PROCESS DIGITALIZATION
FOR POLYMER MANUFACTURING
In this research area, we focus on the digitalization of polymer manufacturing processes, with expertise in polymer characterization, polymer processing, and polymer engineering. Our work supports the optimization, monitoring, and control of industrial polymer processes, with a particular focus on thermoplastic composites, including unidirectional (UD) tapes.
Our objective is to enable a deeper understanding of process–structure–property relationships, allowing manufacturing processes to be operated more robustly and efficiently. Through data-driven and model-based approaches, processes can be improved technically, economically, and environmentally, fostering greater sustainability.
AREA MANAGEMENT
DI Dr. Christian Marschik
Area 1 Manager for Digitalization Polymer Processing,
R&D Infrastructure Site Linz
Christian Marschik is Area Manager for Process Digitalization at the Competence Center CHASE. He leads several research projects at the interface of science and industry, with a strong focus on sustainability and digitalization in the plastics industry.
His main research fields include polymer extrusion, mechanical plastics recycling, and thermoplastic composites. He develops and applies physics-based and data-driven models and hybrid simulation approaches to optimize industrial polymer processes.
He completed his studies in Polymer Engineering and Technologies at Johannes Kepler University Linz and received his PhD in Technical Engineering in 2018. He has an extensive publication record and is also a patent holder.
Research Gate: ↗
LinkedIn: ↗
Contact:
Phone: +43 664 8568520
Email: Send email
Dr. Karin Kloiber, BSc
Area 1 Manager for Digitalization Chemical Systems,
Key Researcher Digitalization
Karin Kloiber is Area Manager for Process Digitalization at the Competence Center CHASE. She heads the Advanced Data Analytics team, with a focus on data-driven methods, simulation expertise, and international scientific collaboration.
Her main research focuses on the use of advanced machine learning and Artificial Intelligence for process monitoring and control, physics-informed machine learning for complex chemical systems, and data-driven surrogate models for physical simulations.
She received her PhD in Chemistry and a BSc in Physics from the University of Innsbruck, has around 15 years of academic experience, and has been awarded several fellowships. She is the author of more than 25 peer-reviewed scientific publications.
Contact:
Phone: +43 664 8481317
Email: Send email
KEY SCIENTIFIC PARTNERS
CHASE collaborates with leading scientific institutions and partners to advance research in sustainable process digitalization and polymer manufacturing:
Univ.-Prof. DI Dr. mont. Gerald R. Berger-Weber, JKU Linz - Profile↗
Univ.-Prof. DI Dr. Zoltán Major, JKU Linz - Profile↗
Univ.-Prof. DI Dr. Jörg Fischer, JKU Linz - Profile ↗
INDUSTRY REFERENCES
CHASE works closely with and for industrial partners to implement innovative solutions and optimize polymer production processes:
Bilfinger SE, Covestro AG, Engel GmbH, EREMA Group GmbH, FACC AG, Festo SE & Co. KG, Greiner Perfoam GmbH, Leistritz AG, Renolit SE, Thermo Fisher Scientific (Austria) GmbH
OUR GOALS
The following objectives are pursued in our research area:
-
To develop standardized workflows for the creation of static, dynamic, and adaptive digital twins for process analysis, optimization, and control.
-
To implement application-specific modeling approaches (mechanistic, data-driven, hybrid) for digital twins across different scales, from single processing steps to entire production systems.
-
To enable practical use of digital twins for various processes, including (bio-)chemical and polymer manufacturing.
-
To perform dynamic evaluation and validation to demonstrate improved process and product quality stability using digital twins.
OUR APPROACH
The following approach is pursued in our research area:
-
To apply a bottom-up, application-oriented design that integrates industrial and SME requirements.
-
To combine first-principles mechanistic modeling with data-driven methods, including machine learning, to develop robust hybrid approaches.
-
To collect and analyze comprehensive process and system-wide data to support knowledge discovery and model generation.
-
To use novel machine learning techniques to enhance mechanistic model creation and facilitate efficient model transfer between similar processes.
-
To leverage and extend existing industrial IoT technologies provided by partners.
-
To implement technology-driven smart living labs for evaluation, demonstration, and validation.
YOUR RESULTS
The following results are pursued in our research area:
-
Enhanced process and product quality assurance through the implementation of digital twins.
-
Increased resource efficiency via predictive maintenance enabled by digital twins.
-
Improved overall process efficiency.
-
Prototypical implementation of digital twins for smart polymer production.
-
Experimental validation of developed models in pilot plant environments.
ONE OF OUR PROJECTS
Watch the video about our Aircraft Guide Vane Project here or visit our Youtube channel:
