两电机同步系统的神经网络逆控制

以多变量、非线性、强耦合的两电机同步控制系统为研究对象，在同步旋转坐标下，建立了两电机同步系统的数学模型，并进行了可逆性分析．采用静态神经网络加积分器构造两电机同步控制系统的逆系统，将此逆系统与原系统相串联构成复合伪线性系统．即两电机同步系统被线性化且已解耦成速度和张力两个相对独立的系统，速度环为y=s^-1φ（s）型伪线性子系统，张力环为y=s^-2φ（s）型伪线性子系统，再分别设计线性闭环调节器对速度环和张力环进行控制．实验结果证明了采用神经网络逆系统控制方法可以实现两电机同步调速系统的解耦控制．

Neural network inverse control of two-motor synchronous system

The two-motor synchronous system which is a multivariable nonlinear coupling system is stu-(died.)The mathematic model and invertibility are given.By cascading the ANN inverse which consists of a static ANN and an integrator with the two-motor,and by constructing a neural network inversion and combining it with the two-motor synchronous system itself,a pseudo-linear system is completed.The multivariable,nonlinear coupled twomotor system is decoupled into two independent linear subsystems: speed subsystem and tension subsystem.A linear close-loop adjustor is designed to control each of the subsystems.The experiment results show that the twomotor synchronous system is decoupled based on a neural network inverse control.two-motor synchronous system;inverse system control;decoupling control;artificial neural network;tension;speed