基于GA-RBF神经网络逆的两电机同步控制

Synchronous Control of Two-Motor Based on GA-RBF Neural Network Inverse

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,提出了基于遗传算法的径向基函数(GA-RBF)神经网络逆的两电机同步控制方法。根据给定的性能指标,采用遗传算法对RBF神经中心进行优化,在此基础上串联RBF神经网络逆与两电机系统,构建复合伪线性系统。这一复杂控制对象即可解耦成转速与张力两个线性子系统,进而通过设计线性闭环调节器实现了解耦控制。实验结果表明,采用GA-RBF神经网络逆的两电机系统,对速度和张力实现了较好的解耦控制,且具有较强的抗干扰能力。

As a multi-variable, nonlinear and strongly coupled research object, a two-motor synchronous control sys- tem was investigated in this paper. A new synchronous control strategy for two-motor system was proposed based on RBF neural network inverse with genetic algorithm. To enhance the system performance, the genetic algorithm was adopted to opti- mize the RBF nerve center,an optimized RBF neural network inverse and a two-motor system was connected in series to form composite preudo-linear system. This two-motor synchronous system can be decoupled into two independent linear subsystems, e. g. , speed and tention types. Moreover, a linear closed-loop adjustor was designed to control each subsystem. The experimental results show that the two-motor synchronous system can be decoupled well for speed and tension based on a GA-RBF neural network inverse system. Also ,the proposed system can deal with external disturbances with strong robustness.