Premium
Between the Poles of Data‐Driven and Mechanistic Modeling for Process Operation
Author(s) -
Solle Dörte,
Hitzmann Bernd,
Herwig Christoph,
Pereira Remelhe Manuel,
Ulonska Sophia,
Wuerth Lynn,
Prata Adrian,
Steckenreiter Thomas
Publication year - 2017
Publication title -
chemie ingenieur technik
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.365
H-Index - 36
eISSN - 1522-2640
pISSN - 0009-286X
DOI - 10.1002/cite.201600175
Subject(s) - process (computing) , process modeling , computer science , process state , process control , quality (philosophy) , work in process , product (mathematics) , process engineering , biochemical engineering , risk analysis (engineering) , systems engineering , engineering , mathematics , operations management , operating system , medicine , philosophy , geometry , epistemology
The best method for process control is the use of model‐based solutions, based on process analytical technology for online monitoring of critical process variables, product quality attributes, or a holistic process state estimation. Mechanistic models as well as data‐driven techniques are essential for real‐time process monitoring. Their main characteristics, advantages and disadvantages, and the link between both are discussed as well as the synergetic effects, benefits, and drawbacks resulting from their combination. Aspects and differences of the computational model life cycle management are highlighted.