Fraunhofer IPMS
Smart demonstrator for system maintenance
Fraunhofer IPMS has developed a demonstrator that combines sensor technology, data acquisition and AI-based data evaluation for condition monitoring and predictive maintenance.
The demonstrator uses sensor technology combined with AI-based data processing to detect potential machine damage at an early stage and avoid downtime. This opens up new possibilities for the preventive maintenance of systems and machines.
Dr. Marcel Jongmanns, head of the project at Fraunhofer IPMS, explains: "Our solution enables precise condition monitoring of machines through the use of sensors and intelligent data analysis. The integration of AI into the sensors allows us to detect damage before it occurs, optimizing maintenance intervals and minimizing downtime."
Multimodal sensors for system monitoring
The ShowCase displays a miniaturized conveyor belt and demonstrates the performance of a new type of toolbox for monitoring industrial plants. Multimodal sensors are used in the demonstrator. 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 system.
The system offers two main functions: The detection of belt tension and the detection of blockages. The AI models are based on extensive data analyses and enable the precise 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 solution aims to combine the sensors with a dedicated edge computing unit based on the RISCV architecture for data processing directly on site. This enables complex AI operations and real-time analyses. Changing environmental influences can be modeled directly 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 plant. Existing limitations in computing power for real-time modeling in embedded systems are overcome.
You might also be interested in
Flexible production architecture available from the end of 2024
The 'SWAP-IT' production architecture developed by a consortium of Fraunhofer Institutes is ready for use - for capacity-optimized, flexibly arranged production modules that are loaded by driverless transport systems and can manufacture many...
read more...How legally compliant is AI in maintenance?
Lufthansa Industry Solutions has had its AI Maintenance Assistant assessed by TÜV SÜD and Calvin Risk. The aim was to ensure compliance with the EU AI Act in order to maintain a high level of legal certainty.
read more...100% quality control of ultra-thin barrier layers
Until now, it has not been possible to test the quality of plasma coatings inline and non-destructively. Instead, the state of the art is random quality testing using time-consuming laboratory procedures. A new type of sensor changes this.
read more...High-performance biolubricants and additives
The Fraunhofer Institute for Process Engineering and Packaging IVV is developing plant-based alternatives to mineral oil-based lubricants and lubricant additives and will be showcasing them at this year's Achema from June 10 to 14, 2024.
read more...Business field 'Microdisplays & Sensors' integrated
The 'Microdisplays & Sensors' business unit of the Fraunhofer Institute for Organic Electronics, Electron Beam and Plasma Technology FEP will be integrated into the Fraunhofer Institute for Photonic Microsystems IPMS with retroactive effect from...
read more...Strengthening the security of 5G/6G networks
In the "RealSec5G" project, the data security requirements in communication devices for 5G/6G infrastructures are to be tested in a deterministic time-sensitive network (TSN). The Fraunhofer Institute IPMS is designing a TSN-MACsec function block...
read more...European pilot infrastructure for quantum technologies
European industry is facing the challenge of translating innovations in the field of quantum technology into scalable processes and products. The 'Qu-Pilot' project aims to help here by using the existing pilot manufacturing infrastructure.
read more...Sensors learn to think
In the Fraunhofer lighthouse project NeurOSmart, the Fraunhofer Institute for Photonic Microsystems IPMS and four other institutes (ISIT, IMS, IWU, IAIS) are researching particularly energy-efficient and intelligent sensors for the next generation...
read more...Wireless TSN by light
Deterministic and real-time capable data transmission via TSN. In addition to traditional Ethernet cabling, WLAN, 4G/LTE and 5G are being discussed for data transmission. But there is another way: using light, as Fraunhofer IPMS will be...
read more...