AREA 1 - PROCESS DIGITALIZATION
Area-Management
Area Manager Dr. Karin Kloiber, BSc
Digitalization Chemical Systems
Key Researcher Digitalization
​
Phone: +43 664 8481317
Area Manager DI Dr. Christian Marschik
Digitalization Polymer Processing
R&D Infrastructure Site Linz
​
Phone: +43 664 8568520
SCIENTIFIC LEAD
​
Univ.-Prof. Dr. Zoltan Major, JKU Linz
Univ.-Prof. DI Dr. Georg Steinbichler, JKU Linz
​
PARTNERS
​
Bilfinger, Covestro, Engel, EREMA, FACC, Festo, Greiner Perfoam, Leistritz, Renolit, Thermo Fisher
(c) JKU
TOPICS
​
Digitalization is the opportunity front of Europe, a once-in-a-generation chance to boost its position in the hyper-connected global marketplace. Data, software, robots, connected things and machines will power the new European digital economy in production systems. These are the main topics in chemical and physical processing systems where the projects of Area 1 are focusing on.
​
GOALS
​
-
Establish (generic) workflows for the development of static, dynamic and adaptive digital twins for process analysis, optimization and control.
-
Application specific modelling approaches (mechanistic, data-driven, hybrid) required for established digital twins at different scales from a single processing step to the whole production system.
-
Cloud service based approaches for digital twin development as well as deployment.
-
Useable digital twins for different processes: (bio-)chemical and polymer processing.
-
Dynamic evaluation and validation as well as demonstration of increased process and product quality stability by means of digital twins.
​
APPROACH
​
-
Application oriented bottom up design by consideration of industry and SME-requirements.
-
First principles modelling (mechanistic models) combined with data-driven approaches (like machine learning) yielding powerful hybrid approaches.
-
Comprehensive data collection and analytics integrating process / system wide data sources for knowledge discovery and model generation.
-
Novel machine learning approaches supporting mechanistic model generation as well as efficient model transfer between similar processes.
-
Leveraging and extending existing industrial IoT technologies provided by industrial partners.
-
Technology based smart living labs for evaluation and demonstration.
​
EXPECTED RESULTS
​
-
Improved quality assurance of processes and products enabled by digital twins.
-
Improved resource efficiency of processes by means of predictive maintenance enabled by digital twins.
-
Improved process efficiency.
-
Prototypical implementation of digital twins for smart polymer production.
-
Prototypical implementation of digital twins for (bio-)chemical process monitoring and control.
-
Experimental evaluation and validation of developed models within pilot plants.
​