Direct adaptive neural control for strict-feedback stochastic nonlinear systems

Abstract

This note considers the problem of direct adaptive neural control for a class of nonlinear singleinput/single-output (SISO) strict-feedback stochastic systems. The variable separation technique is introduced to decompose the coefficient functions of the diffusion term. Radical basis function (RBF) neural networks are used to approximate unknown and desired control signals, then a novel direct adaptive neural controller is constructed via backstepping. The proposed adaptive neural controller guarantees that all the signals in the closed-loop system remain bounded in probability. A main advantage of the proposed controller is that it contains only one adaptive parameter needed to be updated online. Simulation results demonstrate the effectiveness of the proposed approach.

Observer-based adaptive neural dynamic surface control for a class of non-strict-feedback stochastic nonlinear systems

“…Unlike the existing results in Deng and Krstic (1999), Yu, Zhang, and Fei (2008), Li et al (2009), Chen, Jiao, andDu (2010), Wang, Chen, and Lin (2012), Wang et al (2013), Wang et al (2014a), Wang, Liu, et al (2014), Yu and Li (2014) and Zhou et al (2013), the proposed strategy is suitable to control such non-strict-feedback systems with less conservative assumptions.…”

Observer-based adaptive neural control for a class of nonlinear pure-feedback systems

“…In [12][13][14][15], the problems of stabilization or tracing control are discussed for multiinput and multi-output (MIMO) nonlinear systems based on adaptive neural/fuzzy control technique. These results are further extended to stochastic nonlinear systems in [16][17][18][19][20][21].…”

Adaptive fuzzy control for perturbed strict-feedback nonlinear systems with predefined tracking accuracy

“…The essential idea of these control methods is that neural networks (NNs) or fuzzy logic systems (FLSs) are used to approximate unknown nonlinearities in systems dynamics, and then adaptive controllers are designed by means of adaptive control method and the backstepping technique. Lots of significant results have been reported for various uncertain systems, for instance strict-feedback systems [1][2][3][4][5][6][7], pure-feedback systems [8][9][10][11], output-feedback systems [12][13][14][15][16], nonlinear stochastic systems [17][18][19], large-scale systems [20][21][22], multi-input multi-output (MIMO) systems [23][24][25][26][27][28][29][30], and time-delay systems [31][32][33][34][35][36][37][38][39].…”