Competence Center AI Engineering
Competence Center AI Engineering

QuickCheck profiles

Are you considering applying for a QuickCheck, but don't yet know specifically what it involves? To give you an insight into what we offer, we publish QuickChecks that have already been carried out in profiles on this page. Here you can read about the approaches we take to your questions and the results QuickChecks can lead to.

 

Automated anomaly detection

Siempelkamp NIS Ingenieurgesellschaft mbH provides monitoring solutions for large steam and gas turbine generator sets in the energy industry. For these plants, a monitoring concept has already been developed. The goal of the QuickCheck is to investigate the extent to which an AI/ML solution can be developed to automatically distinguish normal machine plant behavior from abnormal behavior.

To profile
 

Condition-oriented analysis of pipelines

The condition of underground infrastructure systems can be analyzed in several ways. Direct inspections by using robots are state of the art  but those approaches are epxensive and time consuming. Meanwhile, network operators have more or less extensive damage statistics and inspection findings. To support operators, the company 3S Consult carries out age-dependent analyses of the pipeline condition. The QuickCheck examines the extent to which an AI can assist experts in this process.

To profile
 

Hardware-accelerated SoC platforms

PLC2 is an authorized training partner for FPGA technologies from Xilinx Inc. as well as for SoC/MPSoC architectures and offers customized solutions and hardware accelerators. The combination with extensive expertise in imagingADAS systems for automated driving and data logging, makes PLC2 an outstanding industry partner for developments in the automotive image processing area on real-time capable hardware structures.


To profile
 

Simulation models in AI systems engineering

Knowtion GmbH is a data science company with expertise in research, development and application of data processing algorithms, e.g. for sensor or machine data. For automated driving, complex virtual development and test environments are already used, e.g. to generate vehicle or traffic scenario data, but also sensor data virtually. The goal is to train or test AI-based algorithms for environment perception at an early stage in virtual driving tests with corresponding sensor models.  

To profile
 

Energy consumption optimization during One-Pedal-Driving

The ARADEX AG develops electrical powertrain solutions for commercial and utility vehicles, construction machinery and marine applications. Besides these innovative hardware solutions ARADEX offers software services, which shall be augmented with AI technology. Data shall be analyzed e.g., to improve the available range of the electric vehicle or to identify malicious driving behavior in regards to battery life.

To profile
 

Plant monitoring for grinding machines

Vollmer Werke Maschinenfabrik GmbH is a SME mechanical engineering company and one of the leading manufacturers of machines for processing rotary tools, circular saws and metal-cutting band saws. The company's portfolio includes around 60 types of grinding machines, which generate a varying amount of measurement data per grinding process, depending on the sensor equipment. Currently, this data is evaluated manually and, if necessary, by process experts.

To profile
 

Optimized production of UHCP building materials

Hypercon Solutions UG is developing a plant concept for the automated production of UHCP building materials (ultra-high-performance concrete). In the individual automated plants, sensors collect and process data during the production process. The collected data from all plants will be used in the future to develop solutions with AI methods (artificial neural networks, ANN) that optimize the UHPC recipes used and/or the production process in terms of quality and cost-effectiveness, among other things.

To profile
 

Easy reverse engineering with AI

The company EKS InTec GmbH works on the virtual commissioning of production plants. It develops digital twins as models to replicate component behavior in simulated production lines. For real components, the digital twin can rely on the behavior. If these are not available, the behavior model must be created manually by virtual commissioning engineers, based on signal data, component documentation and reverse engineering.

 

To profile
 

AI-assisted train control in tunnel

In December 2021, Verkehrsbetriebe Karlsruhe brought the rail tunnel in Karlsruhe into operation. Driving a train in the tunnel is much more complex for the drivers. On the one hand, visibility is restricted due to the tunnel, on the other hand, there are much more restrictive safety precautions in the tunnel. Therefore, the relevant legal ordinance for trains in Germany, the Betriebsordnung für Straßenbahnen (BOStrab), requires a train protection for tunnel operation comparable to the signaling of railroad lines.

 

To profile
 

© Berliner Wasserbetriebe / Jack Simanzik

Anomaly detection in wastewater pumping stations

Berliner Wasserbetriebe (BWB) supplies Berlin with drinking water and treats wastewater using state-of-the-art technology. Ecological, economic and socially sustainable water cycle management is particularly important. They support research projects to optimize resource use, energy efficiency and plant availability. Data-driven methods are investigated here.

To profile
 

Voice control mobile robots

NEXT. robotics is a development office focusing on lightweight robotics, advanced robotics and cobotics. In mobile robotics there is a need to catch up with walking robots, because of the complex control they are rather used in research projects. A voice control system could expand the possible applications in terms of safety and acceptance when interacting with humans.

To profile
 

© RA Consulting GmbH

ML for developing Diagnostic Tools

RA Consulting GmbH is an IT service provider and tool specialist in Bruchsal. Their portfolio consists of solutions for the automotive industry. The company is characterized by its know-how in measurements, calibrations and diagnostics. The QuickCheck investigates whether statistical analysis and machine learning can be used in the development of these systems. This requires an understanding of the recorded diagnostic data. Based on this , the data is examined for patterns.

To profile