一类含动态扰动的随机非线性系统的FNN控制

针对一类非仿射且带有动态扰动的纯反馈随机非线性不确定系统，在随机Lyapunov稳定性理论框架下，利用自适应Backstepping方法并结合模糊神经网络( FNN)，设计出保证闭环系统所有信号概率意义下有界的自适应控制器。在控制器设计中，对系统动态扰动进行参数化处理，并对系统不确定性进行FNN逼近，以四层神经网络为基础构架，引入模糊逻辑对网络进行推理，其输出权值可自适应调整，设计方法有效地减少了可调参数的数量，数值仿真结果也表明设计方法的有效性。

Fuzzy Neural Network-based Control for a Class of Uncertain Stochastic Nonlinear Systems with Dynamics Disturbances

The problem of boundedness in probability is investigated for a class of uncertain stochastic nonlinear pure-feedback systems with dynamic disturbances. Under the framework of stochastic Lyapunov stability theory and based on FNN,the controllers and the adaptation laws are obtained by using of the backstepping design technique,which render the closed-loop systems boundedness in probability. During the course of designing,the dynamic disturbances are parameterized and the uncertainties are approxima-ted. Due to four layers of neural network architecture,a better approximation can be achieved by introdu-cing fuzzy logic and the adjustable weight of output layer. So the fewer design parameters are demanded. An example is given to verify the effectiveness of the proposed design approach.