具有未知控制方向的自适应神经网络控制

讨论了一类具有未知死区模型和未知函数控制增益的SISO非线性系统的自适应神经网络控制问题.根据滑模控制原理,并利用Nussbaum函数的性质,提出了一种自适应神经网络控制器的设计方案.该方案取消了函数控制增益符号已知和死区模型参数上界、下界已知的条件.通过引入逼近误差的自适应补偿项来消除建模误差和参数估计误差的影响.理论分析证明了闭环系统是半全局一致终结有界,且跟踪误差收敛到零.

Adaptive neural network control with unknown control direction

The problem of adaptive neural network control for a class of signal input signal output(SISO) nonlinear systems with unknown dead-zone model and unknown function control gain is discussed.Based on the principle of sliding mode control and the property of Nussbaum function,a design scheme of adaptive neural network controller is proposed.The approach does not require a priori knowledge of the sign of the control gain and the upper bound and lower bound of dead zone model parameter to be known a priori.The adaptive compensation term of the approximation error is adopted to minify the influence of modeling errors and parameter estimation errors.By theoretical analysis,the closed-loop control system is proved to be semi-globally uniformly ultimately bounded with tracking error converging to zero.