FEATURE Smart factories & AI


Feature sponsored by


AI and automation: leading the way to sample testing


Kistler is researching new possibilities for fully automated optical quality assurance. By Oliver Schnerr Head of Sales for Integrated Solutions, Automation Solutions, Vision Systems and Fastening Technology at Kistler


H


igh standards, high quality, high risk: manufacturers in the automotive, metal work and medical technology


industries have to meet these ever- increasing demands. This means that the entire quality control process must be designed for precision and reproducibility. Kistler has collaborated with the Eastern Switzerland University of Applied Sciences (OST) in Rapperswil to demonsrate this. The team are looking at using AI to leverage data for improved quality predictions. Typically, manufacturing companies use statistical process control (SPC) methods to check the quality of their production.  scope of the random samples to be taken and tested, so users can monitor the production process according to pre-  these samples have always been removed, transported and tested manually. The process ties up extensive resources (time, personnel, costs) depending on the scope of production and throughput rate. This can be automated.


Individual inspection A holistic automated inspection concept delivers particular advantages for production operations involving high throughput volumes and parts subject to similar inspection requirements. By automating the entire quality assurance  enhanced reproducibility and lower costs. When starting to design an inspection concept of this sort, the focus is initially on the requirements for the part being tested. The team assigned to the project collaborates with the manufacturers to develop the required quality-relevant test parameters – mostly related to surface defects and dimensional accuracy – and select appropriate test methods. Experts from the Competence Center then design the test cell accordingly.


32 September 2024 | Automation


The integrated safety concepts monitor the progression of each step in the process, to guarantee process reliability whilst preventing data loss.


The research project Quality control is a particularly sensitive issue in injection molding production – especially in the med-tech sector.  from automated random sample inspection, so Kistler is cooperating on a research project with the IWK Institute for Materials Technology and Plastics Processing at the Eastern Switzerland University of Applied Sciences, to set up an example of a fully-automated manufacturing and testing process. An injection-molding machine


produces parts, serialises them with QR codes, and sorts them into trays. Whilst production is still in progress, the ComoNeo process monitoring system uses sensors to monitor the respective cavity pressures. With support from a trained AI model, the ComoNeoPREDICT software generates quality predictions for the individual parts. Driverless transport


vehicles convey the parts selected for spot checks to the optical test cell: this is  performed autonomously. Later, additional injection molding machines with other parts can be integrated into this set-up, to cater for even more complex production environments.


Data analysis for optimsation After inspection, the autonomous vehicle transports the tested parts to the warehouse and the test cell sends the analysed data to higher-level QA or MES systems.


If variances occur during the production


processes, the AI models are retrained with the new test data.


As well as exploring the options for designing a comprehensive system of this type, the research project is investigating possible ways to automate data matching and the adaptation of neural networks. Thanks to this approach, manufacturers  quality from optical inspections, but they can also design their entire process to be as rigorous and error-free as possible.


automationmagazine.co.uk


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44  |  Page 45  |  Page 46  |  Page 47  |  Page 48