SYSiDAT Lab - Lab for AI system simulations, machine learning, and industrial data analysis

Room 9.1.02 - Campus II
Logo SYSiDAT Lab

In research and teaching, the lab concentrates on optimizing business processes by developing and using new technologies and methods of data analysis against the background of Industry 4.0 and Big Data.

Particular attention is paid to the application of up-to-date methods from the fields of artificial intelligence and machine learning.

Main topics

The lab is divided thematically and organizationally into two sub-areas:

Simulation and optimization of material flows:

Complex material and information flows can be mapped into a simulation model and simulated with the help of specialized software solutions (SIEMENS Technomatix®, PlantSim®). The result is a data-supported simulation environment that can be used to design, plan, simulate and virtually optimize work systems and processes in logistics and production right up to complete semi-automated or fully automated factories.

Please visit the website of Plant Simulation from Siemens to learn more about the software we use.

Screenshot of the software Logistics and Material Flow Simulation from Siemens
Screenshot of the software Plant Simulation from Siemens

Data-driven process optimization

The goal is to create sustainable and efficient business processes. In the context of a digitally networked Industry 4.0 enviroment, data obtained from processes is indispensable. The topic “data-driven process optimization” aims in particular at the analysis and optimization of highly complex business processes in Industry 4.0 logistics and production. The use of the latest intelligent processes and quantitative methods from the field of artificial intelligence is intended to increase the potential for value creation in operational business processes. Under the heading “industrial analytics”, the focus is on the following application areas:

  • Effective and efficient data acquisition from data bases and operational logistics or manufacturing processes (data mining)
  • Information acquisition and processing of sensor data from the real-time operation of plants and partially or fully automated processes (Big Data Analytics)
  • Evaluation and interpretation of the data obtained using quantitative methods from the fields of statistics, artificial intelligence (AI) and machine learning (ML)
  • Process optimization on the basis of SIX SIGMA and DFSS (Design for SIX SIGMA)