From Research to Application: Projects at Fraunhofer EMFT

Edge computing is considered a key for new IoT applications. In order to bring artificial intelligence into future edge products, Fraunhofer EMFT researchers are working together with Fraunhofer IIS and Fraunhofer IPMS as part of the EU ANDANTE project to develop innovative mixed-signal artificial neural network (ANN) accelerator with computation-in-memory (CIM) ability. These are intended to enable the construction of solid hardware and software platforms for AI application development.

Nature sets a high bar: Our brain is capable of processing and storing huge amounts of information without using more energy than a 20-watt light bulb. This is a good reason for researchers worldwide to take the human brain as a model for circuits in so-called neuromorphic chips. Within the EU project NeurONN, a Fraunhofer EMFT research team is working with six European partners on extremely energy-efficient elements and architectures for neuromorphic computing. Innovative 2D materials are also being used in the process.

An advanced abatement system and exhaust gas cleaning solutions capture and reduce PFAS, NF3, and SF6 emissions in semiconductor manufacturing.

Many plasma coating systems used in the semiconductor industry have to undergo thorough cleaning on a regular basis after each stage of production. Currently this is mainly carried out using perfluorinated compounds (PFCs) and nitrogen trifluoride (NF3) gases, which are up to 17,000 times as damaging to the environment and climate as the greenhouse gas CO2. Solvay, Texas Instruments, Muegge and Fraunhofer EMFT are working on the project ecoFluor to develop an environment-friendly alternative which only has the greenhouse potential of CO2: the gas mixture used by the cooperation partners – Solvaclean®, consisting of fluorine, nitrogen and argon – dispenses entirely with the highly environmentally harmful gases PFCs and NF3.

The technology is already state of the art in modern cars: radar sensors that alert the driver when the vehicle is approaching an obstacle. Collision protection of this kind is also crucial in the future of production - smart factories in which intelligent industrial robots are expected to act completely autonomously in an increasing number of work steps - in order to ensure safe cooperation between man and machine. In the RoboMove project, Fraunhofer EMFT is working with robotics manufacturer KUKA and InnoSenT GmbH to develop an intelligent 3D distance measurement and obstacle detection system for robot arms in motion.

The aim of predictive maintenance is to maintain operating resources proactively and with foresight. This should reduce downtime and maintenance costs to a minimum. Researchers at Fraunhofer EMFT are testing new concepts that use machine learning methods to efficiently process even extremely heterogeneous data and make accurate maintenance predictions for production facilities.

In the EU project SusFe, Fraunhofer EMFT is working with European partners to develop an efficient and resource-saving design and production platform for medical devices. The aim is to meet both the growing demand for medical devices as well as the aspect of sustainability.

Within the SOIL project, Fraunhofer EMFT develops FDSOI IP blocks to boost Europe's next-generation chipindustry.

In the GaSeKa (Gas Sensor System with Self-Calibration function) project, Fraunhofer EMFT and EC Sense are developing a miniaturized sensor system for the precise and cost-effective monitoring of air pollutants. By enabling a much denser network of monitoring points in urban areas, the technology will help improve air quality monitoring and support better public health.

How can supply chains for the chip industry become more independent and better protected? The coronavirus pandemic in particular has highlighted the problems for Germany and Europe. In the "Semiconductor-X" research project on the digitalization of supply chains in the semiconductor industry, Fraunhofer EMFT is working with over 20 partners to make supply chains more sustainable and resilient and to promote decentralized, sovereign data exchange.