What's next for the digital twin

Digital Twin is a widely spread concept of creating a virtual representation of object state. The object may be small, like a raindrop, or huge as a factory. The goal is to simplify the operations on the object by creating a set of plain interfaces and limiting the amount of stored information. With a simple interface, the object can be easily manipulated and observed, while the state of its physical reflection is adjusted accordingly.

In  the automotive and aerospace industries , this is a common approach to use virtual objects representation to design, develop, test, manufacture, and operate both parts of a vehicle, like an engine, drivetrain, chassis/fuselage, or a full vehicle – a whole car, motorcycle, truck or aircraft. Virtual representations are easier to experiment with, especially on a bigger scale, and to operate - especially in situations when connectivity between a vehicle and the cloud is not stable ability to query the state anyway is vital to provide a smooth user experience.

It’s not always critical to replicate the object with all details. For some use cases, like airflow modeling for calculating drag force, mainly exterior parts are important. For computer vision AI simulation, on the other hand, user checking if the doors and windows are locked only requires a boolean true/false state. And to simulate the combustion process in the engine, even the vehicle type is not important.

Today,  artificial intelligence takes a significant role in a lot of car systems, to name a few: driver assistance, fatigue check, predictive maintenance, emergency braking, and collision avoidance, speed limit recognition, and prediction. Most of those systems do not live in a void - to operate correctly they require information about the surrounding world gathered through V2X connections, cameras, radars, lidars, GPS position, thermometers, or ABS/ESP sensors.

Let’s take Adaptive Cruise Control (ACC). The vehicle is kept in lane using computer vision and a front-facing camera. The distance to surrounding vehicles and obstacles is calculated using both a camera and a radar/lidar. Position on the map is gathered using GPS, and the speed limit is jointly calculated using the navigation system, road sign recognition, and distance to the vehicle ahead. This is an example of a complex system, which is hard to test - all parts of it have to be simulated separately, for example, by injecting a fake GPS path. Visualizing this kind of test system is complicated, and it’s hard to use data gathered from the car to reproduce the failure scenarios.

Here the Virtual World comes to help. The virtual world is an extension of the vehicle shadow concept where the multiple types of digital twins coexist in the same environment knowing their presence and interfaces. The system is composed of digital representation of physical assets whenever possible – including elements recognized via computer vision. Vehicles, road infrastructure, positioning systems, or even pedestrians are part of the virtual world. All vehicles are part of the same environment meaning they can share the data regarding the position of other traffic participants.

•  Such a system provides multiple benefits: Improved accuracy of assistance systems, as the recognized infrastructure and traffic participants can come from other vehicles, and their position can be estimated even when they are still outside the range of sensors.
•  Easier, more robust communication between infrastructure, vehicles, pedestrians, and cloud APIs as everything remains in the same digital system.
•  Possibility to fully reproduce conditions of system failure as the state history of not just vehicle, but all of its surrounding remains in cloud and can be used to recreate and visualize the area.
•  Ability to enhance existing systems leveraging data from the greater area - for example, immediately notifying about an obstacle on the road in 500 meters and suggestion to reduce speed.
•  The extensive information set can be used to build new AI/ML applications, like real-time weather information (rain sensor) can be built to close sunroofs of vehicles parked in the area.
•  The same system can be used to better simulate its behavior, even using data from real vehicles.
•  Common interfaces allow for quicker implementation.

Obviously, there are also challenges - the amount of data to be stored is huge, so it should be heavily optimized, and storage has to be highly scalable. There is also an impact of  the connection between the car and the cloud . Overall, the advantages overweight the disadvantages, and the Virtual World will be a common pattern in the next years with the growing  implementation of software-defined vehicles and machine learning applications requiring more and more data to improve its operations.

 NASA used a precursor to these technologies to bring the Apollo 13 astronauts back to Earth. Lockheed Martin claims these types of solutions are one of six game-changing technologies in the defense industry. The opinion-forming Gartner includes them in its list of ten strategic technologies that can streamline corporate decision-making processes. When Porsche and Volkswagen Group reach for them, it’s a signal for the automotive industry to  become interested in digital twin technology for good.

Although the concept of a digital twin had been developing in the space industry since the 1970s, it was not until the 1990s that it was first mentioned in the literature (the book entitled  Mirror World, by David Gelernter). In industry, the technology was recognized even later, 30 years after the Apollo mission, when the authority in the field of PLM - Michael Grieves - disseminated it.

Today, the technology, which was officially named Digital Twin by NASA just over 10 years ago, is placed on the pinnacle of key solutions at the convergence of the virtual and real world. It works well wherever there is a high number of failures, work of coupled systems, and where the production process is long and burdened with numerous risks.

The  automotive industry is one of these sectors, as demonstrated by the virtual car concept developed by Porsche for the new Taycan. What is a digital twin and what benefits does it bring?

•  test prototypes for their functionality, durability and user expectations;
•  predict defects and analyze possible design errors;
•  save time and financial means;
•  reduce design and production risks;
•  improve monitoring capabilities of vehicle fleets;
•  and best of all - it enables continuous product improvement, as it often collects data from not only one, but thousands of objects. This makes it learn faster and predict defects more precisely, as it is based on knowledge gathered from a vast  number of sources.

In the case of cars, these could be sensors from dozens of systems spanning the entire vehicle lifecycle: from research and development to the manufacturing plant and  OTA updates , to  connected services .

„Chassis twin” - a virtual car concept developed by Porsche for TaycanThe „chassis twin” project has been in the process of development at Porsche for the past three years and then it was continued by the CARIAD company (the Volkswagen Group's vehicle software provider). The air suspension of the new Porsche Taycan was chosen as the main object.

Why the chassis and not the entire car? Because it is this part of the vehicle that is subjected to the most strain, especially on racetracks.

Porsche engineers used intelligent neural algorithms to centrally analyze the data, and in-car sensor data was collected not only from Porsche cars but also from Volkswagen Group vehicles. This increased the data pool by over 20 times. The "chassis twin" concept enables chassis loads to be detected, even if they are not noticeable inside the cabin, and notify the driver before faults appear, even when no suspicious sound or vibration has yet been noted by the driver or mechanic.

The data collected by the vehicles is sent via Porsche Connect to a  central system in the cloud , where an algorithm calculates the relevant durability and vehicle operation thresholds for the whole fleet of vehicles to create a baseline. When these are possibly exceeded, the driver of a specific vehicle receives a notification via Porsche Communication Management (PCM), that the chassis may require inspection. Looped into the computational work, the algorithm recommends not only the type of service needed but also the scope of work to be carried out in the service center.
By removing a faulty or overloaded component early on, the driver will not only be able to avert potential malfunctions, but also keep the vehicle in better overall condition.

In the future, based on a vehicle's digital usage history, Porsche or a  partner insurance broker can offer extended warranties and better services to the driver . The data can be classified, analyzed, and used not only for repairs to a specific vehicle but to predict life-cycle events for the entire product. This allows Porsche to create new services and features, and to test different scenarios for the development of a particular vehicle line. Thus, it saves the time and resources required to bring ill-conceived solutions into reality.

The other possible use case is that drivers themselves can use the  data collected by the digital twin to negotiate with the prospective buyer. The buyer can view the vehicle's overall condition and chassis service history.
As for drivers' concerns about their own privacy, the manufacturer assures that it collects data anonymously and the system does not store any information that could identify the driver directly. The future of the concepts digitization of the automotive industry is gaining pace year after year. The digital twin concept may prove to be one of the key technologies that will push  software-defined vehicles to new tracks and help companies create safer cars, provide new services and increase vehicle lifespan.

So far, half of the Taycan users have signed up for the Porsche pilot program, which collects data from the chassis of their sporty electric cars. In 2022, the program is to launch at a test level, and only sensor data directly from the mechatronic components will be evaluated. In the future, the concept is to reach its full potential, making it possible, among other things, to calculate the wear and tear of specific components without the need for physical measuring devices.

How will the  "chassis twin" model developed by Porsche work out ? The future will tell. What is certain is that a return to the past is only possible in the movies. In 2022, Volkswagen is commencing an era in which a virtual equivalent will soon await the driver, in addition to their actual real vehicle.

 Retail stores and factories are being cloned for the virtual world, for familiarity and efficiency. Now it's time for automotive, which is more and more willing to use digital twin factory. This innovative technology perfectly bridges the real and virtual worlds. It is already happening now, for instance in BMW factories.

Digital twin and Industry 4.0

The fourth industrial revolution necessitates the use of advanced data-driven technologies. This includes digital twins. It's an idea that allows you to simulate products, services, and entire processes for creating more efficient and faster quality solutions.  By using video, images, diagrams or other data for advanced 3D mapping, a new virtual reality is created.

This concept is becoming increasingly common in various market sectors, including  automotive . Not only     individual vehicle parts   , but even entire factories are already being created in the digital space. The latter can be seen, for example, at BMW.

But it is also being used in many other sectors, not just the industry as such. For instance, tests are being carried out to use the technology for surgical treatment of patients with heart conditions - so digital twins would be used for the advanced replication and examination of internal organs. Besides, they would enable faster development of prototypes of even such machines as airplanes. Architects, by contrast, no longer have to rely solely on their imagination in such a scenario, but can use perfectly reproduced models of skyscrapers, accurate down to the nearest centimeter.

Digital twins enter factories now

Just imagine this scenario: the opening gate of a manufacturing plant. Coating a car door with paint. Workers, going from section to section, carrying out their jobs. Except that these are just very realistic simulations. And the workers are, in fact, only avatars. This is how the idea of the digital twin in the automotive industry can be summarized.  It's creating a separate, comprehensively perceived manufacturing process.

 The digital twin in the automotive industry includes a virtual replica of the entire car and its physical behavior, including software, electronics, mechanisms, etc. And it can additionally store all performance and sensor data in real-time, as well as configuration changes, service history, and warranty information.

Making the digital twin a reality at BMW

 This trend is already becoming widespread. For example, at the German BMW factory. The virtual three-dimensional replica of the vehicle factory used by the company is a space reproduced down to the smallest detail, which can be accessed using a screen or VR goggles. Why " dabble" in such technology at all? To save money, at least, among other things. Non-physical, virtual resources  allow you to test or improve assembly line parts without having to move or operate on heavy machinery.

Machine learning algorithms also help in managing robots. These, in a simulated version, can make various complex moves  to make the process as streamlined as possible. And all this without wasting energy on time-consuming tests. Besides, this way robots learn new ways of working.

Advanced software also simulates,e.g., the behavior of workers: their paths of movement and actions. By doing so, an attempt is made  to minimize possible ergonomic problems. Frank Bachmann, BMW's factory manager, says the time needed to plan the factory's operations has been reduced by at least  25 percent . Anyway, the changes are happening  as we speak , because even before the individual parts of the drive systems for electric vehicles leave the BMW plant, the entire production process is already finalized in the virtual version of the Regensburg factory.

The aforementioned benefits are such a boon for BMW that the company intends to develop more of this type of technology. Their soon-to-be-introduced twin factory model is expected to be a replica of the factory in Hungary, and subsequently, this will apply to other factories around the world.

Innovation driven by synergistic collaboration

BMW is an automotive giant that promotes and uses the virtual technology of tomorrow not alone, but with the right support from technology companies that are responsible for the software implementation. In the case of the German automotive brand, the partner is the chip company, Nvidia. It uses its proprietary Omniverse system, which offers the possibility to simulate the entire production process, taking into account even such physical factors as gravity.
Clearly, everything is to be conducted in the framework of photorealistic detail. This complex virtual environment allows for the creation of diverse 3D models. It's also innovative in the sense that Omniverse's open file standard is compatible with numerous computer-aided design packages. Richard Kerris, general manager of Omniverse at Nvidia, refers to the project as "one of the most complex simulations ever made".

But the solutions do not close at Invidia, and automotive companies can also choose from other offers of technological implementations. And there is every indication that there will be more and more of these offerings. For example, in November 2021, Amazon unveiled the  AWS IoT TwinMaker , a service that generates digital duplicates of real-world systems for business. An immersive 3D view of systems and operations enables optimizing efficiency, increasing production, and improving performance.  So does the  platform-as-a-service (PaaS) offering,     Azure Digital Twins   . It enables the creation of digitally based models of various environments such as buildings, factories, power grids, and even entire cities.

Use cases, in other words: how can the concept of digital twin be used in the automotive industry?

It may seem to some that creating digital twins in the automotive industry is unnecessary "gadgetry" or blind following of trends.

After all, why simulate the creation of a vehicle? Isn't it better to spend time, energy, and resources on improving what is already underway? Isn't it better to invest in the REAL production result? All of this is not so simple. Especially when you realize that this technology is not just about virtualizing the vehicle development stage.  The idea behind digital twin factories focuses not so much on the development of the cars themselves, but on the entire broad ecosystem. It is about creating and sustaining, in a controlled environment, the entire production environment:

•  logistics,
•  employees,
•  deployment of machinery,
•  chain value.

Ding Zhao, a Carnegie Mellon University professor specializing in artificial intelligence and digital simulations, argues that simulations are crucial to the industry. This is the case for two reasons. First, it's about simulating dangerous situations. Under "normal" circumstances, this is often simply impossible. Just as impossible is running machines for millions of cycles each time, only to collect the necessary data for analysis.

The simulation, therefore, takes into account the entire environment of the production process.  It is a comprehensive and all-encompassing view of the problem. A virtual answer to the question of real needs, and of real benefits. And these are numerous.

Prediction first

The digital twin gives people in charge of maintaining productivity in a factory an important "weapon" to fight against financial loss. It's called predictive maintenance. Predicting what's to come saves resources and allows us to better plan future production and sales activities.

This ranges from product testing, determining maintenance needs and line improvements, to turnover planning. For instance, different types of chassis can be tested in diverse weather conditions. In a virtual world, of course. What is more, such solutions can be tested right away by customers, who will thus immediately share their impressions of the product. So you get feedback even before the solution is released on the market.

OEMs can maintain a twin vehicle of each VIN and software number and can do  updates wirelessly (SOTA) or temporarily enable or disable some features.

In the simulation, for example, you can also pay attention to functionalities that drivers rarely use. If something doesn't work, you can back out of the idea, even before it is implemented.

In addition, it is also possible to configure the infrastructure of factories so that employees can be trained remotely without physically installing the equipment. This opens up further possibilities for the internationalization of a brand. In this way, a manufacturing company in the U.S. can train a new team in Japan even before the plant in the Land of Cherry Blossoms is completed.

Improving manufacturing capabilities

The technology described here yields huge savings not only in terms of money but also in terms of time. In the traditional automotive industry, companies have to focus too long on verifying new features or designs. And all because they have to wait for the production process to be completed.

The digital twin clears this hurdle.  You can easily test the impact of a new machine with new features and parameters for your production output. It's a fast, yet reliable way to verify the success and performance of an innovative project.

Effective data management

Virtual simulation technology allows for  reliable data analysis , both present, and past. All data, e.g. regarding stoppages or configuration changes, are collected in real-time. So you can see exactly when machine stoppages are likely to occur. And not only that.

As a result, people in decision-making positions can  plan uninterrupted production with minimal financial loss. And car dealers, having an insight into a vehicle's service history, know exactly what they are marketing.
Based on this, you can also better  anticipate customers' demand and improve customer satisfaction when using the car.

Importantly, the data collected is integrated and unified across several sources simultaneously. It is not a problem to  get insight into     performance data, driver behavior data    , and archived information on previous models.

Perfect finish

As you may be aware, the production of a new model may take even 5-6 years, therefore even a minor oversight may disturb the stability of a company, especially when it concerns the flagship and widely advertised model.  For image and financial reasons, it is particularly significant today that the product is competitive, reliable and perfectly developed.

What is the conclusion? Even a small omission can impair the stability of a company, especially when it involves its flagship and widely advertised model.  For image and financial reasons, what matters today is that the product is competitive, reliable and perfectly developed.

The digital twin, which allows design and simulation in a completely virtual environment, favors the creation of products perfect in every detail. High-performance rendering and visualization tools allow you to select from a wide variety of materials and textures. And nothing stands in the way of optimizing airflow or heat emission. Every detail will be planned.

Why use a digital twin?

There are many benefits when using a digital twin in automotive. A simulation of this type means:

•  an optimal design of the production process already at the digital copy stage, rather than on a "living organism".
•  saving time and money. By "getting ahead" of future production problems.
•  a better estimate of production line extension costs
•  an easier analysis of each stage of the production process for so-called "bottlenecks".
•  faster, more interactive communication between vehicle designers, stakeholders and end customers.
•  improved ergonomics at all workstations in the plant.
•  the determination of product behavior throughout the life cycle. Thus facilitating R&D work.
•  the ability to reuse proven models and quickly evaluate the impact of changes.
•  an option to integrate all data between the previous vehicle generation and the current vehicle design in a digital model.

Clearly, this is one of the most cost-effective data-driven manufacturing concepts today.

Digital Twin factory. No longer science fiction

The concept of digital twins in  the automotive industry is the future, not science fiction. Before long, every factory or building will have a digital counterpart, helping to better manage it.

The digital and real worlds will seamlessly intertwine. The convergence of physical and virtual versions offers the possibility of overcoming various challenges that are now commonplace in the automotive value chain.

The most powerful giants, with BMW at the forefront, know this.  Everything indicates that soon every manufacturer in the industry will have to consider investing in such solutions at some stage and to some extent. Anyway, from the company's point of view, it is not a sacrifice, but a chance to develop against the competition. And an opportunity to achieve numerous measurable benefits.