New Journal at De Gruyter!
Ed. by de Lasa, Hugo / Xu, Charles
1 Issue per year
Increased IMPACT FACTOR 2011: 0.790
Volume 11 (2013)
Volume 10 (2012)
Volume 9 (2011)
Volume 8 (2010)
Volume 7 (2009)
Volume 6 (2008)
Volume 5 (2007)
Volume 4 (2006)
Volume 3 (2005)
Volume 2 (2004)
Volume 1 (2002)
Most Downloaded Articles
- Micro- and Macromechanics of Hopper Discharge of Ultrafine Cohesive Powder by Tomas, Jürgen and Kache, Guido
- Effect of Chitosan Addition on NiMo/Al2O3 Catalysts for Dibenzothiophene Hydrodesulfurization by Ríos-Caloch, Guillermina/ Santes, Víctor/ Escobar, José/ Valle-Orta, Maiby/ Barrera, María C. and Hernández-Barrera, Melissa
- Fischer Tropsch Synthesis: The Promoter Effects, Operating Conditions, and Reactor Synthesis by Sarkari, Majid/ Fazlollahi, Farhad and Atashi, Hossein
- A Trickle Fixed-Bed Recycle Reactor Model for the Fischer-Tropsch Synthesis by Brunner, Kyle M./ Duncan, Joshua C./ Harrison, Luke D./ Pratt, Kyle E./ Peguin, Robson P. S./ Bartholomew, Calvin H. and Hecker, William C.
- A Comprehensive Review of Just Suspended Speed in Liquid-Solid and Gas-Liquid-Solid Stirred Tank Reactors by Jafari, Rouzbeh/ Chaouki, Jamal and Tanguy, Philippe A.
Combined Mechanistic and Empirical Modelling
1ISEC, Polytechnic Institute of Coimbra, firstname.lastname@example.org
2DEQ, Universidade de Coimbra, email@example.com
3Imperial College, firstname.lastname@example.org
Citation Information: International Journal of Chemical Reactor Engineering. Volume 2, Issue 1, Pages –, ISSN (Online) 1542-6580, DOI: 10.2202/1542-6580.1128, January 2004
- Published Online:
We consider a hybrid modelling approach based on the combination of prior knowledge, in the form of mechanistic models, with tools for the extraction of knowledge from operating data: the first component captures first-principles system behavior features, while the second one accounts for the differences found between mechanistic predictions and real data. The empirical modelling methods tested include backpropagation Artificial Neural Networks (ANN), Multivariate Adaptive Regressive Splines (MARS) and Regression Analysis (RA). In the proposed hybrid structure, mechanistic predictions provide additional inputs for the empirical module. To evaluate the performance of the various combinations of modules and hybrid approaches, we consider two simulated case studies (involving a CSTR with a reversible reaction and a fed-batch penicillin fermentation process). In all of the above, our hybrid structure based on a mechanistic module together with an empirical component has outperformed other approaches, and the mechanistic model/MARS combination resulted in lowest overall prediction errors.