神经网络非线性智能控制在光电跟踪系统中的应用

林贻翔

doi:10.3788/OPE.20182612.2949

您当前的位置：

首页 >

文章列表页 >

神经网络非线性智能控制在光电跟踪系统中的应用

微纳技术与精密机械 | 更新时间：2020-07-05

- 神经网络非线性智能控制在光电跟踪系统中的应用
- Application of neural network-based nonlinear intelligent control in electro-optical tracking systems
- 光学精密工程 2018年26卷第12期页码：2949-2955
- 作者机构：
  
  中国电子科技集团公司第十研究所, 四川成都 610036
- 作者简介：
  
  [ "林贻翔(1989-)，男，福建福清人，博士，工程师，2012年、2017年于武汉大学分别获得学士、博士学位，主要从事无线激光通信、光束控制方面的研究工作。E-mail:linix@whu.edu.cn" ]
- 基金信息：
  
  装备预研基金资助项目(41411040101);装备预研基金资助项目(315040303)
- DOI：10.3788/OPE.20182612.2949
  中图分类号： TP18;TP273
- 收稿日期：2018-05-02，
  
  录用日期：2018-7-1，
  
  纸质出版日期：2018-12-25
- 稿件说明：
移动端阅览
林贻翔. 神经网络非线性智能控制在光电跟踪系统中的应用[J]. 光学精密工程, 2018,26(12):2949-2955.

Yi-xiang LIN. Application of neural network-based nonlinear intelligent control in electro-optical tracking systems[J]. Optics and precision engineering, 2018, 26(12): 2949-2955.
林贻翔. 神经网络非线性智能控制在光电跟踪系统中的应用[J]. 光学精密工程, 2018,26(12):2949-2955. DOI： 10.3788/OPE.20182612.2949.

Yi-xiang LIN. Application of neural network-based nonlinear intelligent control in electro-optical tracking systems[J]. Optics and precision engineering, 2018, 26(12): 2949-2955. DOI： 10.3788/OPE.20182612.2949.

摘要

针对伺服系统中非线性力矩干扰导致光束跟踪性能下降的问题，采用神经网络算法实现光电跟踪系统的非线性控制。分析了径向基函数神经网络监督控制算法应用于光电跟踪系统的优势，设计了光束跟踪实验，数据显示神经网络能够智能输出非线性控制量抑制摩擦力矩干扰，提高光束跟踪性能，对幅度3°、频率在1 Hz以内的光束扰动抑制比达到-28~-51 dB，比初始未优化的PID控制提高15 dB以上。实验结果表明，神经网络算法可以自动建立反馈量与控制量的非线性映射，适用于复杂系统的非线性控制。

Abstract

A neural network-based nonlinear intelligent control method was proposed for electro-optical (EO) tracking systems to overcome the performance reduction caused by the complex nonlinearity existent in real systems. A radial basis function neural network supervisory control structure was employed

and the associated advantages and characteristics were expatiated in the proposed study. Furthermore

a tracking experiment was conducted for performance evaluation. The obtained experimental results demonstrate that the disturbance attenuation performance can vary from -28 dB to -51 dB within the disturbance frequency of 1 Hz and amplitude of 3°

which indicates an improvement of 15 dB over the PID control method. The results also indicate that EO tracking technology based on neural network control possesses the advantage of intelligent optimized tracking by learning a system's nonlinear information without human intervention. Hence

compared to conventional tracking algorithms

neural network-based EO tracking technology can be incorporated more effectively in complex application environments.

关键词

Keywords

references

RABINOVICH W S, MOORE C I, MAHON R, et al.. Free-space optical communications research and demonstrations at the U.S. Naval Research Laboratory[J]. Applied Optics, 2015, 54(31):F189-F200.

程龙, 陈娟, 陈茂胜, 等.光电跟踪系统快速捕获时间最优滑模控制技术[J].光学精密工程, 2017, 25(1):148-154.

CHENG L, CHEN J, CHEN M SH, et al.. Fast acquisition of time optimal sliding model control technology for photoelectric tracking system[J]. Opt. Precision Eng., 2017, 25(1):148-154. (in Chinese)

邓永停, 李洪文, 刘京, 等.基于扰动力矩观测器的大口径望远镜低速控制[J].光学精密工程, 2017, 25(10):2636-2644.

DENG Y T, LI H W, LIU J, et al.. Low-speed control of large telescope based on disturbance torque observer[J]. Opt. Precision Eng., 2017, 25(10):2636-2644. (in Chinese)

CONG S, DENG K, SHANG W, et al.. Isolation control for inertially stabilized platform based on nonlinear friction compensation[J]. Nonlinear Dynamics, 2016, 84(3):1123-1133.

崔晶, 王思宇, 楚中毅.高加速度运动系统的非线性摩擦前馈补偿控制[J].光学精密工程, 2018, 26(1):77-85.

CUI J, WANG S Y, CHU ZH Y. Feed-forward compensation control of nonlinear friction for high acceleration motion system[J]. Opt. Precision Eng., 2018, 26(1):77-85. (in Chinese)

郭鹏飞, 邓永停, 王帅.基于摩擦模型的反演滑模控制在大型望远镜上的应用[J].光学精密工程, 2017, 25(10):2620-2626.

GUO P F, DENG Y T, WANG SH. Backstepping sliding mode control of large telescope based on friction model[J]. Opt. Precision Eng., 2017, 25(10):2620-2626. (in Chinese)

HAYKIN S. Neural Networks and Learning Machines[M]. Third Edition. Beijing:China Machine Press, 2011:1-27, 63-68.

李宇, 刘雪莹, 张洪群, 等.基于卷积神经网络的光学遥感图像检索[J].光学精密工程, 2018, 26(1):200-207.

LI Y, LIU X Y, ZHANG H Q, et al.. Optical remote sensing image retrieval based on convolutional networks[J]. Opt. Precision Eng., 2018, 26(1):200-207. (in Chinese)

刘峰, 沈同圣, 马新星, 等.基于多波段深度神经网络的舰船目标识别[J].光学精密工程, 2017, 25(11):2939-2946.

LIU F, SHEN T SH, MA X X, et al.. Ship recognition based on multi-band deep neural network[J]. Opt. Precision Eng., 2017, 25(11):2939-2946. (in Chinese)

HUNT K J, SBARBARO D, ZBIKOWSKI R, et al.. Neural networks for control systems-A survey[J]. Automatica, 1992, 28(6):1083-1112.

刘金琨.先进PID控制MATLAB仿真[M].第3版.北京:电子工业出版社, 2011:301-311.

LIU J K. Advanced PID Control and Matlab Simulation[M]. 3rd edition. Beijing:Publishing House of Electronics Industry, 2011:301-311. (in Chinese)

WANG Y C, CHIEN C J, TENG C C. Direct adaptive iterative learning control of nonlinear systems using an output-recurrent fuzzy neural network[J]. IEEE Transactions on Systems Man & Cybernetics Part B:Cybernetics, 2004, 34(3):1348-1359.

田俊林, 胡晓阳, 游安清.利用自适应卡尔曼滤波实现光电跟踪中的复合控制[J].光学精密工程, 2017, 25(7):1941-1947.

TIAN J L, HU X Y, YOU A Q. Compound control of photoelectric tracking by using adaptive Kalman filtering algorithm[J]. Opt. Precision Eng., 2017, 25(7):1941-1947. (in Chinese)

MARQUES F, FLORES P, CLARO J C P, et al.. A survey and comparison of several friction force models for dynamic analysis of multibody mechanical systems[J]. Nonlinear Dynamics, 2016, 86(3):1407-1443.

LIN Y X, AI Y, SHAN X. Identification of electro-optical tracking systems using genetic algorithms and nonlinear resistance torque[J]. Optical Engineering, 2017, 56(3):033105.

刘金琨. RBF神经网络自适应控制MATLAB仿真[M].北京:清华大学出版社, 2014:15-47.

LIU J K. RBF Neural Network Control for Mechanical Systems Design, Analysis and MATLAB Simulation[M]. Beijing:Tsinghua University press, 2014:15-47. (in Chinese)

姜会林, 佟首峰, 张立中, 等.空间激光通信技术与系统[M].北京:国防工业出版社, 2010:257-277.

JIANG H L, TONG SH F, ZHANG L ZH, et al.. The Technologies and Systems of Space Laser Communication[M]. Beijing:National Defense Industry Press, 2010:257-277. (in Chinese)

浏览量

270

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于圆卷积神经网络的粘连导电粒子检测

面向领域自适应的部分最优传输高光谱图像分类

基于热传导和卷积神经网络的磨床主轴热误差预测

基于刚度预测-神经网络的调姿平台误差补偿

基于平面补丁的自适应八叉树三维图像重建