Projects

Today, most crash tests to evaluate vehicle safety are conducted virtually. Documenting the changes to the simulated vehicle models is particularly time-consuming and costly. The SAFECAR-ML project aims to simplify this process. By combining novel methods of artificial intelligence (AI) with technical knowledge from vehicle development, the project partners from research and automotive industry want to standardize the information processing for the documentation of virtual crash tests. New is the combination of semantically processed free text with multimodal engineering data for machine learning.

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.

The service center "WestAI" is a consortium of scientific organizations in North Rhine-Westphalia led by the University of Bonn. The services offered to customers from science and industry include support in the processing of data, in the transfer of AI technologies, in preliminary research and in the development of prototypes and customer-specific AI solutions.

Computer Aided Manufacturing (CAM) systems enable computer-aided planning of manufacturing processes. CAM software is used to create the control code for Computerized Numerical Control (CNC) machine tools.The CAM2030 project aims to develop a new generation of CAM systems characterized by reduced planning effort, optimized process planning and long-term knowledge acquisition and retention. To this end, the project uses user-centric enrichment of CAM systems with novel digital optimization tools – such as evolutionary algorithms, cloud computing and artificial intelligence.

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.the further development of procedures.

The "Artificial Intelligence Learning Lab" is being set up at the Fraunhofer Institute Center Schloss Birlinghoven in Sankt Augustin. It supports small and medium-sized enterprises (SMEs) in particular in getting started in artificial intelligence (AI), learning about concrete applications, and qualifying employees.

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.

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.

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.

The Flex4Apps project addresses the challenges of monitoring and optimizing large, distributed, cyber-physical systems. The goal of the project is to provide a solution to manage the high data volumes and complexity of system monitoring whilst disturbing the target system as little as possible.