Abstract
Aiming at a kind of nonlinear dead zone system, a novel identification method based on support vector machines was presented. In the method, the nonlinear dynamic characteristic of systems was expressed by using the Hammerstein model and the dead zone nonlinear model was created by using the least squares support vector machine. Furthermore, the strategy of the modified cost function was adopted to improve the accuracy of the dead zone model based on the inputs. In addition, the convergence condition of the algorithm is analyzed theoretically. Finally, the simulation on a hydraulic positioning servo system was carried out, and it is verified that the accuracy of the model identification is improved efficiently by using the proposed method.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Merzouki, R., Davila, J.A., Fridman, L., et al.: Backlash Phenomenon Observation and Identification in Electromechanical System. Control Engineering Practice 15(4), 447–457 (2007)
Li, S.X., Zhu, J.: A Modeling Method for the Non-Linear Servo System Containing a Dead Zone. Automation Technology and Application 18, 4–8 (1999)
Dai, Y.P., Deng, R., Liu, J.: Research on Parameter Identification for Nonlinear Steam Turbine Governing System Based on Genetic Algorithm. Power Engineering 23(1), 2215–2218 (2003)
Cao, X.Q., Lu, Q.H.: Two-Step Method for Identifying Physic Parameters of Systems with Dead Zone Nonlinearity. Journal of Tsinghua University (Natural Science) 47, 2045–2047 (2007)
Wang, X.S., Sub, C.Y., Henry, H.: Robust Adaptive Control of a Class of Nonlinear Systems with Unknown Dead-Zone. Automatica 40, 407–413 (2004)
Lee, S.W., Kim, J.H.: Control of System with Deadzones Using Neural Network Based on Learning Controller. In: Proc. IEEE Int. Conf. Neural Networks, pp. 2535–2538 (1994)
Zhu, Q.B.: Neural Network Learning Correction Method of the Nonlinear Sensing Characteristics and Its Application. Instruments Journal 25(6), 505–805 (2004)
Tsai, C.H., Chuang, H.T.: Deadzone Compensation Based on Constrained RBF Neural Network. Journal of the Franklin Institute 341, 361–374 (2004)
Selmic, R.R., Lewis, F.L.: Deadzone Compensation in Motion Control Systems Using Neural Networks. IEEE Trans. Autom. Control 45, 602–613 (2000)
Vapnik, V.: The Nature of Statistical Learning Theory. Springer, New York (1995)
Suykens, J., Vandewalle, J.: Least Squares Support Vector Machines Classifiers. Neural Processing Letters 9, 293–300 (1999)
Suykens, J., Van, G., De Brabanter, J., et al.: Least Squares Support Vector Machines. World Scientific Publishing Co Pte Lte, Singapore (2002)
Tsai, C.H., Chuang, H.T.: Deadzone Compensation Based on Constrained RBF Neural Network. Journal of the Franklin Institute 341, 361–374 (2004)
Chen, Z.H.: A New Identification Method of Nonlinear System Based on the Hammerstein Model. Control Theory and Applications 24(1), 143–147 (2007)
Shen, Q.K., Zhang, T.P.: Robustly Adaptive Fuzzy Control for the Unknown Nonlinear Dead-zone. Control and Decision 21(4), 368–375 (2006)
Cho, H., Bai, E.W.: Convergence Results for an Adaptive Deadzone Inverse. Int. J. Adaptive. Control Signal Processing 12, 451–466 (1998)
Tao, G., Kokotovic, P.V.: Adaptive Sliding Control of Plants with Unknown Dead-zone. IEEE Trans. Autom. Control 39, 59–68 (1994)
Vijayakumar, S., Wu, S.: Sequential Support Vector Classifiers and Regression. In: Proc. Int. Conf. on Soft Computing, vol. 5, pp. 610–619 (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Du, J., Wang, M. (2009). Nonlinear Dead Zone System Identification Based on Support Vector Machine. In: Wang, H., Shen, Y., Huang, T., Zeng, Z. (eds) The Sixth International Symposium on Neural Networks (ISNN 2009). Advances in Intelligent and Soft Computing, vol 56. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-01216-7_25
Download citation
DOI: https://doi.org/10.1007/978-3-642-01216-7_25
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-01215-0
Online ISBN: 978-3-642-01216-7
eBook Packages: EngineeringEngineering (R0)