Nonlinear internal model control strategy for neural network models

Computers and Chemical Engineering

Volumn 16, Issue 12, 1992, Pages 1039-1057

  Nahas, E P ^a   Henson, M A ^a   Seborg, D E ^a  

^a UNIVERSITY OF CALIFORNIA   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

CENTRAL METHODS; MODEL STUDIES; NEURAL NETWORKS;

ALGORITHMS; COMPUTER SIMULATION; MATHEMATICAL MODELS; NEURAL NETWORKS; NONLINEAR CONTROL SYSTEMS; PH;

CONTINUOUS STIRRED TANK REACTORS; NEURAL NETWORK MODELS; NONLINEAR INTERNAL MODELS; PH NEUTRALIZATION;

CHEMICAL REACTORS;

EID: 0027007477     PISSN: 00981354     EISSN: None     Source Type: Journal    
DOI: 10.1016/0098-1354(92)80022-2     Document Type: Article

References (65)

1. Advances in process identification.
2. Nonlinear control of chemical processes—a review.
3. Optimization approaches to nonlinear model predictive control.
4. Use of neural nets for dynamic modeling and control of chemical process systems.
5. Modeling chemical process systems via neural computation
6. Generalization performance of overtrained backpropagation networks.
7. Nonlinear system identification using neural networks.
8. Adaptive control of nonlinear systems using neural networks.
9. Adaptive control of nonlinear systems using neural networks—a dead-zone approach.
10. Approximation by superpositions of a sigmoidal function.
11. Internal model control. 5. Extension to nonlinear systems.
12. On the approximate realization of continuous mappings by neural networks.
13. Nonlinear neural networks: principles, mechanisms, and architectures.
14. Dynamic modeling and reaction invariant control of pH.
15. Modelling and self-tuning control of a multivariable pH neutralization process. Part I: Modelling and multiloop control.
16. Theory of the backpropagation neural network
17. Input—output linearization of general nonlinear processes.
18. A critique of exact linearization strategies for process control.
19. An internal model control strategy for nonlinear systems
20. Neural network modelling and an extended DMC algorithm to control nonlinear systems.
21. A nonlinear DMC controller: some modeling and robustness considerations.
22. A study of the control relevant properties of backpropagation neural net models of nonlinear dynamical systems
23. Multilayer feedforward networks are universal approximators.
24. Artificial neural network models of knowledge representation in chemical engineering
25. Neural networks for nonlinear internal model control.
26. An introduction to neural computing.
27. Nonlinear principal component analysis using autoassociative neural networks.
28. Diagnosis using backpropagation neural networks—anlysis and criticism.
29. Geometric methods for nonlinear process control I. Background.
30. Geometric methods for nonlinear process control II. Controller synthesis.
31. Improvement of the backpropagation algorithm for training neural networks.
32. Neural network control of unknown nonlinear systems.
33. Process control strategies for constrained nonlinear systems.
34. An introduction to computing with neural nets
35. Interpreting biosensor data via backpropagation.
36. Error trajectory descriptions of nonlinear controller design.
37. Minimum-phase nonlinear discrete-time systems and feedback stabilization
38. Backpropagation neural networks for process control.
39. Identification and control of dynamical systems using neural networks.
40. Generalization of backpropagation to recurrent neural networks.
41. Sensor data analysis using artificial neural networks.
42. Process identification using neural networks.
43. Direct and indirect model based control using artificial neural networks.
44. Global stabilization of partially linear composite systems.
45. Neural net based model predictive control.
46. Universal approximation using feedforward networks with non-sigmoid hidden layer activation functions
47. Limitations on the stabilizability of globally minimum phase systems.
48. Neural networks in process control—a survey.
49. Adaptive networks for fault diagnosis and process control.
50. Adaptive neural networks for on-line prediction in fermentation.
51. Process fault detection using neural networks—I Steady-state processes
52. Beyond regression: new tools for prediction and analysis in the behavioral sciences.
53. 30 years of adaptive neural networks: perceptron, madaline, and backpropagation.
54. Artificial neural networks in process engineering.
55. Non-linear predictive control using optimization techniques.
56. Forecasting and control using adaptive connectionist networks.