Transfer Center »Process Engineering / Chemistry«

There are often substantial differences between model-based planning data of process plants and the process data actually recorded during plant operation, and clarifying these differences is highly relevant for the further development of the processes.

The seemingly obvious use of standard machine learning methods is not effective here, since the complex sensors and analytics in production plants usually only incompletely capture the input-output behavior and can only be learned to a limited extent based on this.

Therefore, the essential goal is to close such systematic gaps by means of models through the strongly interdisciplinary cooperation in the transfer center »Process Engineering / Chemistry« and thus to advance decision support and process development in the chemical industry.

Focus Areas at a Glance

  • Decision support in chemical and pharmaceutical industry 
    • Model-based design of experiments 
    • Optimal control
    • AI for interactive decision support
  • Optimized design of apparatus and processes in separation technology (distillation, filtration, separation, processing) and in reaction technology (catalysis, electrochemistry)
    • Multiscale design of separation equipment 
    • Microstructure design of catalytic processes
    • Digital filter models for online monitoring 
    • Steady-state and dynamic simulation in the equilibrium stage model, e.g. for batch distillations
  • Process development for fibers and nonwovens 
    • Simulation of spinning processes
    • Design and functional property evaluation of filter media and filter elements for air, solids and particle filtration

Projects for the development of hybrid/greybox processes in the chemical industry

  • »KEEN: AI incubator labs in the process industry« 
  • »Ammonpaktor: Utilization of ammonia as carbon dioxide-free hydrogen storage for decentralized hydrogen supply - development of an innovative compact reactor concept«
  • »Batch2Konti: Using smart models from batch to continuous processes in biotechnology«
  • »SmartModels: using learning methods to optimize products and production processes« 
  • »Kernel methods for confidence regions in optimal experimental design and parameter estimation« 


We work together with BASF, Bayer, Evonik, IBS Filtran, Lonza, Merck and Umicore, among others.