基于积分型切换函数的自适应神经网络控制

针对一类具有未知函数控制增益的非线性系统，利用RBF神经网络的逼近能力，依据滑模控制原理，提出了一种直接自适应神经网络控制器设计新方案。通过引入积分型切换函数及逼近误差自适应补偿项，监督控制用饱和函数代替符号函数，根据李雅普诺夫稳定性理论，证明了闭环系统是全局稳定的，跟踪误差收敛到零。该算法应用于连续搅拌型化学反应器CSTR（Continuous Stirred Tank Reactor），仿真结果显示，该算法能很好地使CSTR跟踪给定的温度信号，表明了该控制策略的有效性。

Adaptive Neural Network Control Based on Integral Switching Function

A design scheme of direct adaptive neural network controller for a class of nonlinear systems with unknown control gain is proposed.The design is based on the principle of sliding mode control and the approximation capability of RBF neural networks.By introducing integral switching function and adopting the adaptive compensation term of the approximation error,especially saturating function being instead of sign function in the supervisory controller,the closed-loop control system is shown to be globally stable in terms of Lyapunov theory,with tracking error converging to zero.The presented method is applied to the continuous stirred tank reactor(CSTR).Simulation results show that the control law assures the CSTR following given temperature well and the proposed control strategy is effective.