Abstract
In this paper, we present and investigate a new type of radial basis function (RBF) neural networks mechanism using raised-cosine (RC) function to identify nonlinear dynamic system. In this design, the RBF neural networks mechanism utilizes RC function to replace Gaussian function, which is called RCRBF. An N-dimensional RC function has the constant interpolation property, which is benefit for the function approximating errors analysis in the neural networks. Based on multivariable RC function approximation theory, we develop how to select the updated parameters and the distance of adjacent nodes in lattice points. Therefore, the proposed networks can uniformly approximate nonlinear dynamical function. As persistency excitation (PE) plays an important part in neural networks learning system, how does PE condition behave in input sequences is formulated by RC function analysis. The weights updating and errors convergence are concluded by Lyapunov function analysis. To illustrate the effectiveness of the proposed RCRBF method, Van Der Pol and Rossler dynamical system are used as test examples, in comparison with GRBF mechanism. The results show that the proposed method has better accurate identification and approximating effect than that of GRBF mechanism.
Similar content being viewed by others
References
Xu X, Lian C, Zuo L et al (2014) Kernel-based approximate dynamic programming for real-time online learning control: an experimental study. IEEE Trans Control Syst Technol 22:146–156
Min W, Cong W (2015) Neural learning control of pure-feedback nonlinear systems. Nonlinear Dyn 79:2589–2608
Zong Q, Wang F, Tian B et al (2014) Robust adaptive dynamic surface control design for a flexible air-breathing hypersonic vehicle with input constraints and uncertainty. Nonlinear Dyn 78:289–315
Zhang Y, Li S, Liu X (2017) Adaptive near-optimal control of uncertain systems with application to underactuated surface vessels. IEEE Trans Control Syst Technol 26:1–15
Dong J, Zhang G (2017) Identification and robust control of the nonlinear photoelectrothermal dynamics of LED systems. IEEE Trans Ind Electron 64:2215–2225
Arnst M, Ghanem R, Masri R (2010) Maximum entropy approach to the identification of stochastic reduced-order models of nonlinear dynamical systems. Aeronaut J 114:637–650
Pavlenko V, Pavlenko S, Speranskyy V (2013) Interpolation method of nonlinear dynamical systems identification based on volterra model in frequency domain. In: 2013 IEEE 7th international conference on intelligent data acquisition and advanced computing systems: technology and applications (IDAACS). IEEE
Greblicki M, Pawlak M (2019) The weighted nearest neighbor estimate for Hammerstein system identification. IEEE Trans Autom Control 64:1550–1565
Chen Y, Bo Y, Dong J (2006) Time-series prediction using a local linear wavelet neural network. Neurocomputing 69:449–465
Pindoriya NM, Singh SN, Singh SK (2008) An adaptive wavelet neural network-based energy price forecasting in electricity markets. IEEE Trans Power Syst 23:1423–1432
Wai RJ, Chang HH (2004) Backstepping wavelet neural network control for indirect field-oriented induction motor drive. IEEE Trans Neural Netw 15:367–382
Park J, Sandberg IW (2014) Universal approximation using radial-basis-function networks. Neural Comput 3:246–257
Alexandridis A, Chondrodima E, Giannopoulos N et al (2017) A fast and efficient method for training categorical radial basis function networks. IEEE Trans Neural Netw Learn Syst 28:1–6
Zhang XY, Xie GS, Liu CL et al (2017) End-to-end online writer identification with recurrent neural network. IEEE Trans Hum–Mach Syst 47(2):285–292
Mou L, Bruzzone L, Xiao XZ (2018) Learning spectral–spatial–temporal features via a recurrent convolutional neural network for change detection in multispectral imagery. IEEE Trans Geosci Remote Sens 57:1–12
Tang J, Fang L, Zou Y et al (2017) An improved fuzzy neural network for traffic speed prediction considering periodic characteristic. IEEE Trans Intell Transp Syst 18:1–11
Mushage BO, Chedjou JC, Kyamakya K (2017) Fuzzy neural network and observer-based fault-tolerant adaptive nonlinear control of uncertain 5-DOF upper-limb exoskeleton robot for passive rehabilitation. Nonlinear Dyn 87:2021–2037
Zhao H, Gao S, He Z et al (2014) Identification of nonlinear dynamic system using a novel recurrent wavelet neural network based on the pipelined architecture. IEEE Trans Ind Electron 61:4171–4182
Cannon M (1995) Space-frequency localized basis function networks for nonlinear system identification and control. Neurocomputing 9:293–342
Chen Y, Yang B, Dong J (2006) Time-series prediction using a local linear wavelet neural network. Neurocomputing 69:449–465
Zhang J, Walter GG, Miao Y et al (1995) Wavelet neural networks for function learning. IEEE Trans Signal Process 43:1485–1497
Carrillo-Santos CA, Seck-Tuoh-Mora JC, Hernandez-Romero N et al (2018) Wavenet identification of dynamical systems by a modified PSO algorithm. Eng Appl Artif Intell 73:1–9
Kumar R, Srivastava S, Gupta JRP et al (2018) Diagonal recurrent neural network based identification of nonlinear dynamical systems with Lyapunov stability based adaptive learning rates. Neurocomputing 287:102–117
Tavoosi J, Badamchizadeh MA (2013) A class of type-2 fuzzy neural networks for nonlinear dynamical system identification. Neural Comput Appl 23:707–717
Sanner RM, Slotine JJE (1992) Stable recursive identification using radial basis function networks. In: American control conference
Gorinevsky D (1995) On the persistency of excitation in radial basis function network identification of nonlinear systems. IEEE Trans Neural Netw 6:1237–1244
Kurdila AJ, Narcowich FJ, Ward JD (2006) Persistency of excitation in identification using radial basis function approximants. SIAM J Control Optim 33:625–642
Wang C, Hill DJ (2003) Learning from neural control. IEEE Trans Neural Netw 17:130–146
Zheng T, Wang C (2017) Relationship between persistent excitation levels and RBF network structures, with application to performance analysis of deterministic learning. IEEE Trans Cybern 47:3380–3392
Wang C, Hill DJ, Chen G (2009) Deterministic learning of nonlinear dynamical systems. Int J Bifurc Chaos 19:1307–1328
Yuan C, Wang C (2011) Persistency of excitation and performance of deterministic learning. Syst Control Lett 60:952–959
Liu T, Wang C, Hill DJ (2009) Learning from neural control of nonlinear systems in normal form. Syst Control Lett 58:633–638
Zeng W, Ismail SA, Lim YP et al (2019) Classification of gait patterns using kinematic and kinetic features, gait dynamics and neural networks in patients with unilateral anterior cruciate ligament deficiency. Neural Process Lett 50:887–909
Wei Z, Cong W, Yang F (2014) Silhouette-based gait recognition via deterministic learning. Pattern Recognit 47:3568–3584
Schilling RJ, Carroll JJJ, Alajlouni AF (2001) Approximation of nonlinear systems with radial basis function neural networks. IEEE Trans Neural Netw 12:1–15
Pan Y, Yu H, Meng JE (2014) Adaptive neural PD control with semiglobal asymptotic stabilization guarantee. IEEE Trans Neural Netw Learn Syst 25:2264–2274
Al-Ajlouni AF, Schilling RJ, Harris SL (2004) Identification of nonlinear discrete-time systems using raised-cosine radial basis function networks. Int J Syst Sci 35:211–221
Sanner RM, Slotine JE (1992) Gaussian networks for direct adaptive control. IEEE Trans Neural Netw 3:837–863
Jinkun LIU (2013) RBF neural network control for mechanical systems design, analysis and Matlab simulation. Tsinghua & Springer Press, New York
Wirkus S, Rand R (2015) The dynamics of two coupled van der Pol oscillators with delay coupling. Nonlinear Dyn 30:205–221
Park JH (2005) Adaptive synchronization of Rossler system with uncertain parameters. Chaos Solitons Fract 25:333–338
Acknowledgements
The authors would like to thank anonymous peer reviewer.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Luo, G., Yang, Z., Zhan, C. et al. Identification of Nonlinear Dynamical System Based on Raised-Cosine Radial Basis Function Neural Networks. Neural Process Lett 53, 355–374 (2021). https://doi.org/10.1007/s11063-020-10410-9
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-020-10410-9