Audi’s factory of the future technology unveiled

Car manufacturer Audi has revealed how it is setting up a fully networked, highly efficient and sustainable production system.

The goal is to design a resilient, agile, and flexible value chain to meet future challenges successfully. These include a growing diversity of variants, the transition to electromobility, the increasingly volatile supply situation, and political uncertainties.

“We’re using synergies and looking at production as a whole – from the worker to the fully automated cycle,” said Gerd Walker, member of the board of management for production and logistics. “We’re digitizing specifically within the framework of an open innovation culture. We’re ensuring efficient value creation and making it possible to utilise resources and capacities flexibly and efficiently.”

Modular assembly

Audi says the traditional automotive assembly line is increasingly reaching its limits. Numerous derivatives and individualisation options are making products more and more varied. In a rigid, sequential process, that complexity is more and more difficult to master.

“Modular assembly is one of our answers to future challenges,” said Mr Gerd Walker. “We’re using digital technologies specifically to our employees’ advantage while obtaining a more flexible and efficient assembly process.”

In the Audi Production Lab, project manager Wolfgang Kern’s team is preparing modular assembly for mass production.

Audi is initially implementing the concept in interior door panel pre-assembly in the Ingolstadt plant. In the test operation, work no longer follows a uniform sequence. Instead, it meets particular needs.

Automated guided vehicles (AGVs) bring door panels right to the station where the components are assembled.

Audi's Automated guided vehicles (AGVs)
Audi's Automated guided vehicles (AGVs)

“By reducing production time through an orientation toward value creation and self-guidance, we can increase productivity by up to 20% in some cases,” Mr Kern said. “In addition, we can link the modular assembly to specific production steps. For example, now, a single worker can install complete sun blinds. That used to require two or three workers due to the preset processing times in an assembly line.

Virtual assembly planning in smart production

Virtual assembly planning not only saves material resources but also makes innovative, flexible collaboration possible across different locations. It eliminates the need to build prototypes in the planning process. A scanning process generates three-dimensional point clouds that can be used to virtually reverse engineer machines and infrastructure. The software is based on artificial intelligence and machine learning. It makes it possible for employees at Audi to navigate through assembly lines virtually. Volkswagen’s Industrial Cloud gives them an efficient tool that allows them, for example, to compare locations and use appropriate solutions from other production lines in their planning.

Right now, Audi is working with NavVis to test Spot the robot dog so they can do the 3D scans as efficiently as possible. Around four million square meters and 13 plants have been involved since site digitalisation started in 2017. Scanning 100,000 square meters – for instance, in Audi A6 production in Neckarsulm – takes about three weeks in single-shift operation. The scans can only be done at night or on weekends. On top of that, structural obstacles like steps and doors make scanning work more difficult.

By contrast, Spot the robot dog can do that scanning in 48 hours and figure out his route autonomously. Audi has been testing Spot intensively since December 2021.

Spot the dog
Spot the dog

“The test results are extremely promising and can be updated regularly,” said project manager André Bongartz. “Input data are constantly coming in, and we can use it in planning for new car models.” Any range of 3D scans can be integrated into the virtual images, which Andrés Kohler’s team is responsible for. “Merging all the planning data in our digital twin has given us a holistic look at our future production plans years ahead of time,” Kohler explains. Like in a real factory, it includes the shop floor, conveyor technology, tools, shelving, and containers alongside the new Audi model.

Assembly sequences and logistical aspects are largely designed and optimized by interdisciplinary teams in what is known as 3D process workshops. Thanks to the digital twin and an in-house VR solution, Audi exploits the benefits of digitalization and visualization. These include component data that are updated daily and a view of various car variants. “Above all, we look at production in terms of what it will look like later on as a whole,” Andrés Kohler explained. He emphasizes that collaboration remains a core element: “I’m always fascinated all over again the moment we put on the VR glasses and meet our colleagues as avatars in the virtual world. First, we build our new Audi there or look at a computer-generated avatar and how it applies as a real-time simulation. And when necessary, while we're in there together, we discuss and optimize the sequences and the workplace environment, like how to set up materials of what tools are needed.”

Artificial intelligence in production

Artificial intelligence and machine learning are core technologies in Audi’s digital transformation and modern production. An AI algorithm in the Ingolstadt press shop helps identify flaws in components. That procedure is supported by software based on an artificial neural network. The software itself identifies the smallest flaws and reliably marks them. The solution is based on deep learning, a special kind of machine learning that can work with unstructured and high-dimensional data volumes. The team used several million test patterns to train the artificial neural network over months. That database comprises several terabytes of these images from presses at Audi sites and several Volkswagen sites.

In another pilot project, Audi uses artificial intelligence to check the quality of spot welds in high-volume production at its Neckarsulm site. It takes about 5,300 weld spots to connect the components in the body of an Audi A6 with one another. Until now, production staff have used randomized ultrasound analyses to monitor the quality of resistance spot welding (abbreviated WPS in German). As part of the WPS Analytics pilot project, experts use artificial intelligence (AI) to detect quality anomalies automatically in real-time. Currently, the algorithm, dashboard, and deep quality analysis application are all used to construct the body of the A6 and A7. It is a blueprint for other applications in networked production.

Edge Cloud 4 Production concept

With the local server solution Edge Cloud 4 Production, Audi is initiating a paradigm shift in factory automation. After successful testing in the Audi Production Lab (P-Lab), three local servers will take over worker support in the Böllinger Höfe. In production in Neckarsulm, the Audi e-tron GT quattro1 and the R8 share an assembly line. The small-scale series produced there are particularly well suited for testing projects from the P-Lab and trying things out for large-scale series. Audi wants to be the first manufacturer in the world to turn to these kinds of centralized server solutions in cycle-dependent production. If the server infrastructure continues to operate reliably, Audi wants to roll out this automation technology – the only one of its kind in the world – for serial production throughout the group.

With the Edge Cloud 4 Production, a few centralized and local servers will take on the work of countless expensive industrial PCs. The server solution makes it possible to level out the virtualized clients across the total number of them – a far more efficient use of resources. Production will be economized, particularly where software rollouts, operating system changes, and IT-related expenses are concerned. “What we’re doing here is a revolution,” says Gerd Walker, Member of the Board of Management of AUDI AG Production and Logistics. “We used to have to buy hardware when we wanted to introduce new functions. With Edge Cloud 4 Production, we only buy applications in the form of software. That is the crucial step toward IT-based production.”




Related Articles
Most recent Articles

Login / Sign up