Dynamic modeling of batch polymerization reactors via the hybrid neural-network rate-function approach

Chang, Jyh-Shyong; Lu, Shih-Chieh; Chiu, Yu-Lun

doi:10.1016/j.cej.2006.11.011

Cited by 24 publications

(17 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Whereas, when someone adopts this method, some unknown parameters have to be fitted by employing nonlinear optimization methods [2]. For avoiding the difficulties of traditional mathematical models, neural networks [3,4] are utilized as an alternative technology.…”

Section: Introductionmentioning

confidence: 99%

Soft sensor of chemical processes with large numbers of input parameters using auto-associative hierarchical neural network

Geng

et al. 2015

Chinese Journal of Chemical Engineering

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Soft sensor of chemical processes with large numbers of input parameters using auto-associative hierarchical neural network

Geng

et al. 2015

Chinese Journal of Chemical Engineering

View full text Add to dashboard Cite

“…The system is described by first-principle equations, while neural networks take account of other terms, usually constitutive equations (21,22). Tomksac (23) applied the hybrid model to describe the adsorption of copper, zinc, and chromium ions onto a chitosan foam structure.…”

Section: Introductionmentioning

confidence: 99%

Comparison of Phenomenological and Hybrid Models in the Description of the Ion Exchange Process in a Fixed-Bed Column

D'Arisbo

Silva

Borba

et al. 2013

Separation Science and Technology

View full text Add to dashboard Cite

In this study, two models (phenomenological and hybrid) were used in the description of the ion exchange process in a fixed-bed column. The external and internal mass transfer limitations and thermodynamic equilibrium at the solid-liquid interface were considered. In the phenomenological model, the mass action law was used to describe the equilibrium, while, in the hybrid model an artificial neural network (ANN) was used. The experimental equilibrium data were used for the validation of the ANN. The performance of the models was compared using experimental breakthrough curves. Both models described well the ion exchange process. The simulation time using the hybrid model was shorter.

show abstract

“…Then the built MRFNN model is used for predicting tested by the unseen testing batch. The predicting RMSE is 0.0073, and the long-range prediction of 2 x from MRFNN on the unseen testing data is shown in Fig. 3 …”

Section: Production Quality Control Of a Batch Reactormentioning

confidence: 99%

“…To construct a mechanistic model for a batch system, challenging difficulties occur in determining coefficients of the reaction. Once the expression is available, the unknown correlated parameters have to be fitted by optimization or estimated [2].…”

Section: Introductionmentioning

confidence: 99%

Batch-to-batch control of batch processes based on multilayer recurrent fuzzy neural network

Liu¹,

Jia²,

Liu³

et al. 2007

Proceedings on Intelligent Systems and Knowledge Engineering (ISKE2007)

View full text Add to dashboard Cite

The batch-to-batch model-based iterative optimal control strategy for batch processes is realized based on multilayer recurrent fuzzy neural network (MRFNN) and chaotic search. MRFNNs are used to model batch processes. Modeling and optimization problems are mainly solved by chaotic search. Due to model-plant mismatches and disturbances, the calculated optimal control profile may not be optimal when applied to the actual process. Current predictions are improved by prediction errors from previous batches, and the model errors are gradually reduced from batch-to-batch. Furthermore, the control strategy is developed for temperature tracking control. The effectiveness is verified on simulated batch reactors.

show abstract

Dynamic modeling of batch polymerization reactors via the hybrid neural-network rate-function approach

Cited by 24 publications

References 20 publications

Soft sensor of chemical processes with large numbers of input parameters using auto-associative hierarchical neural network

Soft sensor of chemical processes with large numbers of input parameters using auto-associative hierarchical neural network

Comparison of Phenomenological and Hybrid Models in the Description of the Ion Exchange Process in a Fixed-Bed Column

Batch-to-batch control of batch processes based on multilayer recurrent fuzzy neural network

Contact Info

Product

Resources

About