控制力矩陀螺框架伺服系统神经网络控制  

Neural Network Control for Control Moment Gyroscope Gimbal Servo System

作　　者：吴琛浩 岳继光[1] 何洪志 苏永清[1] 张激扬[2] 鲁明[2] 赵雷[2] WU Chen-hao;YUE Ji-guang;HE Hong-zhi;SU Yong-qing;ZHANG Ji-yang;LU Ming;ZHAO Lei(College of Electronic and Information Engineering,Tongji University Shanghai 201804,China;Beijing Institute of Control Engineering,Beijing 100190,China)

机构地区：[1]同济大学电子与信息工程学院,上海201804 [2]北京控制工程研究所,北京100190

出　　处：《控制工程》2021年第12期2371-2378,共8页Control Engineering of China

基　　金：国家重点研发计划项目(2018YFB1700902);中国空间技术研究院CAST创新基金资助项目(2018CAST22)。

摘　　要：控制力矩陀螺(control moment gyroscope,CMG)框架伺服系统对柔性机座抑制能力的不足,限制了其控制精度和鲁棒性的进一步提高。通过结合工程实践,基于CMG框架伺服系统的强耦合、非线性特性,推导了传递函数,实现了解耦和降阶。在此基础上提出了一种基于反向传播(backpropagation,BP)神经网络的比例积分微分(proportional-integral-derivative,PID)控制方法,将其应用于CMG框架伺服系统的控制方案,该方案引入了柔性基座的影响。最后,将所提控制系统与传统PID控制器构成的CMG框架伺服控制系统进行仿真实验对比。对比结果表明,BP神经网络PID控制系统可以显著提高系统的各项性能,并且有效抑制扰动力矩的影响,保持较高输出精度,具有强鲁棒性。The insufficient inhibiting ability to the flexible foundation limits the further improvement in control accuracy and robustness of the control moment gyroscope(CMG)gimbal servo system.On the basis of engineering practice,considering the strong coupling and nonlinear characteristics of the CMG gimbal servo system,the transfer function is deduced to realize decoupling and order-reduction.Then,a proportionalintegral-derivative(PID)control method based on the back propagation(BP)neural network is proposed and applied to the control scheme of the CMG gimbal servo system.The control scheme also considers the influence of flexible foundation on the CMG gimbal servo system.Finally,the proposed control system is compared with the CMG gimbal servo control system composed of the traditional PID controller.The comparison results show that the BP neural network PID control system can significantly improve the performance of the CMG gimbal servo system,effectively suppress the influence of disturbance torque,maintain high output accuracy,and has strong robustness.

关 键 词：控制力矩陀螺 非线性系统 PID控制 神经网络控制 鲁棒性 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]