Using MVTec’s Anomaly Detection Method, existing images are taken from a Smart Camera. Between 30 and 100 images are like-ly to be needed to train the system, depending on the complexity of the failure case, but no special hardware is needed, and the procedure is simulated offline using the mapp Vision software.

Outlook

The innovations described in this article offer control system processing times of between 60 to 200ms and will cover the majority of applications. However, there are some applications, notably in the food & beverage industry, that need even faster processing. B&R is developing a technology that is expected to provide a control loop processing time of under 10ms. Another area being investigated is training-free anomaly event detection using Large Language Model Symbolic Pattern Discovery. This technology is a simplification of not only being able to detect a problem, but of also being able to identify its root cause, even if the causes lie some-where else in a process. In truth, users can already do this if the implementation is rules-based. The question is: will such systems be able to predict failures before they happen and fix them during planned maintenance to avoid unscheduled downtime?

www.br-automation.com

Seiten: 1 2