Between the Poles of Data-Driven and Mechanistic Modeling for Process Operation

被引：79

作者：

Solle, Doerte ^{[1
]}

Hitzmann, Bernd ^{[2
]}

Herwig, Christoph ^{[3
]}

Remelhe, Manuel Pereira ^{[4
]}

Ulonska, Sophia ^{[5
]}

Wuerth, Lynn ^{[4
]}

Prata, Adrian ^{[4
]}

Steckenreiter, Thomas ^{[4
]}

机构：

[1] Leibniz Univ Hannover, Inst Tech Chem, Callinstr 5, D-30167 Hannover, Germany

[2] Univ Hohenheim, Inst Food Sci & Biotechnol, Dept Proc Analyt & Cereal Sci, Garbenstr 23, D-70599 Stuttgart, Germany

[3] TU Wien, Inst Chem Environm & Biol Engn, Christian Doppler Lab Mech & Physiol Methods Impr, Gumpendorfer Str 1a, A-1060 Vienna, Austria

[4] Bayer AG, Kaiser Wilhelm Allee, D-51373 Leverkusen, Germany

[5] TU Wien, Inst Chem Environm & Biol Engn, Res Div Biochem Engn, Gumpendorfer Str 1a, A-1060 Vienna, Austria

来源：

CHEMIE INGENIEUR TECHNIK | 2017年 / 89卷 / 05期

关键词：

Case studies; Chemometric models; Hybrid models; Modeling methodology; Validation; FED-BATCH CULTURES; OVERFLOW METABOLISM; PREDICTIVE CONTROL; EXPERT-SYSTEM; CELL-CULTURE; KNOWLEDGE; GROWTH; CALIBRATION; BIOPROCESS; CHEMOMETRICS;

D O I：

10.1002/cite.201600175

中图分类号：

TQ [化学工业];

学科分类号：

0817 ;

摘要：

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.

引用

页码：542 / 561

页数：20

共 50 条

[1] Roles of mechanistic, data-driven, and hybrid modeling approaches for pharmaceutical process design and operation
Gaddem, Mohamed Rami
Kim, Junu
Matsunami, Kensaku
Hayashi, Yusuke
Badr, Sara
Sugiyama, Hirokazu
[J]. CURRENT OPINION IN CHEMICAL ENGINEERING, 2024, 44
[2] Mechanistic and data-driven modeling of protein glycosylation
Shek, Coral Fung
Kotidis, Pavlos
Betenbaugh, Michael
[J]. CURRENT OPINION IN CHEMICAL ENGINEERING, 2021, 32
[3] Hybrid Data-Driven and Mechanistic Modeling Approaches for Multiscale Material and Process Design
Zhou, Teng
Gani, Rafiqul
Sundmacher, Kai
[J]. ENGINEERING, 2021, 7 (09) : 1231 - 1238
[4] Data-driven modeling method with reverse process
Yi, Guodong
Yi, Lifan
Zhang, Zaizhao
Li, Chuihui
[J]. INTERNATIONAL JOURNAL OF MODELING SIMULATION AND SCIENTIFIC COMPUTING, 2022, 13 (02)
[5] A Data-Driven Multiobjective Dynamic Robust Modeling and Operation Optimization for Continuous Annealing Production Process
Wang, Yao
Wang, Xianpeng
Dong, Zhiming
Wang, Zan
[J]. ISIJ INTERNATIONAL, 2020, 60 (06) : 1225 - 1236
[6] Stochastic reservoir operation with data-driven modeling and inflow forecasting
Fontes Santana, Raul
Celeste, Alcigeimes B.
[J]. JOURNAL OF APPLIED WATER ENGINEERING AND RESEARCH, 2022, 10 (03): : 212 - 223
[7] Data-driven Modeling and coordination of large process structures
Mueller, Dominic
Reichert, Manfred
Herbst, Joachim
[J]. ON THE MOVE TO MEANINGFUL INTERNET SYSTEMS 2007: COOPLS, DOA, ODBASE, GADA, AND IS, PT 1, PROCEEDINGS, 2007, 4803 : 131 - +
[8] Data-Driven Modeling of the Airport Configuration Selection Process
Ramanujam, Varun
Balakrishnan, Hamsa
[J]. IEEE TRANSACTIONS ON HUMAN-MACHINE SYSTEMS, 2015, 45 (04) : 490 - 499
[9] Integrated Process and Decision Modeling for Data-Driven Processes
van der Aa, Han
Leopold, Henrik
Batoulis, Kimon
Weske, Mathias
Reijers, Hajo A.
[J]. BUSINESS PROCESS MANAGEMENT WORKSHOPS, (BPM 2015), 2016, 256 : 405 - 417
[10] Data-driven surrogate modeling and benchmarking for process equipment
Goncalves, Gabriel F. N.
Batchvarov, Assen
Liu, Yuyi
Liu, Yuxin
Mason, Lachlan R.
Pan, Indranil
Matar, Omar K.
[J]. DATA-CENTRIC ENGINEERING, 2020, 1 (05):

← 1 2 3 4 5 →