Artificial intelligence arrives at the Group's production BMW

Artificial intelligence has become the Group’s new challenge BMW. Now it has been installed in its plants with the aim of improving production.

Artificial intelligence arrives at the Group’s production BMW, and this technology continues to grow in the automotive sector. Since 2018, the German group has been using it in several applications in series production. The first focus is image recognition, where artificial intelligence evaluates and compares images in milliseconds. In this way, the AI application determines possible deviations in real time.

According to Christian Patron, Head of Innovation, Digitalisation and Data Analysis in the production group of BMW, the innovative technology is fast, reliable and, most importantly, easy to use. “Artificial intelligence offers great potential. It helps us maintain our high quality standards while freeing our people from repetitive tasks.”

It is important to highlight that in the German group, flexible, cost-effective, AI-based applications are replacing permanently installed camera portals. AI can also be configured quickly. Employees photograph the component and mark possible deviations. This creates an image database to build a so-called neural network that will be able to evaluate images without human intervention.

https://www.youtube.com/watch?v=V6MmMYjXScI

BMW’s new challenge, artificial intelligence

The artificial intelligence can also carry out more demanding inspection tasks. In the final inspection area at the brand’s Dingolfing plant, an application compares vehicle order data with a live image of the produced model designation.

If the live image and the order data do not match, the final inspection team receives a notification. Christian Patron added that “we fully rely on the experience of our employees in these efforts. They can best judge in which production steps an AI application can improve quality and efficiency. We deliberately keep the configuration and implementation of such applications simple. Their operation does not require advanced IT expertise.”

In the press shop, flat sheet metal parts are turned into high-precision components for the car body. Dust particles or oil residues that remain on the components after forming can easily be mistaken for very fine cracks, which occur in rare cases during the process. Camera-based quality control systems at the BMW Group plant in Dingolfing, Germany, also occasionally flagged these pseudo defects: deviations from the target, although there were no real faults.

With the new AI application, these pseudo defects no longer occur because the neural network can access around 100 real images per feature, i.e. around 100 images of the perfect component, 100 images with dust particles, and another 100 images with oil droplets on the component.

https://www.youtube.com/watch?v=HomqovOH0sc

Artificial Intelligence, integration into plant control

The first intelligent artificial intelligence control application of BMW Group debuted at the Steyr plant of BMW Group. This application speeds up logistics processes by avoiding unnecessary transports of empty containers on conveyor belts. To do this, the containers pass through a camera station. Using the stored image data marked by employees, the AI application recognises whether the container must be strapped to a pallet or whether, in the case of large and stable boxes, no additional securing is required.

If no strapping is required, the AI application directs a container by the shortest route to the forklift removal station. Containers that must be additionally secured, on the other hand, are guided directly to the conveyor section with the strapping system and only then to the removal station located behind it. Previously, all containers had to be transported to the removal station for large containers. From there, containers requiring additional securing had to be sent back, and only after this detour would they reach the strapping installation and finally the correct removal station.

There is already a clear trend towards the use of AI applications in the plants of BMW Group. The growing integration of intelligent data analysis, cutting-edge measurement technology and artificial intelligence opens up new opportunities in production management.