【摘要】 由于压电型电液伺服阀的阀芯采用两个对顶压电驱动器驱动,且压电驱动器固有的迟滞非线性,使两压电驱动器的输出具有很强的耦合作用,不能同步,从而使阀芯的运动速度、精度和平稳性降低。采用单纯的PID控制可以在一定程度上实现解耦控制,但其控制精度较低。提出了一种基于DRNN网络整定的PID控制器,它根据DRNN网络辨识的被控对象的Jacobian信息,在线调整PID控制器的比例、积分和微分参数,从而使DRNN网络整定的PID控制器很好地实现了阀芯的解耦同步控制。实验结果表明DRNN网络整定PID控制的综合性能优于常规PID控制。更多还原

【Abstract】 Since the core of the piezoelectric hydroelectric servo valve was driven by two piezoelectric drivers,and the hysteresis and nonlinearity of the piezoelectric driver made the outputs of two piezoelectric drivers have very coupling role and non-synchronization,which would reduce the speed,precision and tranquilization of the valve core.To adopt the common PID controller could realize decoupling control at a certain extent;however,its control precision was very low.So a parameter self-tuning PID controller basing on DRNN was introduced.Basing on the Jacobian information of the control object identified by DRNN,the PID controller adjusted the proportion,integral and differential parameters of PID controller online by network,which made the PID controller adjusted by DRNN realize decoupling control very well in the decoupling control of the valve core.The result of experiment showed that the synthesis performance of the PID controller adjusted by DRNN was better than that of the PID controller.更多还原