ds automation gmbh
Acoustic sensor network with real-time data evaluation (ASEDA)
This project is co-financed by the European Union in the framework of the European Regional Development Fund. Operational Programme Mecklenburg-Vorpommern 2014 - 2020 – Investment in Growth and Employment.
In condition based maintenance the continuous monitoring of assets in operation, such as marine engines, is indispensable. Impending failure may be discernible by changes in the noise signature long before the critical condition is reached. Today, with acoustic sensor measurement it is already possible to test individual components. The system to be developed of individual sensors shall within this project be expanded to a sensor network, allowing a continuous monitoring throughout the entire lifecycle. Efficient use in the sense of a "condition monitoring system" requires Industry 4.0 approaches: Digitalisation, networking and "machine learning". Acoustic monitoring throughout the entire life cycle thus forms the basis for developing solutions for the megatrend of predictive maintenance.
The aim of the project is to develop a new type of sensor platform which is network-compatible and features adapted analysis and sound localisation procedures. The distributed measurement of sound events opens up unique possibilities for the comprehensive monitoring of large units with just a few sensors, especially through the linking of sensors and sound localisation. In addition to the development of the sensor network and the localisation of the sound events, methods for the optimal placement of the individual sensor systems are being investigated.
The ASEDA project “Acoustic sensor network with real-time data evaluation (ASEDA)” is a collaborative project of ds automation gmbh and the Fraunhofer Institute for Large Structures in Production Engineering (IGP).
Development of a sensor system for monitoring production processes in real time (ISEP)
in Echtzeit (ISEP)
This project is co-financed by the German Federal Ministry for Economic Affairs and Energy.
The partners involved are planning the development of an acoustic sensor for process monitoring that can be flexibly and autonomously integrated into existing production processes. As an exemplary application scenario for the acoustic sensor, it is intended to be used for precise monitoring of filling systems, conveying devices and dosing systems. Using “Machine Learning” (ML) methods, the features are extracted from the audio signals that are essential for recognizing a fault in the process or damage to the system. Process failures affect the quality of the products and machine damages can lead to longer and more expensive downtimes if they are not recognized in time. Error detection is essential to ensure consistent quality and to avoid production downtimes. The characteristics obtained are evaluated by an artificial neural network (ANN). Feature extraction and the neural network are optimized so that they can run embedded on a microcontroller. The manual effort for creating the sensor configuration (testing, training and configuring) shall be replaced by the ANN and is thus automated.
The aim of the project is to develop a new type of sensor platform with an integrated artificial neural network.
The ISEP project “Development of a sensor system for monitoring production processes in real time (ISEP)” is a collaborative project of ds automation gmbh and the Fraunhofer Institute for Microelectronic Circuits and Systems (IMS).