Skip to content

Following a successful pilot project, Audi has begun deploying an artificial intelligence (AI) system to monitor the quality of on-site welding in car body construction. AI is already developed and tested at the Neckarsulm site.

By the end of the year, the technical infrastructure for the use of AI will be installed at three other locations of the Volkswagen Group. The project will serve as leverage for Audi’s Automotive Initiative 2025 (AI25).

Using artificial intelligence, Audi checks around 1.5 million spot welds on 300 vehicles every shift at the Neckarsulm site. In comparison, until recently, production workers used ultrasound to monitor resistance spot welding (abbreviated in German as WPS) processes in random analyses. They have verified approximately 5,000 spot welds per vehicle using the ultrasonic method. By implementing AI, employees can now focus on the unusual things that might happen. This new approach allows them to control quality more efficiently and effectively, says Audi.

IMG_0208

During resistance spot welding (WPS) production at the Neckarsulm site, Audi uses artificial intelligence to analyze up to 1.5 million spot welds from 300 vehicles per shift.


Preparations have already begun to use the technology at other plants in the Volkswagen Group. For example, the technical infrastructure used for AI is currently installed in Audi Brussels. The Volkswagen plant in Emden is due to install the necessary infrastructure this year, as is the Audi headquarters in Ingolstadt.

To install the technical infrastructure in these areas, a team of experts is currently identifying differences in the weld settings to train the AI ​​model accordingly.

The information generated using AI can be used to optimize other processes in the future. As an example, the Audi team is currently working on using the data as a basis for predictive maintenance on the road.

Digitalized assembly lines are the basis of Audi’s vision for the future of production: as part of our 360 factory production strategy, we make production more efficient at Audi locations. In this regard, the use of artificial intelligence in continuous production promises great potential.

– Gerd Walker, Audi Board Member for Production and Logistics

For process audits and certifications, development at the Neckarsulm area is carried out in close cooperation with the German Association for Quality (DGQ), the Fraunhofer Institute for Industrial Engineering (IAO) and the Fraunhofer Institute for Manufacturing. Engineering and Automation (IPA).

This approach reflects the current lack of independent standards or certifications for AI applications.

This means that, for example, it is possible to show with certainty how AI-based test results in manufacturing.

—WPS-Analytics project managers Matthias Mayer and Andreas Ricker

Audi has developed AI guidelines for production with the Fraunhofer Institutes IAO and IPA.

The project “WPS-Analytics” also serves as a use case for the Automotive Initiative 2025 (AI25) launched by Audi. The initiative aims to establish a competence network for digital factory transformation and innovation. Audi wants to use digitalization to make production and logistics more flexible and efficient. On the way to a smart factory, Audi and its science and IT industry partners are testing digital solutions to produce premium vehicles in a real manufacturing environment in Neckarsulm and then deploy them in series production.

[ad_2]