一种自适应CMAC 在交流励磁水轮发电系统中仿真研究

在分析常规CMAC结构的基础上，针对一类非线性、参数时变和不确定的控制系统，提出了一种自适应CMAC神经网络的控制器．该控制器以系统动态误差和给定信号量作为CMAC的激励信号，并与自适应线性神经元网络相结合构成系统的复合控制．为了验证其有效性，将其应用到交流励磁水轮发电机系统的多变量非线性控制中，并与常规的PID控制效果进行了比较．仿真结果表明，该控制器具有较强鲁棒性和自适应能力，控制品质优良。

Simulation Research of an Adaptive CMAC for Hydrogenerating System with AC Excitation

Based on the conventional structure of the cerebellar model articulation controller (CMAC), an adaptive CMAC neural network controller is presented for a class of nonlinear uncertain systems with time-varying parameters. Combining it with the adaptive linear neuron network, the multiplex control strategy takes the dynamic errors and given signals of the system as input signals to the CMAC neural network. The digital simulation of multivariable and nonlinear control for the hydrogenerator system with AC excitation is studied and the conventional PID controller is used to compare with it. The simulation results show that the proposed adaptive CMAC is of good robustness, and adaptive ability and excellent control quality.