Industrial predictive maintenance demonstrator leverages edge AI

Industrial predictive maintenance demonstrator leverages edge AI

Technology News |
By Jean-Pierre Joosting

A groundbreaking demonstrator for predictive maintenance of industrial equipment, developed by the Fraunhofer Institute for Photonic Microsystems IPMS uses advanced sensor technology combined with AI-based data processing to detect potential machine damage at an early stage and avoid costly downtime.

The development of the demonstrator was based on the results of the iCampus project ForTune. It combines sensor technology, data acquisition and AI-based data evaluation for condition monitoring and predictive maintenance, which opens up new possibilities for the preventive maintenance of plants and machines. Fraunhofer IPMS leveraged its expertise in edge computing and real-time data transmission in the development of the demonstrator.

Dr. Marcel Jongmanns, project leader at Fraunhofer IPMS, explains: “Our solution enables precise condition monitoring of machines through the use of sensors and intelligent data analysis. By integrating AI into the sensors, we can detect damage before it occurs, optimize maintenance intervals and minimize downtime.

The demonstrator displays a miniaturized conveyor belt and showcases the performance of a novel toolbox for industrial plant monitoring. The demonstrator uses multimodal sensors. The sensor function records accelerations in the spatial directions and the corresponding rotation rates. In addition, magnetic field sensors and acoustic or ultrasonic sensors are used to monitor the industrial equipment. The system provides two main functions — belt tension detection and jam detection. The AI models are based on extensive data analysis and enable accurate prediction of damage. To increase the accuracy of the models, real-time calibrations can be performed to adapt the system to new environments.

The Fraunhofer IPMS system combines in-house sensors with its own edge computing unit based on RISCV architecture for efficient data processing directly at the point of use. This enables complex AI operations and real-time analysis. Changing environmental influences can be directly modeled or taken into account in the analysis. This enables the integration of a large number of sensors and significantly increases the accuracy of predictions about the condition of the industrial equipment. Existing limitations in computing power for real-time modeling in embedded systems are overcome. The expertise of Fraunhofer IPMS in the field of sensor technology and AI evaluation enables the continuous further development of the technology. Existing partnerships with companies such as Vetter Kleinförderbänder GmbH demonstrate the industry’s interest in such systems.

Image: Predictive Maintenance Demonstrator for Industrial Equipment. Copyright Fraunhofer IPMS.

If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :    eeNews on Google News


Linked Articles