Even modern mobile networks and wired communication networks will be unable to process such immense amounts of data in the near future. At the same time, the requirements for data security and protection are increasing. Keeping raw data at the edge is a promising way to both reduce data volumes and increase data security.
In the KIS project, researchers at Fraunhofer EMFT are therefore working on equipping sensors and actuators with AI. The aim is to be able to carry out intelligent (pre-) processing and compression of data already at the edge. To this end, various methods are initially being investigated that allow ML models to be trained in such a way that they can be executed in an intelligent sensor node. Furthermore, the research team will conceptualize and develop an intelligent environmental measuring station. This will be installed on the roof of the Fraunhofer EMFT, for example, in order to monitor the environmental impact of traffic and industrial plants in the Munich urban area. In the project, the measuring station serves on the one hand as a supplier of measurement data, where data is suitably collected so that it can be used for training ML models, and on the other hand as a vehicle for investigating and testing ML models integrated in the sensor node.
A second transfer demonstrator for AI-controlled micro-dispensing will then be developed to evaluate the transferability of the lessons learned. In addition, further transfer demonstrators will be defined together with industry to demonstrate the developed methods.
The project is funded by the Bavarian Ministry of Economic Affairs, Regional Development and Energy.