A batch-to-batch iterative optimal control strategy based on recurrent neural network models

Zhang, Xiong; Zhang, Jie

doi:10.1016/j.jprocont.2004.04.005

Cited by 140 publications

(114 citation statements)

References 30 publications

Supporting

Mentioning

113

Contrasting

Unclassified

Order By: Relevance

“…In the on-line control of polymerization processes, application of recurrent NNs can be useful (Figure 9) (Tian, et al, 2001;Xiong & Zhang, 2005). Recurrent NNs are similar to a multilayered, feed-forward, fully connected network of perceptions, but one or more of the inputs (at time t) are the outputs of the NN at times t-1, t-2 and others.…”

Section: Recurrent Neural Networkmentioning

confidence: 99%

Neural network applications in polymerization processes

Fernandes

Lona

2005

Braz. J. Chem. Eng.

View full text Add to dashboard Cite

show abstract

Section: Recurrent Neural Networkmentioning

confidence: 99%

Neural network applications in polymerization processes

Fernandes

Lona

2005

Braz. J. Chem. Eng.

View full text Add to dashboard Cite

show abstract

“…Later, Heejin et al (2004) used an Artificial Neural Network to estimate the deactivation catalyst factor used in the process of obtaining styrene monomer, with good results according to the authors. Xiong and Zhang (2005) present an application of Neural Networks to preview properties of the polymer resulting from peroxide-initiated batch polymerization of methyl methacrylate, with satisfactory results.…”

Section: Introductionmentioning

confidence: 99%

Modeling techniques and processes control application based on Neural Networks with on-line adjustment using Genetic Algorithms

Marcolla

Machado

Cancelier

et al. 2009

Braz. J. Chem. Eng.

View full text Add to dashboard Cite

-In this work a strategy is presented for the temperature control of the polymerization reaction of styrene in suspension in batch. A three-layer feed forward Artificial Neural Network was trained in an off-line way starting from a removed group of patterns of the experimental system and applied in the recurrent form (RNN) to a Predictive Controller based on a Nonlinear Model (NMPC). This controller presented very superior results to the classic controller PID in the maintenance of the temperature. Still to improve the performance of the model used by NMPC (RNN) that can present differences in relation to the system due to the dead time involved in the control actions, nonlinear characteristic of the system and variable dynamics; an on-line adjustment methodology of the parameters of the exit layer of the Network is implemented, presenting superior results and treating the difficulties satisfactorily in the temperature control. All the presented results are obtained for a real system.

show abstract

“…Because the batch processes are repetitive, the general idea of batch-to-batch or run-to-run optimization is using results from previous batches to find iteratively the optimal operating conditions, while performing the smallest number of suboptimal runs and preferably no unacceptable ones [7]. Various strategies have been proposed for batch-to-batch optimization.…”

Section: Introductionmentioning

confidence: 99%

“…Lee and his co-workers proposed a model predictive control for batch processes (BMPC) approach with quadratic criterion for temperature control in batch processes [8]. Xiong and co-workers adopted the idea of ILC, proposed a batch-to-batch iterative optimal control strategy based on recurrent neural network models to improve product quality from batch-to-batch [7], [9]. The model predictions are iteratively modified by using errors of the network model during previous batch runs, and then updated control policy is calculated by SQP for each batch using the modified model predictions.…”

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

A batch-to-batch iterative optimal control strategy based on recurrent neural network models

Cited by 140 publications

References 30 publications

Neural network applications in polymerization processes

Neural network applications in polymerization processes

Modeling techniques and processes control application based on Neural Networks with on-line adjustment using Genetic Algorithms

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

Contact Info

Product

Resources

About