Automobile production meets software

Whether it relates to cars, factory floors, networks, or entire cyber systems, the term "software-defined" is currently on everyone's lips. but what it actually means is open to a wide variety of definitions, and the debate on the subject almost takes on philosophical dimensions.

"The way I see it," says Prof. Michael Weyrich, head of the Institute of Industrial Automation and Software Engineering (IAS), "we need to go much further than that: rather than simply using software to configure systems, our goal is to create entirely new interconnected systems. Software creates a parallel world to the mechanical world, a world of information in which data and rules can be interchanged and shaped. The resulting functionalities are not only derived from the individual modules, but also from their interaction in an environment of parallel information. New 'smart products'", he continues, "are being created, which are capable of tackling completely new tasks. The upshot of all of this is that, in the long run, software-defined products will not only improve existing systems, but will actually provide an opportunity to create novel system capabilities."

Both of these perspectives are reflected in two major projects; the "Software-defined Manufacturing for the Automotive and Supplier Industry" project (SDM4FZI, spokesperson Prof. Alexander Verl, ISW) and the "Software-defined Car" project (SofDCar, spokesperson Prof. Michael Weyrich, IAS), being carried out at the University of Stuttgart under the auspices of BOSCH in collaboration with the Karlsruhe Institute of Technology (KIT) and numerous other partner organizations from science and industry. The German Federal Ministry for Economic Affairs and Climate Action is providing millions of euros in funding for these projects. Both projects are linked to the novel research area "Software-defined Mobility",which is being pursued at the University of Stuttgart's Innovation Campus Mobility of the Future (ICM), of which both professors are members of the board of directors and to which the two institutes are contributing numerous scientists with funding from the state of Baden-Württemberg.

Researchers in the SDM4FZI project hope to develop production engineering solutions that will enable small and medium-sized enterprises to adapt quickly, flexibly, and efficiently to demand fluctuations, supply bottlenecks, and the demand for bespoke products. Other University of Stuttgart partners include the ISW (which is heading up the consortium), the IAS, and the Institutes of Industrial Manufacturing and Management (IFF) and Software Engineering (ISTE).

The inspiration for the SDM4FZI project arose from discussions between the ISW and BOSCH on how to make factories less rigid in the future. "We at the Institute and the partner companies have been working on the concept of flexibility for a long time, and the software-defined manufacturing method was developed collaboratively by ISW and BOSCH," says Alexander Verl. The core idea is that contemporary information and communication technologies are being introduced into operational technology (OT), i.e., the systems and processes used to control and monitor industrial plants and processes. Our goal is to design a factory that is primarily self-organizing and adapts automatically. Yet so far, only a few companies in the supplier sector in particular have taken full advantage of the opportunities offered by digital technology. "With this project," says Verl, "we now want to create a framework that will help these companies move forward in terms of exploiting the benefits of virtualization, standardization, digital twins, and data models.”

As project coordinator Michael Neubauer explains, the key lies in radically decoupling software and hardware: "Think of it like a smartphone, where you first buy the hardware with its operating system,” he explains: “Applications can be installed as needed, turning the phone into anything from an MP3 player, to a calculator, or a Gameboy. Our aim is to develop a similar approach for production technology.” To date, however, this has been hampered by the fact that production systems, as well as those used across the various stages of the supply chain, are based on totally different system architectures, which have been developed organically for specific applications and neither speak the same language nor are able to exchange data with each other.

To achieve this and create a virtual representation of the production system, data models are used to describe the three central elements of production, i.e., the products, manufacturing processes, and resources (e.g., machinery), whereby the reference model forms a meta-level that describes the relation between the various data models. Once these relationships are understood, it becomes possible to dispense with rigid production processes and to modify specific process steps or bring in other pieces of equipment during the production sequence in order to optimize the process as a whole.

The Digital Twins mentioned above are a key element in the practical implementation of software-defined manufacturing. "These," as Verl explains, "describe the production process by means of data, information, and behavioral models created over the entire machine or product life cycle. Coupling a piece of equipment with the digital twin allows for a more efficient process, less downtime, and better product quality."

The SDM4FZI partners want to show how the interaction between the virtual and real worlds actually works in the "Stuttgart Machine Factory", a software-defined factory in the ISW's machine hall, in which the production technology of a manufacturing plant is simulated using real industrial machinery and equipment as well as logistics systems. The factory uses a variety of manufacturing processes to autonomously produce complex products with a whole range of distinct features. "Using this approach," says Michael Neubauer, "it is possible to model the products in the virtual world first in order to plan the interaction between different resources and, if necessary, to revert to a plan B or C. One can also predict manufacturing quality, production costs, and lead times in this way and adjust the strategy before a plan is implemented in the real world with the associated real costs."

Under the leadership of Prof. Michael Weyrich of the IAS, eight working groups from three departments at the University of Stuttgart as well as the Research Institute for Automotive Engineering and Powertrain Systems Stuttgart are collaborating in the Software- defined Car project (SofDCar). As Weyrich explains, while SofDCar also has its sights set on the automotive industry, its focus is different: "The corporate and product scene that we want to network," he says, "is dominated by a handful of major manufacturers and suppliers, who have the power to influence systems in a very significant way. But on the product side, there are currently many millions of vehicles all over the world using the roads under a plethora of technical, legal, and ethical framework conditions."

Researchers in the SofDCar project are focusing on electrical, electronic, and software architectures in a completely novel way by putting the software at the forefront of the system, whereby there are two distinct levels involved. The first step is to get control of the over 100 control units and functions commonly found in existing vehicles. "However," says Weyrich, "the bigger picture is different. The novel thing about our approach is that we think of every individual vehicle as a node in a networked vehicle and system topography.” And, as project coordinator Matthias Weiss explains: "Another of our goals is to enable the digital sustainability of existing and future generations of vehicles, as well as using data effectively, in addition to which we are also looking at innovative use cases throughout a vehicle's lifecycle."

All elements of networked vehicles continuously transmit and receive information, whether within the vehicle itself, between different vehicles, or between the vehicle and the traffic infrastructure, such as stoplights or parking facilities, so the big question is how to implement these connections via a software architecture, which is where SofDCar's digital twin comes into play, which can map the information pool of an entire fleet and, more importantly, manage the so-called "data loop", i.e., the connection between the circulating vehicles and the manufacturers. This feedback loop is currently static but the respective measurements will be dynamically adaptable and continuous across the entire vehicle fleet in the future. As Weiss points out: "This data can be used for development purposes throughout the entire life cycle of a given vehicle with a view to permanently honing the algorithms and, in turn, the vehicles themselves."

Of course, this means that one first has to identify the bugs, which is something that Dr. Andrey Morozov, a Junior Professor at the IAS, who is also working on both projects, specializes in. His focus in the SofDCar project is on anomaly detection. "Our task," he says, "is to check the data to verify that everything is okay.”

Not an easy thing to do in complex cyber-physical systems, in which it is difficult to identify the exact reason for the malfunction, which, as Morozov explains, is why troubleshooting is carried out at different levels. For example, faults at the component level manifest themselves in the form of sensor, control system, or network errors. More complex problems can be detected at the vehicle level, which result from component interactions, for example, when the vehicle accelerates but the sensors indicate that its speed is decreasing. Any unusual behavior on the part of the driver could also indicate that something is wrong. And, at vehicle fleet level, the focus is on traffic anomalies. "The hardest thing in this context," as Morozov explains, "is to recognize which indicators are relevant at any given moment within the infinitely vast amount of available data. It is critical to dynamically manage what we are paying attention to depending on the context. If, for example, we are charging an electric car in the garage, we need to focus on the battery controller, but when driving in the city at rush hour, we need to focus more on our surroundings."

Morozov and his team are using artificial intelligence and deep learning to enable the vehicle to autonomously identify the plethora of potential anomalies in the system as a whole. The research team already developed a so-called "KrakenBox" in 2020, which is a device that can be programmed with the aid of a neural network to autonomously detect faults in industrial cyber-physical systems with no human intervention. Morozov emphasizes the fact that neural networks are particularly well suited to deal with these issues because, as he explains: “they are good at remembering the origins of a given signal and predicting its future development. By comparing this forecast with what actually happens, you can then assess whether something might go wrong in the near future."

So, whereas Morozov focuses on risk mitigation in the SofDCar project, his contribution to the SDM4FZI project is all about risk analysis, which has traditionally been a one-off process before a system goes into operation. But, in the case of software-defined manufacturing (SDM), any software update could have a potentially drastic impact on the process and create new risk scenarios: new hazards are continuously emerging, so the risk analysis also needs to be automated in order to be carried out before any software update. Researchers use risk assessment models to describe how likely a disruption is to occur and what damage it may cause. However, as Morozov explains, the problem is that: "The number of potential risk scenarios rises exponentially in any complex system."

In addition to these technical hurdles, software-defined systems are also subject to tricky legal and ethical issues. For example, as Weyrich explains, in this "delicate information scenario," the built-in sensor systems needed for automated and autonomous driving facilitate the collection of a wide range of data about the vehicle, its occupants, and its surroundings, such as video recordings of what is happening inside and outside the vehicle. Various countries and even continents have very different views of what is desirable, still permitted or prohibited, and in some cases the respective standards are even contradictory. Weyrich is aware that "there is an enormous amount of social tension relating to this field, which still receives little attention,” and resolving these issues goes beyond the project scope. But the IAS director emphasizes: "This is something that we are continuously discussing in relation, for example, to the European Commission's legislative framework, as well as in numerous other initiatives. This involves some difficult questions, but we are wide open to the relevant discussions."

A digital twin is a virtual replica of a real-world object, which makes a comprehensive exchange of data possible and enables complex products and processes to be modeled, tested, and optimized in the digital sphere before being manufactured and later operated in the real world. Digital twins comprise one or more models of the object or process they represent, and may also include simulations, algorithms, and services that describe, influence, or provide services in relation to the properties or behavior of the modeled object or process. Digital twins are an indispensable part of so-called Industry 4.0 developments and the Internet of Things and could become part of our everyday lives in the future, not only in the manufacturing and automotive sectors, but also in such areas as medicine and "smart" living.

Editor: Andrea Mayer-Grenu