Automated condition monitoring

Condition monitoring of your processes and plants

Our motivation

Production processes are affected by a wide variety of anomalies and errors. Such errors can affect the quality of the products or lead to unplanned machine and production downtime. The remedy here is reliable process monitoring, which makes it possible to detect errors and problems in the process flow at an early stage and in an automated manner.  

 

Our idea

The self-learning Condition Monitoring System (CMS) is a simple and effective protection system that contributes to early fault detection in real time and thus significantly to the stability of the process. It integrates seamlessly into existing automation systems without any configuration effort. Various connectors are available for fast connection to the production environment (OPCUA, MQTT, Profinet connector with patented self-configuration procedure, etc.), which store the data required for condition monitoring in a time series database (TSDB).

 

A web application enables the automatic creation of the process models for condition monitoring as well as condition monitoring in real time. To create the process models, it is only necessary to configure the connection to the TSDB. Machine learning is used to automatically learn a suitable process model from the process data. For this purpose, learning methods are already available for various fields of application, which can be extended to meet customer-specific requirements (among other things, there are methods for creating automata, Petri nets, hidden Markov models, kNN classifiers and LSTMs). During condition monitoring, the respective process model is compared with the actual process run. In this way, anomalies and errors in the process flow can be detected.

 

In addition to the web application, there is also a robust and space-saving hardware version of the CMS. Convince yourself of this solution. [here]

 

Your benefit

The self-learning CMS offers reliable fault detection in real time, which can be easily integrated into existing production systems without configuration effort. The condition monitoring system is available as a web application or as a SmartBox. Various connectors and condition monitoring methods exist for use in diverse production environments. The self-learning CMS makes it possible to minimize errors and plant downtimes and to improve production quality.

See for yourself and contact us!

Oliver Niehörster

Contact Press / Media

Dr. Oliver Niehörster

Machine Learning

Fraunhofer Institute of Optronics, System Technologies and Image Exploitation IOSB
Campusallee 1
32657 Lemgo, Germany

Phone +49 5261 942 90-22

Stefan Windmann

Contact Press / Media

Dr.-Ing. Dipl.-Inf. Stefan Windmann

Senior Scientist

Fraunhofer IOSB-INA
Campusallee 1
32657 Lemgo

Phone +49 5261/94290-51