By AI Trends Staff
With the Covid-19 pandemic forcing its factories to close, BMW AG is taking the opportunity to accelerate deployment of AI in its factories.
Matthias Schindler, head of AI development for BMW’s production systems group, has actually set up AI-powered quality control systems in a lot of the company’s 31 factories over the previous three years, according to an account in the WSJPro He had generally set up and checked new AI systems during prepared work blockages throughout holidays, however the pandemic-related shutdowns allowed work to take place in the factories without facing production.
The extra quality assurance checks are especially crucial to BMW considered that vehicles are ending up being more customizable, with different interior surfaces, technical features, engine types and energy choices.
” We have diesel cars, we have petrol vehicles, we have hybrid cars, and, in the really near future, we will have fully electrical cars and trucks on the same line,” Schindler specified.
Schindler sent out teams to three plants in Bavaria to set up AI-based software application that scans photos of car parts for problems.
The image acknowledgment system analyzes still pictures taken by video cameras positioned at intervals throughout the assembly line. While parts are proceeding assembly lines, the checks detect abnormalities such as loose or missing screws. “Usually around 8,000 to 12,000 parts will be put together into a cars and truck, depending on the derivative,” Schindler mentioned. “The customer desires all these thousands of parts to be precisely as he has actually bought.”
BMW did have a system to inspect cars on the assembly line with cams, however the line needed to stop while the images were inspected by third-party software application versus target images. The old system tended to produce more incorrect positives, slowed the line and needed more manual checks. BMW’s flagship factory in Munich can produce nearly 1,000 vehicles each day, so the line pauses are pricey.
Press Store Makes Body Components Out of Blank Pieces of Metal
Journalism shop at the BMW Group’s plant in Munich turns more than 30,000 blank pieces of metal a day into car body parts. Given that a system integrating AI was installed in 2019, each blank has actually been given a laser code at the start of production, so the body part can be determined throughout, according to an account in metrology.news The code is picked up by the system, called iQ Press, which records parameters such as the thickness of the metal, oil layer, temperature level and speed of journalisms. The specifications are then related to the quality of the parts produced.
The data is published to the cloud in genuine time and is immediately readily available to the production group, so they can acquire a more clear photo.
Assistance for the advance of AI throughout BMW was likewise supported by Robert Engelhorn, Director of BMW Group Plant Munich. He specified in an interview, “At Plant Munich, it takes about 30 hours to produce a lorry. During that time, each car we make creates massive amounts of information. With the assistance of AI and clever information analytics, we can use this information to handle and examine our production intelligently.”
He added, “AI is assisting us to streamline our production even further and ensure exceptional quality for every single customer. It also saves our employees from needing to do tedious, repeated jobs. Our team in production are extremely experienced specialists, so they are the very best judges of whether an AI application can increase quality and efficiency at any provided phase of production.”
AI at BMW Can Paint, Too
BMW also recently started a brand-new pilot aimed at utilizing AI in the painting procedure, according to an entry on the BMWBlog The system will initially be set up in Munich and if results call for, worldwide.
Every brand-new cars and truck will be examined in the paint shop to collect data to be used towards dust particle analysis, which will be stored in a database ideally of best practices. The group will be developing AI algorithms that compare live data from dust particle sensors to the recommendation data, in the hope of determining any potential defect.
” Data-based solutions assist us secure and further extend our strict quality requirements to the benefit of our consumers,” stated Albin Dirndorfer, Senior Citizen Vice President Painted Body, End Up and Surface at the BMW Group.
As an example of how the system can be used, the data gathered by the system can determine if weather condition conditions are not optimal for painting. During extended dry durations, for example, the algorithms might potentially find whether the variety of dust particles has actually increased so that filters require to be changed. If that can not happen in time and the vehicle gets painted, it might not satisfy the quality requirement.
The paint system’s algorithm screens over 160 includes associated to the automobile body, thus is able to anticipate the quality of paint application very properly. BMW’s AI professionals are positive the new paint system will be suitable to be released in more of its factories throughout the world.