The BSH Startup Kitchen is an initiative that offers young companies the possibility to collaborate with BSH by offering their cutting-edge solutions to improve the company’s products and processes. The BSH Startup Kitchen tests promising new technologies and, following a successful pilot phase, offers the chance of a long-term business relationship.
One area where BSH intended to improve its existing processes was quality assurance (QA). As the systems in place still allowed some defected items to slip through, BSH was looking for a QA method that withheld the company’s strict quality standards without being too complex and cumbersome to deploy. As the need arose for an accurate, reliable, but user-friendly system, the BSH Startup Kitchen decided to approach Inspekto.
Automating QA allows manufacturers to save time and money. The cost of poor product quality is notorious — damage to a hard-earned reputation, erosion of customer trust, expensive recalls, material waste and reworking costs are just some consequences of releasing defective products. For this reason, QA is a crucial step in every manufacturing process, regardless of industry size or sector. However, manual QA is not fit for the strict standards of Industry 4.0, since human inspectors may miss defects, especially when inspecting highly complex electrical items. On the other hand, traditional machine vision solutions are extremely expensive and complex to set up and maintain, making them unpractical for many manufacturers. BSH wanted to implement a reliable automated QA system, but was struggling to find a satisfying solution.
"Even with multiple inspection check-ups, mistakes still emerged, thus increasing scrap-related costs,” explained Dipjyoti Deb, venture partner at BSH Startup Kitchen. “BSH had experimented with automated inspection solutions in the past, but each proved unsatisfactory and costly."
BSH’s challenge was to increase the accuracy and efficiency of batch inspection processes, in a way that was simple and did not require the design and installation of a complex, customized project.
BSH project engineers Markus Maier and Stefan Schauberger were responsible for reducing the detection time of component defects at one of BSH’s oven manufacturing plants in Traunreut, Germany. They approached BSH Startup Kitchen with this problem, and a partnership with Inspekto was formed.
Inspekto is the inventor of AMV, a new approach to industrial QA that mimics the entire human vision process while retaining the reliability and repeatability of industrial machine vision.
Just as the human brain adapts our single optical system — our eyes — to each scenario, AMV adapts a single electro-optical system to fit a wide range of use-cases. As a result, MV systems are not tailor-made, case-specific solutions, but off-the-shelf products that come pre-trained for a wide variety of use cases, so that users can easily install and deploy them independently and in a very short time.
The user does not need to specify the parameters for image capturing, like the distance between the camera and the sample item, lighting, focus value, shutter speed and exposure time — all of this will be automatically calculated and dynamically adjusted by the AMV system using its artificial intelligence (AI) engines. Users only need to present the system with 20 to 30 good sample items, so that it can learn the characteristics of the items to be inspected and flag any deviation from the memorised standards.
BSH implemented in its Traunreut plant the INSPEKTO S70, the only AMV system currently on the market.
“The result was so impressive that, while the solution was initially planned for only three use cases, it is now successfully tested and validated for six additional applications in different production lines,” confirmed Dipjyoti.
The INSPEKTO S70 can be deployed at any point along the production line, not just at the end, helping the company spot defects early on. This means that precious resources are not wasted completing a product that is already damaged. It also means that the plant can pinpoint areas where defects happen more frequently and take action to improve the production process.
With the systems in place at the beginning of the assembly line, the Traunreut plant managed to cut material waste by up to 90%.