Details
| Original language | English |
|---|---|
| Pages (from-to) | 542-561 |
| Number of pages | 20 |
| Journal | Chemie-Ingenieur-Technik |
| Volume | 89 |
| Issue number | 5 |
| Publication status | Published - 6 Apr 2017 |
Abstract
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.
Keywords
- Case studies, Chemometric models, Hybrid models, Modeling methodology, Validation
ASJC Scopus subject areas
- Chemistry(all)
- General Chemistry
- Chemical Engineering(all)
- General Chemical Engineering
- Engineering(all)
- Industrial and Manufacturing Engineering
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Chemie-Ingenieur-Technik, Vol. 89, No. 5, 06.04.2017, p. 542-561.
Research output: Contribution to journal › Article › Research
}
TY - JOUR
T1 - Between the Poles of Data-Driven and Mechanistic Modeling for Process Operation
AU - Solle, Dörte
AU - Hitzmann, Bernd
AU - Herwig, Christoph
AU - Pereira Remelhe, Manuel
AU - Ulonska, Sophia
AU - Wuerth, Lynn
AU - Prata, Adrian
AU - Steckenreiter, Thomas
N1 - Funding information: C. Herwig, S. Ulonska: Financial support was provided by the Austrian Research Promotion Agency (FFG) under the scope of the COMET program within the research project “Industrial Methods for Process Analytical Chemistry – From Measurement Technologies to Information Systems (imPACts)” (contract # 843546). All authors want to thank the workgroup Prozessanalytik of the GDCh and DECHEMA for giving the impetus for preparing this manuscript.
PY - 2017/4/6
Y1 - 2017/4/6
N2 - 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.
AB - 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.
KW - Case studies
KW - Chemometric models
KW - Hybrid models
KW - Modeling methodology
KW - Validation
UR - http://www.scopus.com/inward/record.url?scp=85017479178&partnerID=8YFLogxK
U2 - 10.1002/cite.201600175
DO - 10.1002/cite.201600175
M3 - Article
AN - SCOPUS:85017479178
VL - 89
SP - 542
EP - 561
JO - Chemie-Ingenieur-Technik
JF - Chemie-Ingenieur-Technik
SN - 0009-286X
IS - 5
ER -