the VR and AR technologies that will make digital twins even more immersive and effective.
Conclusion
The evolution of digital twins over the coming years will merge what is possible in the two different realities toward a cyber-physical continuum, allowing the actions of each world to influence the other. The opportunities seem truly boundless as the two worlds constantly monitor, learn from each other, and then adapt.
In every respect, some form of a digital twin will influence you, the place you work and even the world around you.
Jon Gamble, Ericsson, Imagine Studio, discusses how we can build on our existing digital reality with gamechanging technology.
A vision of 2030
Digital twins improve productivity, safety and quality and support sustainability targets by removing travel requirements and wastage
Contributors
Giulio Bottari
Master Researcher
Like what we do?