Skip to main content
Erschienen in: Neural Computing and Applications 3/2005

01.09.2005 | Original Article

Adaptation of diagonal recurrent neural network model

verfasst von: D. L. Yu, T. K. Chang

Erschienen in: Neural Computing and Applications | Ausgabe 3/2005

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

An adaptive direct recurrent neural network model is developed for nonlinear dynamic system modelling in this paper. The model adaptation is achieved with the extended Kalman filter (EKF). A novel recursive algorithm is proposed to calculate the Jacobian matrix in the model adaptation so that the algorithm is simple and converges fast. The effectiveness of the developed adaptive model is demonstrated by applying to modelling a simulated continuous stirred tank reactor (CSTR). The model converges to the new process dynamics very quickly after a constant disturbance is added, and therefore can be used as an adaptive model in the adaptive model predictive control or internal model control for time-varying systems or fault tolerant control of nonlinear systems.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Almeida LB (1989) Backpropagation in non-feedforward networks. In: Aleksander (ed) Neural computing architectures. MIT Press, Cambridge, pp 75–91 Almeida LB (1989) Backpropagation in non-feedforward networks. In: Aleksander (ed) Neural computing architectures. MIT Press, Cambridge, pp 75–91
2.
Zurück zum Zitat Elman JL (1991) Distributed representations, simple recurrent networks, and grammatical structure. Machine Learn 7(2–3):195–225 Elman JL (1991) Distributed representations, simple recurrent networks, and grammatical structure. Machine Learn 7(2–3):195–225
3.
Zurück zum Zitat Hopfield J (1982) Neural networks and physical systems with emergent collective computational abilities. Proc Natl Acad Sci 79:2554–2558 Hopfield J (1982) Neural networks and physical systems with emergent collective computational abilities. Proc Natl Acad Sci 79:2554–2558
4.
Zurück zum Zitat Iiguni Y, Sakai H, Tokumaru H (1992) A real-time algorithm for a multilayered neural network based on the extended Kalman filter. IEEE Trans Signal Processing 40(4):959–966 Iiguni Y, Sakai H, Tokumaru H (1992) A real-time algorithm for a multilayered neural network based on the extended Kalman filter. IEEE Trans Signal Processing 40(4):959–966
5.
Zurück zum Zitat Karayiannis NB, Mi GW (1997) Growing radial basis neural networks: merging supervised and unsupervised learning with network growth techniques. IEEE Trans Neural Netw 8(6):1492–1506 Karayiannis NB, Mi GW (1997) Growing radial basis neural networks: merging supervised and unsupervised learning with network growth techniques. IEEE Trans Neural Netw 8(6):1492–1506
6.
Zurück zum Zitat Ku CC, Lee KY (1995) Diagonal recurrent neural networks for dynamic system control. IEEE Trans Neural Netw 6(1):144–156 Ku CC, Lee KY (1995) Diagonal recurrent neural networks for dynamic system control. IEEE Trans Neural Netw 6(1):144–156
7.
Zurück zum Zitat Lapedes A, Farber R (1986) A self-optimising nonsymmetrical neural network for content addressable memory and pattern recognition. Physica 22(Part D):247–259 Lapedes A, Farber R (1986) A self-optimising nonsymmetrical neural network for content addressable memory and pattern recognition. Physica 22(Part D):247–259
8.
Zurück zum Zitat Liguni Y, Sakai H, Tokumaru H (1992) A real-time learning algorithm for a multilayered neural network based on the extended kalman filter. IEEE Trans Signal Processing 40(4):959–966 Liguni Y, Sakai H, Tokumaru H (1992) A real-time learning algorithm for a multilayered neural network based on the extended kalman filter. IEEE Trans Signal Processing 40(4):959–966
9.
Zurück zum Zitat Liu GP, Kadirkamanathan V, Billings SA (1999) Variable neural networks for adaptive control of nonlinear systems. IEEE Trans Syst Man Cybern Pert C 29(1):34–43 Liu GP, Kadirkamanathan V, Billings SA (1999) Variable neural networks for adaptive control of nonlinear systems. IEEE Trans Syst Man Cybern Pert C 29(1):34–43
10.
Zurück zum Zitat Ljung L (1991) Issue in system identification. IEEE Control Syst Mag 11(1):25–29 Ljung L (1991) Issue in system identification. IEEE Control Syst Mag 11(1):25–29
11.
Zurück zum Zitat Ljung L, Soderstrom T (1983) Theory and practice of recursive identification. MIT Press, Cambridge Ljung L, Soderstrom T (1983) Theory and practice of recursive identification. MIT Press, Cambridge
12.
Zurück zum Zitat Luo W, Billings SA (1998) Structure selective updating for nonlinear models and radial basis function networks. Int J Adapt Cont Signal Processing 12:325–345 Luo W, Billings SA (1998) Structure selective updating for nonlinear models and radial basis function networks. Int J Adapt Cont Signal Processing 12:325–345
13.
Zurück zum Zitat Mandic DP, Chambers JA (2000) A normalised real time recurrent learning algorithm. Signal Processing 80(9):1909–1916 Mandic DP, Chambers JA (2000) A normalised real time recurrent learning algorithm. Signal Processing 80(9):1909–1916
14.
Zurück zum Zitat Pearlmutter BA (1989) Learning state space trajectories in recurrent neural networks. Neural Comput 1:263–269 Pearlmutter BA (1989) Learning state space trajectories in recurrent neural networks. Neural Comput 1:263–269
15.
Zurück zum Zitat Pereira C, Henriques J, Dourado A (2000) Adaptive RBFNN versus conventional self-tuning: comparison of two parametric model approaches for non-linear control. Control Eng Pract 8(1):3–12 Pereira C, Henriques J, Dourado A (2000) Adaptive RBFNN versus conventional self-tuning: comparison of two parametric model approaches for non-linear control. Control Eng Pract 8(1):3–12
16.
Zurück zum Zitat Pineda FJ (1987) Generalization of backpropagation to recurrent networks. Phys Rev Lett 59:2229–2232 Pineda FJ (1987) Generalization of backpropagation to recurrent networks. Phys Rev Lett 59:2229–2232
17.
Zurück zum Zitat Pineda FJ (1989) Recurrent backpropagation and the dynamical approach to adaptive neural computation. Neural Comput 1:161–172 Pineda FJ (1989) Recurrent backpropagation and the dynamical approach to adaptive neural computation. Neural Comput 1:161–172
18.
Zurück zum Zitat Valoor MT, Chandrashekhara K, Agarwal S (2001) Self-adaptive vibration control of smart composite beams using recurrent neural architecture. Int J Solids Struct 38(44–45):7857–7874 Valoor MT, Chandrashekhara K, Agarwal S (2001) Self-adaptive vibration control of smart composite beams using recurrent neural architecture. Int J Solids Struct 38(44–45):7857–7874
19.
Zurück zum Zitat Werbos PJ (1990) Backpropagation through time: what it does and how to do it. Proc IEEE 78(10):1550–1560 Werbos PJ (1990) Backpropagation through time: what it does and how to do it. Proc IEEE 78(10):1550–1560
20.
Zurück zum Zitat Williams RJ, Zipser D (1989) A learning algorithm for continually running fully recurrent neural networks. Neural Comput 1:270–280 Williams RJ, Zipser D (1989) A learning algorithm for continually running fully recurrent neural networks. Neural Comput 1:270–280
21.
Zurück zum Zitat Yang YY, Linkens DA (1994) Adaptive neural network based approach for the control of continuously stirred tank reactor. IEE Proc Part D Control Theory Appl 141(5):341–349 Yang YY, Linkens DA (1994) Adaptive neural network based approach for the control of continuously stirred tank reactor. IEE Proc Part D Control Theory Appl 141(5):341–349
22.
Zurück zum Zitat Yingwei L, Sundararajan N, Saratchandran P (1997) Identification of time-varying nonlinear systems using minimal radial basis function neural networks. IEE Proc Part D: Control Theory Appl 144(2):202–208 Yingwei L, Sundararajan N, Saratchandran P (1997) Identification of time-varying nonlinear systems using minimal radial basis function neural networks. IEE Proc Part D: Control Theory Appl 144(2):202–208
Metadaten
Titel
Adaptation of diagonal recurrent neural network model
verfasst von
D. L. Yu
T. K. Chang
Publikationsdatum
01.09.2005
Erschienen in
Neural Computing and Applications / Ausgabe 3/2005
Print ISSN: 0941-0643
Elektronische ISSN: 1433-3058
DOI
https://doi.org/10.1007/s00521-004-0453-9

Weitere Artikel der Ausgabe 3/2005

Neural Computing and Applications 3/2005 Zur Ausgabe

Premium Partner