Optimal output-feedback tracking of SISO stochastic nonlinear systems using multi-dimensional Taylor network

The randomness and nonlinearity of stochastic nonlinear systems increase computational complexity and impede their tracking performance. However, randomness and nonlinearity are inevitable in practical applications, and the existing methods can hardly achieve the desirable control effect, especially in real-time control. For this end, a new network control strategy based on multi-dimensional Taylor network (MTN), whose design depends only on the system output, is put forward to solve the optimal output-feedback tracking problem of the SISO stochastic nonlinear systems. The network structure of the MTN is given first, and its approximation properties are proven. Based on the quadratic cost function design learning algorithm, the tracking error is minimized to update the controller parameters, and the desired tracking performance is obtained. Using the Lyapunov stability theorem, it is proved that the corresponding closed-loop system is bounded in the sense of probability and it can be ensured that the output tracking error converges to a small residual set around the origin in the sense of probability. An example is provided to illustrate the effectiveness of the proposed design approach. Comparative simulation study reveals that the proposed solution promises desirable real-time dynamic performance.

[1]  B Zhou.  A Dynamics Model Based on Intermittent Feedback Multi-dimensional Taylor Network , 2014 .

[2]  Antonio T. Alexandridis,et al.  NN-Based Adaptive Tracking Control of Uncertain Nonlinear Systems Disturbed by Unknown Covariance Noise , 2007, IEEE Transactions on Neural Networks.

[3]  Quanxin Zhu,et al.  Razumikhin-type theorem for stochastic functional differential equations with Lévy noise and Markov switching , 2017, Int. J. Control.

[4]  Licheng Jiao,et al.  Adaptive NN Backstepping Output-Feedback Control for Stochastic Nonlinear Strict-Feedback Systems With Time-Varying Delays , 2010, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[5]  Hai-Bo Ji,et al.  Adaptive output-feedback tracking of stochastic nonlinear systems , 2006, IEEE Transactions on Automatic Control.

[6]  L. Jiao,et al.  Brief Paper: Output-feedback adaptive dynamic surface control of stochastic non-linear systems using neural network , 2010 .

[7]  Quanxin Zhu,et al.  Decentralized risk-sensitive design for large-scale stochastic interconnected systems with time-varying delays , 2016, J. Frankl. Inst..

[8]  Hong-Sen Yan,et al.  Asymptotically tracking and dynamic regulation of SISO nonlinear system based on multi-dimensional Taylor network controller , 2015, 2015 15th International Conference on Control, Automation and Systems (ICCAS).

[9]  Bing Chen,et al.  Adaptive neural tracking control for a class of stochastic nonlinear systems , 2014 .

[10]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[11]  T. Başar,et al.  Adaptive Controller Design for Tracking and Disturbance Attenuation in Parametric-Strict-Feedback Nonlinear Systems , 1996 .

[12]  Dan Wang,et al.  Neural network-based adaptive dynamic surface control for a class of uncertain nonlinear systems in strict-feedback form , 2005, IEEE Transactions on Neural Networks.

[13]  X. Mao.  LaSalle-Type Theorems for Stochastic Differential Delay Equations , 1999 .

[14]  Zigang Pan,et al.  Differential geometric condition for feedback complete linearization of stochastic nonlinear system , 2001, Autom..

[15]  Jie Tian,et al.  Adaptive state-feedback stabilization for high-order stochastic non-linear systems with uncertain control coefficients , 2007, Int. J. Control.

[16]  Lin Yi,et al.  Nonlinear time series prediction method based on multi-dimensional Taylor network and its applications , 2014 .

[17]  Shuzhi Sam Ge,et al.  Adaptive neural network control for strict-feedback nonlinear systems using backstepping design , 1999, Proceedings of the 1999 American Control Conference (Cat. No. 99CH36251).

[18]  Wang Chaoli,et al.  Adaptive state-feedback stabilization of stochastic high-order nonholonomic systems with nonlinear parameterization , 2014, Proceedings of the 33rd Chinese Control Conference.

[19]  Zhong-Ping Jiang,et al.  Decentralized adaptive output-feedback stabilization for large-scale stochastic nonlinear systems , 2007, Autom..

[20]  Quanxin Zhu,et al.  Noise suppresses explosive solutions of differential systems: A new general polynomial growth condition☆ , 2015 .

[21]  Shuzhi Sam Ge,et al.  Robust adaptive neural control for a class of perturbed strict feedback nonlinear systems , 2002, Proceedings of the 4th World Congress on Intelligent Control and Automation (Cat. No.02EX527).

[22]  H. E. Psillakis,et al.  Adaptive Neural Tracking for a Class of SISO Uncertain and Stochastic Nonlinear Systems , 2005, Proceedings of the 44th IEEE Conference on Decision and Control.

[23]  Yungang Liu,et al.  Output feedback control design for strict-feedback stochastic nonlinear systems under a risk-sensitive cost , 2003, IEEE Trans. Autom. Control..

[24]  Jifeng Zhang,et al.  Output‐feedback control of a class of stochastic nonlinear systems with linearly bounded unmeasurable states , 2008 .

[25]  Feng Jiang,et al.  Globally asymptotic stabilization of stochastic nonlinear systems in strict-feedback form , 2015, J. Frankl. Inst..

[26]  P. Florchinger.  Lyapunov-Like Techniques for Stochastic Stability , 1995 .

[27]  Miroslav Krstic,et al.  Stabilization of stochastic nonlinear systems driven by noise of unknown covariance , 2001, IEEE Trans. Autom. Control..

[28]  Geoffrey E. Hinton,et al.  Learning representations by back-propagation errors, nature , 1986 .

[29]  Xiaojun Zhou,et al.  A Particle Swarm Optimization Algorithm with Variable Random Functions and Mutation , 2014 .

[30]  R. Khasminskii.  Stability of Stochastic Differential Equations , 2012 .

[31]  Shaocheng Tong,et al.  Adaptive neural network tracking control for a class of non-linear systems , 2010, Int. J. Syst. Sci..

[32]  M. Krstić,et al.  Stochastic nonlinear stabilization—I: a backstepping design , 1997 .

[33]  Hui Wang,et al.  Finite-time stabilization of high-order stochastic nonlinear systems in strict-feedback form , 2015, Autom..

[34]  Quanxin Zhu,et al.  Mean square exponential stability of stochastic nonlinear delay systems , 2017, Int. J. Control.

[35]  Weisheng Chen,et al.  Adaptive NN output‐feedback decentralized stabilization for a class of large‐scale stochastic nonlinear strict‐feedback systems , 2011 .

[36]  Guo-Xing Wen,et al.  Fuzzy Neural Network-Based Adaptive Control for a Class of Uncertain Nonlinear Stochastic Systems , 2014, IEEE Transactions on Cybernetics.

[37]  Qian Ma,et al.  State feedback control for a class of stochastic high-order feedforward nonlinear systems with time-varying delays: a homogeneous domination approach , 2014 .

[38]  Miroslav Krstic,et al.  Output-feedback stochastic nonlinear stabilization , 1999, IEEE Trans. Autom. Control..

[39]  Simon X. Yang,et al.  Robust stability criteria for uncertain stochastic neural networks of neutral-type with interval time-varying delays , 2011, Neural Computing and Applications.

[40]  Shuzhi Sam Ge,et al.  Neural network control for non-affine nonlinear systems , 2007, 2007 European Control Conference (ECC).

[41]  Qi-Ming Sun,et al.  Optimal tracking control of MISO nonlinear systems based on multi-dimensional Taylor network only by output feedback , 2015, 2015 15th International Conference on Control, Automation and Systems (ICCAS).

[42]  B Zhou.  Financial time series forecasting based on wavelet and multi-dimensional Taylor network dynamics model , 2013 .

[43]  Zigang Pan,et al.  Canonical forms for stochastic nonlinear systems , 1997, Proceedings of the 36th IEEE Conference on Decision and Control.

[44]  T. Basar,et al.  Backstepping controller design for nonlinear stochastic systems under a risk-sensitive cost criterion , 1997, Proceedings of the 1997 American Control Conference (Cat. No.97CH36041).