The enhancement of empirical model capability and optimal/robust design of intractable processes

Industrial and Engineering Chemistry Research

Volumn 40, Issue 18, 2001, Pages 3951-3964

  Lin, J S ^a   Jang, S S ^a   Chien, S J ^a   Ma, C C ^a   Shieh, S S ^b  

^a NATIONAL TSING HUA UNIVERSITY   (Taiwan)

^b CHANG JUNG CHRISTIAN UNIVERSITY   (Taiwan)

Author keywords

[No Author keywords available]

Indexed keywords

NEURAL NETWORKS; POLYMERS; PULTRUSION;

POLYMER COMPOSITES;

PRODUCT DESIGN;

POLYMER;

DESIGN; MODEL; PROCESS OPTIMIZATION;

ARTICLE; ARTIFICIAL NEURAL NETWORK; INDUSTRY; MATHEMATICAL ANALYSIS; MATHEMATICAL MODEL; OCCUPATIONAL SAFETY; SIMULATION;

EID: 0035812256     PISSN: 08885885     EISSN: None     Source Type: Journal    
DOI: 10.1021/ie000543h     Document Type: Article

References (35)

1. Product and process development using artificial neural network model and information theory
2. Experiment design considerations for nonlinear system identification using neural networks
3. Long-term predictions of chemical processes using recurrent neural networks: A parallel training approach
4. Predictive control of quality in a batch manufacturing process using artificial neural network models
5. Process modeling using stacked neural networks
6. A new scheme combining neural feedward control with model-predictive control
7. Dynamic optimization of nonlinear processes by combining neural net model with UDMC
8. Nonlinear internal model control strategy for neural network models
9. Multivariable nonlinear control applications for a high purity distillation column using a recurrent dynamic neuron model
10. A hybrid neural network - First principles approach to process modeling
11. Modeling chemical processes using prior knowledge and neural networks
12. Dynamic rectifcation of data via recurrent neural nets and the extended kalman filter
13. Predictive control of quality in batch polymerization using a hybrid artificial neural network model
14. Generalized multivariable dynamic artificial neural network modeling for chemical processes
15. Network information criterion - Determining the number of hidden units for an artificial neural network model
16. An information criterion for optimal neural network selection
17. Model-structure selection by cross-validation
18. Cross-validation and other criteria for estimating the regularizing parameter
19. Note on generalization, regularization and architecture selection in nonlinear learning systems
20. Regularization algorithms for learning that are equivalent to multilayer networks
21. Asymptotic statistical theory of overtraining and cross-validation
22. The development of a mathematical model for the pultrusion of blocked polyurethane composites
23. The correlations of processing variables for optimizing the pultrusion process
24. Pultrusion of poly(ε-caprolactam)/poly(butadiene-co-arcylonitrile) composites: I. Simulation and a mathematical model
25. Pultruded fiber-reinforced PMMA/PU IPN composites: Processability and mechanical properties
26. A symptotically efficient selection of the order of the model for estimating parameter of a linear process
27. Noise sensitivity signatures for model selection
28. A new look at the statistical model identification
29. Development of a mathematical model for the pultrusion process
30. Heat transfer and cure in pultrusion: Model and experimental verification