Organic redox flow batteries (RFBs) are a promising approach to store temporary surpluses of renewable energy. The SONAR project aims to digitally capture the entire development process with all relevant aspects to accelerate screening for suitable substances and optimize a battery system's design for specific operating conditions. The project partners are developing tools and workflows to investigate electroactive materials up to entire battery systems. To do this, they are combining simulation methods at different physical scales – from the electronic/quantum mechanical level to visible, macroscopic behavior. Factors such as cost, lifetime, and performance are comprehensively considered to compare competing energy storage technologies.
Project duration: 01/2020 – 12/2023
In the VirtualBrainCloud project, Fraunhofer SCAI is working with 16 European partners on a cloud-based IT platform that enables the simulation of communication paths in the brain. The individual simulation of patient brains supports physicians in finding the right diagnosis and therapy for people with neurodegenerative diseases. This is usually difficult because the course and symptoms of diseases such as Alzheimer's are often very different. With this platform, it will be possible to record the state of health of the brain with little effort. Regular routine examinations will enable physicians to detect and treat Alzheimer's disease at an early stage.
Project duration: 12/2018 – 11/2022
In the RADAR-AD project, the project partners will develop methods with which the functional loss in the brain of Alzheimer patients can be measured at an early stage - not only in hospitals but also on an outpatient basis. So-called remote measurement tools (RMT) will enable remote assessments and thus improve patient care. The project is funded by the Innovative Medicine Initiative (IMI), a public-private partnership between the European Union and the European Federation of Pharmaceutical Industries and Associations (EFPIA).
Project duration: 01/2019 – 06/2022
New analysis methods improve evaluation of complex engineering data
A further increase in the performance of supercomputers is expected over the next few years. So-called exascale computers will then be able to deliver more accurate simulation results. Fraunhofer SCAI is developing efficient data analysis methods for the much larger amounts of data generated in this way, which will also provide the engineer with detailed insights into the complex technical interrelationships.
Project duration: 12/2018 – 11/2021
It was only recently discovered that the innate immunoreceptor genes TREM2 and CD33 / SGLEC3 play a role in Alzheimer's disease. However, the significance of the identified genes and of the cellular mechanism has not been sufficiently investigated. The PHAGO project is designed to close these knowledge gaps and develop new tools and test methods that work on these immune receptors and open the way to the development of drugs that inhibit the course of the disease. This will allow new therapies for Alzheimer's patients. The project is funded by the Innovative Medicine Initiative (IMI), a public-private partnership between the European Union and the Federation of Pharmaceutical Industries in Europe (EFPIA).
Project duration: 11/2016 – 10/2021
The project MathEnergy develops mathematical aproaches to tackle the challenges which arise in the context of the energy turnaround. In order to adapt the workload and the expansion of the energy networks, offers and demands have to be adjusted and flexibilities among the energy sources have to be utilized. For this purpose, network-transcending models and model-based monitoring, controlling and evaluation concepts are developed. The goal is to develop a software package for hierarchical complex network models which supports stochastically varying input data and workflows for the integrated simulation and analysis of network-transcendent scenarios of the energy supply with power and gas.
Project duration: 10/2016 - 04/2021
MaGriDo's goal is to (further) develop and analyze deep neural networks (NNs) for industrial problems, which allow existing domain knowledge to be incorporated into the architecture of the networks. Such a hybrid approach can make use of the complementary strengths of "end-to-end" learning approaches and "a-priori models/rules". This approach promises more efficient solutions for many fields of application. For example, the amount of data required is reduced, or the predictions of the ML model are consistent with existing knowledge.
Project duration: 04/2020 – 03/2023
The goal of the project ViPrIA is the development of intelligent assistance systems based on artificial intelligence and machine learning approaches to support engineers in simulation-based, virtual product development. With the help of intelligent assistance functions, calculation engineers are to be supported in the development process with complex decisions and relieved of routine tasks.
Project duration: 10/2019 – 09/2022
The project "COMMITMENT – COMorbidity Modeling via Integrative Transfer machine-learning in MENTal illness" will establish an interdisciplinary research framework for the identification of systems-molecular hallmarks of psychotic and comorbid somatic diseases. The identification of shared and distinct biological profiles and their underlying pathophysiological processes will allow disentangling patient heterogeneity and provide the basis for objective tools for a personalized clinical management of psychotic disorders.
Project duration: 09/2019 – 08/2022
The inhalative route is an important path for nanomaterials and other innovative materials in the nano- and microscale range. The lung is therefore an important target organ for acute toxic effects. At the same time, the barrier function of the lung determines the systemic uptake of the materials and the resulting effects on other organs. The aim of this project is to develop an innovative testing system for airborne nanomaterials based on the partners' existing know-how in the field of in vitro testing procedures. The project is funded within the scope of the topic Nano Safety Research: "NanoCare4.0 - Application-safe Material Innovations".
Project duration: 06/2019 - 05/2022
Using machine learning for the early detection of anomalies helps to avoid damages
The analysis of sensor data of machines, plants or buildings makes it possible to detect anomalous states early and thus to avoid further damage. For this purpose, the monitoring data is searched for anomalies. By means of machine learning, anomaly detection can already be partially automated.
Project duration: 10/2018 - 09/2021
The project "OpenMP for Reconfigurable Heterogeneous Architectures" (ORKA-HPC) aims to support the use of field programmable gate arrays (FPGAs) in heterogeneous HPC architectures. The parallel programming interface for the productive use of the FPGAs will be OpenMP. FPGAs are reconfigurable and allow very efficient implementation of algorithms; but their programming is currently very time-consuming. The developments in ORKA-HPC will significantly reduce the porting effort on FPGAs.
Project duration: 11/2017 - 07/2021
The VMAP project aims to gain a common understanding of interoperable definitions for virtual material models in CAE. Using industrial use cases from major material domains and with representative manufacturing processes, new concepts will be created for a universal material exchange interface for virtual engineering workflows.
Project duration: 09/2017 - 10/2020
In the RoKoRa project, the aim is to exclude hazards of humans by robots. For this purpose, compact radar systems are used. They offer many advantages: radars operate independently of any lighting and are largely insensitive to environmental conditions. In addition, radar sensors can measure not only the distance to the sensor, but also the motion vector of the detected targets. The sensor system to be developed significantly improves personnel safety in human-robot collaboration, resulting in new degrees of freedom for a safe cooperation with larger robots and at higher distance-dependent execution speeds. In the project, SCAI develops a software component for environmental perception for situational analysis and decision-making using methods of machine learning.
Project duration: 07/2017 - 12/2020
The big vision of Industry 4.0 is the automatic adaptation of production processes to rapidly changing requirements. The new Fraunhofer Leitprojekt EVOLOPRO wants to come a step closer to this vision. The project is part of the Fraunhofer initiative "Biological Transformation". Starting in 2019, seven institutes will jointly investigate how developmental and evolutionary biological principles can be transferred to man-made production processes. Transfer and multi-task learning play an important role here - as well as the concept of so-called "digital twins". Biology is the great role model for the work in EVOLPRO and provides important impulses for the further development of procedures.
Project duration: 01/2019 - 12/2023
In the »ManuBrain« project, a universal, scalable, and open platform for artificial intelligence applications in medium-sized industrial companies is being developed. The state of North Rhine-Westphalia and the European Fund for Regional Development are supporting the project over three years with a total of 1.8 million euros. Fraunhofer SCAI develops and evaluates machine learning methods for engineering applications.
Project duration: 01/2020 - 12/2022
Material models and determination of characteristic values for the industrial application of forming and crash simulation taking into account the thermal treatments during coating in the process for high-strength materials. The project is funded by the Arbeitsgemeinschaft industrieller Forschungsvereinigungen (AiF) - Forschungsvereinigung Automobiltechnik e.V. (FAT).
Project duration: 01/2018 - 06/2021