Abstract
The present article gives an extension of the real-valued recurrent neural network topology and its Back-Propagation (BP) learning to the complex-valued one. The BP learning is achieved by the use of diagrammatic rules to obtain the adjoint recurrent neural network topology aimed to propagate the output learning error through it so to learn the neural network weights. Then, this BP learning methodology is applied to the Recurrent Complex-Valued Neural Network (RCVNN) BP-learning using two type RCVNN topologies considering two different kinds of activation functions. After that, the second system identification scheme is incorporated in a total direct complex value control scheme of nonlinear oscillatory plants, introducing also an I-term. The total control scheme contained tree RCVNNs. Furthermore, comparative simulation results of one degree of freedom flexible-joint robot model illustrating system identification and control are obtained. The obtained comparative simulation results confirmed the good quality of the proposed control methodology.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Amer, R.A., Morsy, G.A., Yassin, H.A.: SCG stability enhancement using STATCOM based-ANN controller. WSEAS Trans. Syst. Control 6(9), 325–338 (2011)
Zhang, Y., Hongsheng, S.: Turbo-generator vibration fault diagnosis based on PSO-BP neural networks. WSEAS Trans. Syst. Control 5(1), 37–47 (2010)
Zemouri, R., Gouriveau, R., Patic, P.C.: Combining a recurrent neural network and a PID controller for prognostic purpose: away to improve the accuracy of predictions. WSEAS Trans. Syst. Control 5(5), 353–371 (2010)
Lin, D., Wang, X., Nian, F., Zhang, Y.: Dynamic fuzzy neural networks modeling and adaptive back-stepping tracking control of uncertain chaotic systems. Neurocomputing 73(11–18), 2873–2881 (2010)
Zhang, H., Wang, X., Lin, X., Liu, C.: Stability and synchronization for discrete-time complex-valued neural networks with time varying delays. PLOS ONE 9(4), 6 (2014). e93838.pdf
Haykin, S.: Neural Networks: A Comprehensive Foundations. Macmillan College, New York (1994)
Narendra, K.S., Parthasarasi, K.: Identifications and control of dynamic systems using neural networks. IEEE Trans. Neural Netw. 1(1), 4–27 (1990)
Baruch, I.S., Mariaca-Gaspar, C.R.: A Levenberg-Marquardt learning applied for recurrent neural identification and control of a wastewater treatment bioprocess. Int. J. Intell. Syst. 24, 1094–1114 (2009). ISSN 0884-8173
Hirose, A.: Complex-Valued Neural Networks, vol. 400, 2nd edn. Springer, Berlin (2012)
Hirose, A.: Motion controls using complex-valued neural networks with feedback loops. In: Proceedings of IEEE International Conference on Neural Networks, vol. 1, pp. 156–161, San Francisco, CA (1993)
Minin, A., Chistyakov, Y., Kholodova, E., Zimmermann, H.G., Knoll, A.: Complex-valued open recurrent neural network for power transformer modeling. Int. J. Appl. Math. Inform. 6(1), 41–48 (2012)
Leung, H., Haykin, S.: The complex back-propagation algorithm. IEEE Trans. Signal Process. 39(9), 2101–2104 (1991)
Woo, C., Hong, D.S.: Adaptive equalization using the complex back-propagation algorithm. In: Proceedings of IEEE International Conference on Neural Networks, vol. 4, pp. 2136–2141, Washington, DC (1996)
Miklos, N., Salik, B.: Neural networks with complex activations and connection weights. Complex Syst. 8, 115–126 (1994)
Nava, F., Baruch, I., Poznyak, A., Nenkova, B.: Stability proofs of advanced recurrent neural networks topology and learning. C. R. (Proc. Bul. Acad. Sci.) 57(1), 27–32 (2004)
Wan, E., Beaufays, F.: Diagrammatic method for deriving and relating temporal neural networks algorithms. Neural Comput. 8, 182–201 (1996)
Acknowledgments
The authors Victor M. Arellano Quintana and Edmundo P. Reynaud would like to thank CONACyT, Mexico, for the student grant received during their studies at DCA, CINVESTAV-IPN, Mexico City, Mexico.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Baruch, I., Quintana, V.A., Reynaud, E.P. (2015). Dynamic Systems Identification and Control by Means of Complex-Valued Recurrent Neural Networks. In: Sidorov, G., Galicia-Haro, S. (eds) Advances in Artificial Intelligence and Soft Computing. MICAI 2015. Lecture Notes in Computer Science(), vol 9413. Springer, Cham. https://doi.org/10.1007/978-3-319-27060-9_27
Download citation
DOI: https://doi.org/10.1007/978-3-319-27060-9_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-27059-3
Online ISBN: 978-3-319-27060-9
eBook Packages: Computer ScienceComputer Science (R0)