基于自适应RBF模糊神经网络的旋转柔性铰接梁的振动控制

PDF(2755 KB)

振动与冲击 ›› 2016, Vol. 35 ›› Issue (7) : 89-95.

论文

邱志成，许燕飞

作者信息 +

Vibration control of a Rotating Two-connected Flexible Beam using RBF-based self-adaptive fuzzy neural network

Qiu Zhi-cheng, Xu Yan-fei

Author information +

文章历史 +

摘要

由柔性关节连接中心刚体和挠性附件的刚柔耦合系统广泛应用于卫星太阳能帆板、空间机器人等领域中，在调姿或者外部扰动带来振动时，将影响系统的稳定性和指向精度，对带有铰接结构的柔性梁的影响更甚。设计并建立了带有柔性关节（谐波齿轮）的旋转柔性铰接梁实验平台，进行了基于压电传感器测量信号的振动频响特性分析，分别采用PD控制和自适应RBF模糊神经网络控制算法，进行了基于电机驱动的位置设定点弯曲振动的主动控制研究。实验比较结果验证设计的自适应RBF模糊神经网络控制算法能够快速抑制振动。

Abstract

The coupled rigid and flexible system that connects rigid hub and flexible attachment through flexible joint is widely applied in areas like satellite solar panels and space robot. The vibration generating by slewing and external disturbance excitation will affect the stability and pointing accuracy of the system, while more vulnerable to flexible structure with connected parts. Experimental setup of the rotating two-connected flexible beam is designed and built up, and vibration frequency response feature analysis based on piezoelectric sensor signal is conducted. The PD algorithm and proposed RBF-based self-adaptive fuzzy neural network algorithm are applied to AC servo motor actuator for conducting the set-point active vibration control experiments. Experimental results show that vibrations are significantly suppressed when applying the proposed RBF-based self-adaptive fuzzy neural network algorithm.

导出引用

邱志成，许燕飞. 基于自适应RBF模糊神经网络的旋转柔性铰接梁的振动控制[J]. 振动与冲击, 2016, 35(7): 89-95

Qiu Zhi-cheng, Xu Yan-fei. Vibration control of a Rotating Two-connected Flexible Beam using RBF-based self-adaptive fuzzy neural network[J]. Journal of Vibration and Shock, 2016, 35(7): 89-95

参考文献

[1] Sabatini M, Gasbarri P, Monti R, et al. Vibration control of a flexible space manipulator during on orbit operations [J]. Acta Astronautica, 2012, 73(109-21.
[2] Dwivedy S K, Eberhard P. Dynamic analysis of flexible manipulators, a literature review [J]. Mechanism and Machine Theory, 2006, 41(7): 749-77.
[3] Shin H C, Choi S B. Position control of a two-link flexible manipulator featuring piezoelectric actuators and sensors [J]. Mechatronics, 2001, 11(6): 707-29.
[4] Hassan M, Dubay R, Li C, et al. Active vibration control of a flexible one-link manipulator using a multivariable predictive controller [J]. Mechatronics, 2007, 17(6): 311-23.
[5] Farmanbordar A, Hoseini S M. Neural Network Adaptive Output Feedback Control of Flexible Link Manipulators [J]. Journal of Dynamic Systems, Measurement, and Control, 2012, 135(2): 021009.
[6] Kwak M, Sciulli D. Fuzzy-logic based vibration suppression control experiments on active structures [J]. Journal of Sound and Vibration, 1996, 191(1): 15-28.
[7] Zhao J, Wu J, Yan S, et al. Dynamic modeling and motion precision analysis of spacecraft manipulator with harmonic drive considering the alternate thermal field in orbit [J]. Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering, 2014, 229(1): 135-48.
[8] Jang J-S, Sun C-T. Functional equivalence between radial basis function networks and fuzzy inference systems [J]. Neural Networks, IEEE Transactions on, 1993, 4(1): 156-9.
[9] El-Sousy F F M. Adaptive hybrid control system using a recurrent RBFN-based self-evolving fuzzy-neural-network for PMSM servo drives [J]. Applied Soft Computing, 2014, 21(509-32.
[10] Lu H-C, Chang M-H, Tsai C-H. Parameter estimation of fuzzy neural network controller based on a modified differential evolution [J]. Neurocomputing, 2012, 89(178-92.
[11] Hsu C-F, Lin C-M, Yeh R-G. Supervisory adaptive dynamic RBF-based neural-fuzzy control system design for unknown nonlinear systems [J]. Applied Soft Computing, 2013, 13(4): 1620-6.
[12] 孙海蓉. 模糊神经网络的研究及其应用 [D]: 华北电力大学（河北），2006
[13] Jain A, Nandakumar K, Ross A. Score normalization in multimodal biometric systems [J]. Pattern recognition, 2005, 38(12): 2270-85.