Robotic revolution
Audi looks to revolutionise the testing process in production with artificial intelligence.
Audi is promoting artificial intelligence in a new, quality control application.
22 October, 2018
Artificial intelligence is entering the production and quality control sphere at Audi , thanks to new software developed by the brand that recognises and marks the finest cracks in sheet metal parts – automatically, reliably and in a matter of seconds.
With the increasingly sophisticated design of its cars and the high quality standards at Audi, the company inspects all components directly after production in the press shop. As well as visual inspection by employees, several small cameras are installed directly in the presses, which evaluate the captured images with the help of image-recognition software. This process will soon be replaced by the new ‘machine learning’ (ML) procedure – the software based on a complex artificial neural network that operates in the background of this innovative procedure.
The software detects the finest cracks in sheet metal with the utmost precision and reliably marks the spot. The solution is based on deep learning, a special form of machine learning that can operate with very unstructured and high-dimensional amounts of data such as with images. The team spent months training the artificial neural network with several million test images. The biggest challenges were on the one hand, the creation of a sufficiently large database, and on the other hand, the so-called labelling of the images. The team marked cracks in the sample images with pixel precision – the highest degree of accuracy was required. The effort was worth it because the neural network now learns independently from the examples and detects cracks even in new, previously unknown images. The database consists of several terabytes of test images from seven presses at Audi’s Ingolstadt plant and from several Volkswagen plants.
In the future, it will be possible to apply the ML approach also for other visual quality inspections. If a sufficiently large number of labelled datasets are available, the system can also support paint shops or assembly shops. The sky is the limit.
Machine learning will ensure even higher standards of finish
Subscribe
Want to ensure you always receive the latest news and features from Audi? Subscribe now to the Audi Magazine newsletter.
Audi Australia will collect, record and use your personal information for the purpose(s) of sending you the requested newsletter. You are not required to provide your personal information, however, if you choose not to provide us with your personal information, we may not be able to fulfil the purpose(s) described above. We will keep your personal information for only as long as is necessary to carry out the purpose(s) described above (unless we are required or permitted by law to hold the information for a longer period). We may disclose your personal information to our service providers and to our dealership network in Australia. We may also disclose your personal information to our related parties based in Australia and to our overseas service providers. We may, unless you have opted out, use your personal information to market our products and services to you, to improve our products and services and to invite you to events. We will act in accordance with our privacy policy which is available at http://www.audi.com.au/privacypolicy. If you would like to know more about our privacy policy and procedures and the management of your personal information, or if you would like to access or update your personal information, please contact our customer assistance team, T +1800 50 AUDI (2834), E customerassistance@audi-info.com.au