针对某武器大功率交流伺服系统所存在的大变负载、慢时变、强耦合的非线性特性和不确定扰动等问题，提出了模糊小波神经网络（FWNN）间接自适应控制器，该控制器的特点为Takagi-Sugeno-Kang (TSK)模糊模型的后件部分由自回归小波神经网络（SRWNN）构成。给出了SRWNN参数的迭代算法，利用SRWNN辨识器为控制器提供实时梯度信息，有效地克服了参数变化和负载扰动等不确定因素的影响，且具有良好的动态特性。采用Lyapunov稳定性理论方法证明了闭环系统的稳定性。仿真研究和样机试验结果证明了所提方案的有效性和正确性。
Abstract
A novel indirect stable adaptive fuzzy wavelet neural（FWNN）controller is proposed to control the nonlinearity, wide variation in loads, time-variation and uncertain disturbance of the high power AC servo system in a certain weapon. In the proposed approach, the self-recurrent wavelet neural network (SRWNN) is employed to construct an adaptive self-recurrent consequent part for each fuzzy rule of Takagi-Sugeno-Kang (TSK) fuzzy model. A back-propagation (BP) algorithm offers the real-time gradient information to the adaptive FWNN controller with the aid of an adaptive SRWNN identifier, which overcomes the effects of parameter variations，load disturbances and other uncertainties effectively. It has a good dynamic performance. The stability of the closed loop system is guaranteed by using the Lyapunov method. The simulation result and the prototype test prove that the proposed method is effective and suitable.
关键词
兵器科学与技术 /
大功率交流伺服系统 /
自回归小波神经网络 /
模糊小波神经网络间接自适应控制器 /
模糊小波神经网络
{{custom_keyword}} /
Key words
ordnance science and technology /
high power AC servo system /
self-recurrent wavelet neural network /
indirect stable adaptive fuzzy wavelet neural controller /
fuzzy wavelet neural network
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
［1］ 侯伯杰，李小清，周云飞，等．直线电机伺服系统的复合前馈PID控制[J]. 机床与液压, 2009, 37(2):56-61．
HOU Bo-jie, LI Xiao-qing, ZHOU Yun-fei, et al．The development of feedforward plus PID controller for linear motor[J]. Machine Tool and Hydraulics, 2009, 37(2):56-61．(in Chinese)
[2] BanaeiM R, Kami A. Interline power flow controller (IPFC) based damping recurrent neural network controllers for enhancing stability[J]. Energy Conversion and Management, 2011, 52(7):2629-2636.
[3] MehraeenS, Jagannathan S, Crow M L. Power system stabilization using adaptive neural network-based dynamic surface control[J]. IEEE Transactions on Power Systems, 2011, 26(2):669-680.
[4] MishraS. Neural-network-based adaptive UPFC for improving transient stability performance of power system[J]. IEEE Transactions on Neural Networks, 2006, 17(2):461-470.
[5] YangY, Vilathgamuwa D, Azizur R M. Implementation of an artificial neutral network based. real time adaptive controller for an interior permanent magnet motor drive[J]. IEEE Transactions on Industry Applications, 2003, 39(1):96-104.
[6] RubaaiA, Kotaru R, Kankam M D. Online training of parallel neutral network estimators for control of induction motors[J]. IEEE Transactions on Industrial Application, 2001, 37(5):1512- 1521.
[7] FaaJ L, Wai R J, Hong P C. A PM synchronous servo motor drive with an on-line trained fuzzy neural network controller[J]. IEEE Transactions on Energy Conversion, 1998, 13(4): 319- 325.
[8] ZhangQ H, Benveniste A. Wavelet neural[J]. IEEE Transactions on Neural Networks, 1992, 3(6): 889-989.
[9] YooS J, Park J B, Choi Y H. Indirect adaptive control of nonlinear dynamic systems using self-recurrent wavelet neural networks via adaptive learning rates[J]. Information Sciences, 2007, 177(15): 3074-3098.
[10] HouD, Zhang P A, Xu J. Fuzzy wavelet networks for function learning[J]. IEEE Transactions on Fuzzy Systems, 2001,9(1):200-211.
[11] ZekriM, Sadri S, Sheikholeslam F. Adaptive fuzzy wavelet network control design for nonlinear systems[J]. Fuzzy Sets and Systems, 2008, 159(20):2668-2695.
[12] 郭亚军, 王晓锋, 马大为，等.自适应反演滑模控制在火箭炮交流伺服系统中的应用[J]. 兵工学报, 2011, 32(4): 493- 497.
GUO Ya-jun, WANG Xiao-feng, MA Da-wei, et al. Application of adaptive back-stepping sliding mode control in alternative current servo system of rocket gun [J]. Acta Armamentarii, 2011, 32(4): 493-497. (in Chinese)
[13] KahkeshiM S, Sheikholeslam F, Zekri M. Design of adaptive fuzzy wavelet neural sliding mode controller for uncertain nonlinear systems[J]. ISA Transactions，2013，52(3): 342-350.
[14] RahibH A, Okyay K, Erdal K. A type-2 fuzzy wavelet neural network for system identification and control[J]. Journal of the Franklin Institute，2013，350(7):1658-1685.
[15] GanjefarS，Alizadeh M. Inter-area oscillations damping by multi-objective wavelet neural inverse controlled SSSC[J]. International Review of Electrical Engineering，2012，7(2):4000-4012.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
