一类非线性动态系统的自适应模糊小波神经网络控制

对未知非线性动态系统研究基于模糊小波神经网络的自适应跟踪问题,首先构建一个模糊小波神经网络用于逼近未知的非线性函数的模型,然后根据李亚普诺夫稳定性理论建立自适应率,在线调整的模型参数包括小波网络的权重、小波的伸缩量、偏移量和模糊集合隶属函数的相关参数。提出了一种自适应模糊小波神经网络的滑模控制策略,保证系统的跟踪误差和对外界干扰的抑制被衰减到期望的程度。证明了闭环系统的半全局收敛性和鲁棒性,对倒立摆系统的仿真试验证明了所提控制方法的有效性。

Adaptive Fuzzy Wavelet Network Control for Dynamical Nonlinear Systems

The application of adaptive fuzzy wavelet networks to control problems of a class of unknown nonlinear systems is investigated. A fuzzy wavelet network is constructed to approximate an unknown nonlinear system. Based on the Lyapunov theory, suitable adaptive laws are developed to ad-just parameters including weights, dilations and translations of wavelet network, as well as the related parameters of membership functions. An adaptive sliding mode control based on fuzzy wavelet network is proposed to guarantee the effects of the tracking error and external disturbances can be attenuated to a specific attenuation level. The stability and robustness of the resulting closed-loop system are also proved. An example of an inverted pendulum system is presented to illustrate the efficiency of the proposed design procedure.