Big Chemical Encyclopedia

Chemical substances, components, reactions, process design ...

Articles Figures Tables About

Hybrid neural models

K. Ciesielski and I. Zbicinski, Hybrid neural modelling of fluidised bed drying process. Drying Technology, 19(8) 1725-1738 (2001). [Pg.1100]

Regarding handling of model responses, process inversion (calculation of u°p with the help of the model) can be performed implicitly with the help of numerical procedures (the model provides process responses y as functions of inputs u and initial states x), or can be performed explicitly, by developing empirical and/or hybrid neural models off-line (the model provides inputs u as functions of process responses y and initial states x) [ 196, 203-206]. In the first case, model responses are more robust, although model inversion is much faster in the second case. Besides, if the process model can be fairly described by linear or bilinear models, then analytical results can be provided for the optimization problem [40,193,207,208], which makes the real-time implementation of predictive controllers much easier. [Pg.355]

Cubillos, F. and Lima, E., 1998, Adaptive hybrid neural models for process control. Computers and Chemical Engineering, Vol 22, S989-S992. [Pg.400]

Zbicinski, P. Strumiilo and W. Kaminski, Hybrid Neural Model of Thermal Drying in a Fluidized Bed, Computers Chem. Engng. vol. 20, (1996) 695-700... [Pg.580]

Hybrid neural model based on a parallel architecture. [Pg.576]

Case study prediction of permeate flux decay during ultrafiltration performed in pulsating conditions by a hybrid neural model... [Pg.581]

Case study implementation of feedback control systems based on hybrid neural models... [Pg.587]

Psichogios, D. C., and Ungar, L. H., A hybrid neural network-first principles approach to process modeling. AIChEJ. 38, 1499 (1992). [Pg.205]

Neural Network based hybrid dynamic modelling and optimisation methods for conventional and unconventional column configurations... [Pg.405]

Figure 5.15 Principle of mass transfer model integration with a neural net (hybrid neural-regression model). Figure 5.15 Principle of mass transfer model integration with a neural net (hybrid neural-regression model).
M.A.Reuter, Hybrid Neural Net Modelling in Metallurgy , Second International Symposium on Metallurgical Processes for Early Twenty-First Century. H.Y. Sohn, Ed., The Minerals, Metals and Materials Society, Warrendale, PA, U.S.A., 1994,907-927. [Pg.240]

Qi, H.Y., Zhou, X.G., Liu, L.H. and Yuan, W.K., 1999, A hybrid neural networks-first principals model for fixed-bed reactor. Chemical Engineering Science, 54, 2521. [Pg.604]

The second method is to use combined heuristic and generalisation properties of hybrid GA-ANN or PSO-ANN models. Here a neural model is developed in the same manner discussed previously with input/output unaltered. Thereafter, a PSO or GA is adopted to search for the optimal combinations of input variables to achieve target output with the cost function being trained NN. [Pg.254]

Psichogios, D.C., L.H. Ungar (1992). A hybrid neural network - first principles approach to process modelling, AIChE J. 38 (10) pp. 1499-1511. [Pg.438]

Additionally, there is an hybrid approach to modelling, which combines a neural model with a mathematical model [17,18]. Models of this type are recommended in the cases when a detailed mathematical description of some aspects of the process is available. [Pg.571]

D C Psichogios and L.H Ungar., A Hybrid Neural Network - First Principle Approach to Process Modelling, AIChE Journal, 38, 10, (1992) 1499-1511. [Pg.580]

In the present contribution, it has been shown that both ANNs and hybrid models definitely represent powerful computational tools, offering very reliable predictions of the actual behavior of membrane systems. The results obtained demonstrate, in particular, that the proper combination of a theoretical model with a straightforward neural model is able to widen the applicability of pure neural models beyond the training range, thus paving the way for the exploitation of the HNM for process optimization purposes and for the implementation of efficient on-line controllers operating on different kinds of membrane processes. [Pg.594]

Ou S., Achenie L.E.K., A hybrid neural network model for PEM fuel ceWs, Journal of Power Sources, 2005,140(2), 319-330. [Pg.595]

Psichogios D. D., Ungar L.H., A hybrid neural network-First principle approach to process modeling, A7C/z Journal, 1992,38(10), 1499-1511. [Pg.595]

Saraceno A.,Curcio S.,Calabr6 V.,Iorio G., A hybrid neural approach to model batch fermentation of ricotta cheese whey to ethanol. Computers and Chemical Engineering, 2010,34(10), 1590-1596. [Pg.596]


See other pages where Hybrid neural models is mentioned: [Pg.486]    [Pg.47]    [Pg.576]    [Pg.584]    [Pg.587]    [Pg.587]    [Pg.594]    [Pg.714]    [Pg.486]    [Pg.47]    [Pg.576]    [Pg.584]    [Pg.587]    [Pg.587]    [Pg.594]    [Pg.714]    [Pg.143]    [Pg.457]    [Pg.458]    [Pg.181]    [Pg.206]    [Pg.195]    [Pg.401]    [Pg.569]    [Pg.119]    [Pg.178]    [Pg.85]    [Pg.130]    [Pg.304]   


SEARCH



Hybrid modeling

Hybrid modelling

Hybrid models

Neural modeling

© 2024 chempedia.info