FOOD AND BEVERAGE n Taking a closer look at ceramic bottle tops TThe production of bottles and bottle caps in the beverage industry is highly automated. It is important that inspection processes keep pace with production line speeds, and also with quality requirements. A German automation company, K&S Anlagenbau, has developed an technology for inspecting porcelain bottle caps, in collaboration with a consulting firm, Computer Vision Solutions Consulting & Research. The system is used primarily to check the printing on the bottle caps, but can also check for defects such as cracks. The challenge was to detects faults quickly and reliably in an automated, lowmaintenance process. The system can be switched quickly to other product types and deliver equally reliable results. “Automation only brings decisive added value if the customer has little effort in maintaining the system,” says Dr Markus Heber, MD of the Computer Vision Solutions. “In the newly developed system, quality control is carried out inline. To do this, the camera takes a picture of the bottle cap to be checked. The image of the imprint on the top of the cap is then checked using the MVTec Halcon machine vision software.” One difficulty the developers faced was variability in the printed image on the bottle tops, with errors such as incorrect or out-offocus colours, or partially visible prints. They also had to check that the image had been printed centrally on the cap. “The number of different-looking print images is theoretically infinite,” Heber points out. “This applies both to good (OK) and faulty (not OK) prints. Our task was to ensure that the software was trained to make the right decision at all times and for any prints.” An image of an OK print – known as the “golden sample”– is saved in the software. This serves as a template against which each image is compared during the inspection process. Users can set the degree to which deviations from the golden sample are considered OK. The Halcon machine vision library is integrated into K&S’ software using HDevEngine. This acts as an interpreter that loads and executes the machine vision algorithms dynamically, and enables changes to the vision processes on-the-fly. “The scope of the machine vision software goes beyond inspecting the print,” Heber says. “To ensure that the process is as automated as possible, we have embedded the software in the entire system in such a way that it can communicate with other components. If a bottle cap is not printed correctly, Halcon informs the system and the component is ejected automatically.” Customers are already using the bottlecap inspection technology. "The feedback we have received has been very positive,” Heber reports. The system has been able to test 120 bottle caps per minute. The partners are now working on new inspection technologies, including 3D. n Two German companies have developed a system for inspecting ceramic bottle tops. The system can check 120 caps per minute, and can be adapted rapidly to new inspection tasks. As well as inspecting printed images on ceramic bottle tops, the system can check for any cracks Motors in Washdown Design for food processing, cutting and packaging Learn more
RkJQdWJsaXNoZXIy MjQ0NzM=