基于模糊神经解耦控制的双馈水轮发电机系统仿真

双馈水轮发电机系统是一个涉及水力、水轮机和发电机的综合复杂系统。针对系统具有多变量、非线性、强耦合和参数不确定性的特点，本文提出了一种两级串联结构的自适应模糊神经网络解耦控制策略，前级为基于智能权函数规则的自调整模糊控制器，后级为基于动态耦合特性的自适应神经网络解耦控制器，并从理论上证明了学习算法的收敛性。为了验证所提出控制策略的有效性和正确性，本文对双馈水轮发电机系统在水力、水轮机和发电机参数变化时的鲁棒性分别进行了仿真研究。与常规PID控制的仿真结果比较表明，提出的解耦控制策略能较好地克服参数变化和对象模型结构变化对运行性能的影响，具有鲁棒性好，解耦能力强的优点。

Simulation of doubly fed hydrogenerator system based on fuzzy neural network decoupling control

Doubly fed hydrogenerator system is a synthetical complex system which is made up of water, hydroturbine, generator and controllers. Due to the features of hydrogeneration system with multivariable nonlinear and strong coupling as well as uncertain parameters, a cascade-connected self-adaptive fuzzy neural network decoupling control strategy is proposed in this paper. The former is a self-tuning fuzzy controller by using the intelligent weight function rulers, the latter is a self-adaptive neural network decoupling controller based on the learning algorithm of dynamical coupling characteristic. In addition, the convergence of the network weight learning algorithm is derived by Lyapunov stability theory. The effectiveness and correctness of the presented control strategy is demonstrated under the uncertainty of water, turbine and generator parameters, the robustness .performances of hydrogeneration system are simulated by Matlab/Simulink. Comparing with the conventional PID control, the results have shown that the proposed control strategy is of good robustness, decoupling ability against the variation of model structure and parameters.