Abstract
This paper presents a stable, on-line identification scheme for multivariable nonlinear dynamic system. Growing Gaussian Radial Basis Function (GRBF) network with all its parameters being adaptable is used to approximate an unknown nonlinear system. Based on a continuous-time framework, the parameter adjustment law is derived using Lyapunov synthesis approach, which guarantees the stability of the overall system. In addition, to ensure the convergence of the approximation error, a growing strategy for the network is selected and a dead zone is incorporated in the tuning law. Simulation studies on identifying a time-varying nonlinear missile dynamics illustrate the superior performance of the proposed scheme. The studies also indicate that stability and reduction in approximation error can be extended to a network with pruning strategy, thereby resulting in a Growing and Pruning (GAP) RBF network, which can implement a more compact network structure.
Similar content being viewed by others
References
Ni, X. and Simons, Stef J. R.: Nonlinear dynamic system identification using radial basis function networks. Proceedings of the 35th Conference on Decision and Control, Kobe, Japan, (1996), pp. 935-936.
Liu, G. P., Kadirkamanathan, V. and Billings, S. A.: Stable sequential identification of continuous nonlinear dynamical systems by growing radial basis function networks. Int. J. Control, 65(1) (1996), 53-69.
Chen, S., Mulgrew, B. and Grant, P. M.: A clustering technique for digital communications channel equilization using radial basis function networks. IEEE Trans. Neural Networks 4 (1993), 570-579.
Panchapakesan, C., Ralph, D. and Palaniswami, M.: Effects of moving the centers in an RBF network. Proc.1998 IEEE Int. Joint Conf. Neural Networks 2 (1998), 1256-1260.
Birgmeier, M.: A fully Kalman-trained radial basis function network for nonlinear speech modeling. Proc. IEEE Int. Conf. Neural Networks 1 (1995), 259-264.
Lu, Y., Sundararajan, N. and Saratchandran, P.: Performance evolution of a sequential minimal RBF neural network learning algorithm. IEEE Trans. on Neural Networks 9(2) (1998), 308-318.
Sum, J., Chi-Sing Leung, Young, G. H. and Wing-Kay Kan.: On the Kalman filtering method in neural-network training and pruning. IEEE Trans. on Neural Networks 10(1) (1999), 161-166.
Park, J. and Sandberg, I. W.: Universal approximation using radial basis function networks. Neural Computation 3 (1991), 246-257.
Platt, J. C.: A resource allocating network for function interpolation. Neural Computation 3(1991), 213-225.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Yan, L., Sundararajan, N. & Saratchandran, P. Nonlinear System Identification Using Lyapunov Based Fully Tuned Dynamic RBF Networks. Neural Processing Letters 12, 291–303 (2000). https://doi.org/10.1023/A:1026571426761
Issue Date:
DOI: https://doi.org/10.1023/A:1026571426761