HyProForm

Hybride Prozessregelung für die Formstoffaufbereitung

The aim of the research project "HyProForm" is to develop and introduce a novel control system for molding material preparation in foundries. By implementing the "HyProForm" control method, foundries can significantly increase the stability and robustness as well as the flexibility of their production.

Systems in use today cannot meet the ever increasing requirements for mold quality in the production of complex, thin-walled castings and cause about 40% of all casting defects. In this respect, the "HyProForm" results offer considerable potential for increasing energy, raw material and cost efficiency. The approach is comprised of the following three main aspects:

  1. the division of the system into self-learning subsystems, linked by a higher-level process supervisor,
  2. the development of individual, precisely targeted hybrid control algorithms for the subsystems by combining domain knowledge with machine learning methods,
  3. the introduction of new types of measurement technology in molding material preparation, which enables the recording of parameters that could not be measured previously and makes them available to the control system.

 

Project duration: 04/01/2021 - 09/30/2023
Project lead (UDE): Dr. rer. nat. habil. Robert Martin
Project staff: Leonard Voss, M.Sc.
Consortium: Hochschule Kempten
Josef Brechmann GmbH & Co. KG
Michenfelder Elektrotechnik GmbH & Co. KG
Universität Duisburg-Essen

 

logo_BMWilogo_ZIM ​​

University of Duisburg-Essen Institute for Technologies of Metals

Address
Institut für Technologien der Metalle
Friedrich-Ebert-Str. 12
47119 Duisburg / Laar

Postal address
Universität Duisburg-Essen
Campus Duisburg
Institut für Technologien der Metalle
Forsthausweg 2
47057 Duisburg