Adaptive Control Based on RBF Neural Network for Electro-optical System

doi:10.12382/bgxb.2021.0117

Abstract

Abstract: For improving the tracking accuracy，the servo control algorithm is optimized to enhance the control accuracy and rapidity of control system after hardware design and system integration. A tracking error model is proposed theoretically. According to the proposed model，the numerical computation is implemented. The result illustrates that the control algorithm plays an important role in controlling the tracking errors of electro-optical system. The radial basis function (RBF) algorithm is employed here to adaptively adjust the control system parameters for improving tracking accuracy and robustness. Both the theoretical analysis and hardware-in-the-loop simulation are practiced to verify the availability of the proposed method. It is proved that the proposed method can achieve less than 28 ms delay and lower than 4% attenuation within 3 Hz bandwidth.

Key words: electro-opticalsystem, neuralnetwork, radialbasisfunction, trackingaccuracy, adaptivecontrol

CLC Number:

TP29

ZHANG Tongtong, JIANG Huhai, YUE Wei, SI Chen, YUAN Man. Adaptive Control Based on RBF Neural Network for Electro-optical System[J]. Acta Armamentarii, 2022, 43(3): 556-564.

References

［1］谢瑞宏.机载光电平台伺服系统稳定与跟踪控制技术的研究[D].长春:中国科学院长春光学精密机械与物理研究所，2017:1-8.
XIE R H.The research on stabilization and tracking control techniques of airborne electro-optcal platform servo system[D].Changchun:Changchun Institute of Optics，Fine Mechanics and Physics，Chinese Academy of Sciences，2017:1-8.(in Chinese)
[2］薛珊，孟宪宇，赵运来，等.基于轻量化的舰载雷达稳定平台的设计与特性分析研究[J].制造业自动化，2016，38(10):133-138．
XUE S，MENG X Y，ZHAO Y L，et al.Design and characteristics analysis of shipborne radar stabilized platform based on lightweight[J]. Manufacturing Automation，2016，38(10):133-138.(in Chinese)
[3］黎志强.精密光电稳定平台参数辨识与摩擦补偿控制问题研究[D].长沙:国防科学技术大学，2013:25-27.
LI Z Q.Study on the issues of parameter identification and friction compensation control for precise electro-optical stabilized platforms[D].Changsha:National University of Defense Technology，2013:25-27.(in Chinese)
[4］刘玲玲.PID参数整定技术的研究及应用[D].郑州：郑州大学，2010.
LIU L L.Study and application of the PID parameter tuning technology[D].Zhengzhou:Zhengzhou University，2010.(in Chinese)
[5］ HE W，YAN Z C，SUN Y K，et al. Neural-learning-based control for a constrained robotic manipulator with flexible joints[J].IEEE Transactions on Neural Networks and Learning Systems，2018，29(12): 5993-6003.
[6］ VPHAM C V，WANG Y N.Robust adaptive trajectory tracking sliding mode control based on neural networks for cleaning and detecting robot manipulators[J].Journal of Intelligent & Robotic Systems，2015，79(1):101-114.
[7］ RAHMANI B，BELKHEIRI M.Adaptive neural network output feedback control for flexible multi-link robotic manipulators[J].International Journal of Control，2018，92(10): 2324-2338.
[8］韩宇萌，贾晓洪，王炜强，等.基于BP神经网络的捷联导引头控制系统设计[J].测控技术，2016，35(10):70-74.
HAN Y M，JIA X H，WANG W Q，et al. Control system design based on BP neural network for strap-down seeker[J].Measurement and Control Technology，2016，35(10):70-74. (in Chinese)
[9］殷建国，吕宝林，张继红.基于遗传算法的智能PID系统设计和分析[J].设备管理与维修，2020(10):38-39.
YIN J G，L B L，ZHANG J H.Design and analysis of intelligent PID system based on genetic algorithm [J].Equipment Management Engineering，2020(10):38-39. (in Chinese)
[10］钟山，董云峰. 基于机器学习的卫星姿态控制律设计[J]. 航天控制，2011，29(4):61-65.
ZHONG S，DONG Y F.The design of satellite attitude control law based on machine learning[J].Aerospace Control，2011，29(4):61-65.(in Chinese)
[11］闫锋，张延风，韦悠，等.一种基于神经网络的电机控制算法[J].弹箭与制导学报，2020，40(6):116-118，124.
YAN F，ZHANG Y F，WEI Y，et al.A Motor control algorithm based on neural network[J].Journal of Projectiles，Rockets，Missiles and Guidance，2020，40(6): 116-118，124.(in Chinese)
[12］王春阳，赵尚起，史红伟，等.机载光电稳瞄平台的线性自抗扰控制[J].红外与激光工程，2019，48(12)：248-254.
WANG C Y，ZHAO S Q，SHI H W，et al.Linear active disturbance rejection control of airborne photoelectric stabilized platform[J].Infrared and Laser Engineering，2019，48(12): 248-254. (in Chinese)
[13］徐田荣.运动平台光电跟踪系统的前馈控制技术研究[D].北京：中国科学院光电技术研究所，2020.
XU T R.Research on feedforward control for electro-optical tracking system on moving platform[D].Beijing：Institute of Optics and Electronics，Chinese Academy of Sciences，2020. (in Chinese)
[14］吕明明，刘荣忠，侯远龙，等.一种光电跟踪平台共轴控制的目标运动滤波方法[J].兵工学报，2019，40(3): 549-554.
L M M，LIU R Z，HOU Y L，et al.A target motion filtering method for on-axis control of electro-optical tracking platform[J].Acta Armamentarii，2019，40(3):549-554.(in Chinese)
[15］费业泰.误差理论与数据处理[M].北京:机械工业出版社，2017.
FEI Y T.Error theory and data processing[M].Beijing: China Machine Press，2017. (in Chinese)
[16］贾晓洪，韩宇萌，王炜强.基于RBF神经网络的滚仰式导引头控制系统设计[J].兵器装备工程学报，2016，37(8):1-5.
JIA X H，HAN Y M，WANG W Q. Control system design based on RBF neural network for roll-pitch seeker[J].Journal of Ordnance Equipment Engineering，2016，37(8):1-5.(in Chinese)
[17］罗绍华.基于RBF网络逼近的机器人自适应动态面控制方法研究[D].重庆：重庆大学，2013.
LUO S H.Study on robot adaptive dynamics surface control method based on the RBF network approximation[D].Chongqing：Chongqing University，2013.(in Chinese)
[18］冷鹏飞，徐朝阳.一种深度强化学习的雷达辐射源个体识别方法[J］.兵工学报，2018，39(12):2421-2426.
LENG P F，XU C Y.Specific emitter identification based on deep reinforcement learning[J].Acta Armamentarii，2018，39(12): 2421-2426. (in Chinese)
[19］周志华.机器学习[M].北京:清华大学出版社，2016.
ZHOU Z H.Machine learning[M].Beijing:Tsinghua University Press，2016.(in Chinese)
[20］王世峰，都凯悦，孟颖，等.基于机器学习的车辆路面类型识别技术研究[J].兵工学报，2017，38(8): 1642-1648.
WANG S F，DU K Y，MENG Y，et al.Machine learning-based road terrain recognition for land vehicles[J]. Acta Armamentarii，2017，38(8):1642-1648. (in Chinese)
[21］ KECHAGIAS S O，AOUF N，RICHARDSON M A.3D automatic target recognition for future LIDAR missiles[J].IEEE Transactions on Aerospace and Electronic Systems，2017，52(6): 2662-2675．
[22］ KIM S.Infrared variation reduction by simultaneous background suppression and target contrast enhancement for deep convolutional neural network-based automatic target recognition[J]. Optical Engineering，2017，56(6):063108．
[23］刘凌，李志成，张莹.面向双关节机械臂的参数可调RBF神经网络控制[J].西安交通大学学报，2021，55(4):1-7.
LIU L，LI Z C，ZHANG Y.A RBF neural network control method with adjustable parameters for 2-joint robot manipulators[J].Journal of Xi'an Jiaotong University，2021，55(4): 1-7.(in Chinese)

[1]	CUI Lingfei， GUO Yonghong， XIU Quanfa， SHI Chao， ZHANG Shuoyang. UAV Detection Method Based on Domestic Embedded Intelligent Computing Platform [J]. Acta Armamentarii, 2022, 43(S1): 146-154.
[2]	LI Liangfu， CHEN Weidong， GAO Qiang， XU Kailuan， LIU Xuan， HE Xi， QIAN Jun. Deep Learning-based Intelligent Target Recognition Technology for Electro-optical System [J]. Acta Armamentarii, 2022, 43(S1): 162-168.
[3]	LI Bin， XIE Xin， TANG Wenyong， TAO Jiangping， SUN Yiqiang， ZHAHG Hui. Analysis of Structural Performance of Composite Duct Supporting Structure Based on Approximate Model [J]. Acta Armamentarii, 2022, 43(6): 1435-1446.
[4]	WU Zeliang， YE Jianchuan， WANG Jiang， JIN Ren. Parameter Dimensionality Reduction and Optimal Design of Aircraft Airfoil Based on Deep Autoencoder Neural Network [J]. Acta Armamentarii, 2022, 43(6): 1326-1336.
[5]	XIN Dajun， XUE Kun. Artificial Neural Network-based Prediction Model for the Air Drag Coefficient of Non-spherical Fragments [J]. Acta Armamentarii, 2022, 43(5): 1083-1092.
[6]	LI Mingjun， JIANG Yi， MA Liqi， PAN Xiao. The Prediction Method Based on Neural Network Algorithm for the Bearing Capacity of Launching Site [J]. Acta Armamentarii, 2022, 43(5): 982-991.
[7]	YUAN Hang， LUO Ying， LI Kaiming， CHEN Yijun， ZHANG Qun. Fine Recognition of Human Gait with Vortex Electromagnetic Wave Radar [J]. Acta Armamentarii, 2022, 43(5): 1167-1174.
[8]	LIU Yue, LIU Tielin, JIANG Xiangzheng, HAN Yueming. Health Evaluation of Missile Control System based on RBF and SOM [J]. Acta Armamentarii, 2022, 43(4): 931-939.
[9]	ZHOU Ying， XIE Zhenping， JIANG Xiaojun. Simulation Design of Camouflage Target Concealing Strategy Based on Evolutionary Computation [J]. Acta Armamentarii, 2021, 42(9): 1987-1997.
[10]	LI Heng, YE Zukun, ZHA Wenbin, WANG Yulin. Tool Wear Online Monitoring Based on Multi-sensor Information Decision-making Level Fusion [J]. Acta Armamentarii, 2021, 42(9): 2024-2031.
[11]	PU Yunwei， LIU Taotao， GUO Jiang， WU Haixiao. Radar Emitter Signal Recognition Based on Convolutional Neural Network and Coordinate Transformation of AmbiguityFunction Main Ridge [J]. Acta Armamentarii, 2021, 42(8): 1680-1689.
[12]	WANG Huidong， ZHOU Laihong. Design of A Backstepping Integral Adaptive Controller for Quadrotor UAV [J]. Acta Armamentarii, 2021, 42(6): 1283-1289.
[13]	YUE Bin, MA Wen, HU Weijun. Adaptive Fault-tolerant Control of Hypersonic Vehicles [J]. Acta Armamentarii, 2021, 42(3): 521-529.
[14]	LIU Bingyan， YE Xiongbing， YUE Zhihong， DONG Xianzhou， ZHANG Qiyang. Continuous Space Pursuit-evasion Game Algorithm Based on Multi-group Deep Q Network [J]. Acta Armamentarii, 2021, 42(3): 663-672.
[15]	MA Yuehong， KONG Mengyao. A Lightweight Target Detection Algorithm Based on the Improved Faster-RCNN [J]. Acta Armamentarii, 2021, 42(12): 2664-2674.