caa a22 4500 475801083 CHVBK 20180406123737.0 cr unu---uuuuu 170329e20000601xx s 000 0 eng 10.1023/A:1009615710515 doi (NATIONALLICENCE)springer-10.1023/A:1009615710515 Neural Net Based Hybrid Modeling of the Methanol Synthesis Process [Elektronische Daten] [Primož Potočnik, Igor Grabec, Marko Šetinc, Janez Levec] A Hybrid modeling approach, combining an analytical model with a radial basis function neural network is introduced in this paper. The modeling procedure is combined with genetic algorithm based feature selection designed to select informative variables from the set of available measurements. By only using informative inputs, the model's generalization ability can be enhanced. The approach proposed is applied to modeling of the liquid-phase methanol synthesis. It is shown that a hybrid modeling approach exploiting available a priori knowledge and experimental data can considerably outperform a purely analytical approach. Kluwer Academic Publishers, 2000 hybrid modeling nationallicence genetic algorithms nationallicence feature selection nationallicence methanol synthesis nationallicence neural networks nationallicence Potočnik Primož Laboratory of Technical Physics, Faculty of Mechanical Engineering, University of Ljubljana, Slovenia aut Grabec Igor Laboratory of Technical Physics, Faculty of Mechanical Engineering, University of Ljubljana, Slovenia aut Šetinc Marko Laboratory for Catalysis and Chemical Reaction Engineering, National Institute of Chemistry, Slovenia aut Levec Janez Laboratory for Catalysis and Chemical Reaction Engineering, National Institute of Chemistry, Slovenia aut Neural Processing Letters Kluwer Academic Publishers 11/3(2000-06-01), 219-228 1370-4621 11:3<219 2000 11 11063 https://doi.org/10.1023/A:1009615710515 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1023/A:1009615710515 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Potočnik Primož Laboratory of Technical Physics, Faculty of Mechanical Engineering, University of Ljubljana, Slovenia aut NATIONALLICENCE 700 1- Grabec Igor Laboratory of Technical Physics, Faculty of Mechanical Engineering, University of Ljubljana, Slovenia aut NATIONALLICENCE 700 1- Šetinc Marko Laboratory for Catalysis and Chemical Reaction Engineering, National Institute of Chemistry, Slovenia aut NATIONALLICENCE 700 1- Levec Janez Laboratory for Catalysis and Chemical Reaction Engineering, National Institute of Chemistry, Slovenia aut NATIONALLICENCE 773 0- Neural Processing Letters Kluwer Academic Publishers 11/3(2000-06-01), 219-228 1370-4621 11:3<219 2000 11 11063 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer