| Intelligent Design |
|
|
|
|
| Research on control of underwater manipulator based on fuzzy RBF neural network |
| YUAN Kai1,2, LIU Yan-jun1,2,3, SUN Jing-yu1,2, LUO Xing3 |
1.Institute of Marine Science and Technology, Shandong University, Qingdao 266237, China
2.Shenzhen Research Institute, Shandong University, Shenzhen 518057, China
3.Key Laboratory of High Efficiency and Clean Mechanical Manufacture， Ministry of Education, Shandong University, Jinan 250061, China |
|
|
|
Abstract Aiming at the problem that the control performance of the manipulator is easily affected in the complex underwater working environment, but the traditional control method is not effective, an intelligent controller based on the fuzzy RBF (radial basis function) neural network method is proposed to control the underwater manipulator precisely and stably. In the water disturbance environment, the manipulator was usually affected by the additional mass, water resistance and buoyancy. The Lagrange method and Morison equation were used to establish a dynamics model of the two-bar manipulator, which included those hydrodynamic terms mentioned above. By using the fuzzy RBF neural network, the hydrodynamics uncertainties in the dynamics equation of the underwater manipulator were identified overall and fitted. With the advantages of heuristic search of fuzzy system and high reasoning speed of RBF neural network, the control performance of underwater manipulator system had better precision and strong adaptability. Considering the hydrodynamic terms, the stability of the underwater manipulator system was proved by using Lyapunov stability theory. Finally, the simulation experiment of trajectory tracking control for a two-bar manipulator was carried out by using MATLAB, and the control effect of fuzzy RBF neural network, conventional RBF neural network identification method and traditional fuzzy control method was compared. The simulation results showed that compared with the conventional RBF neural network identification method, under the control of fuzzy RBF neural network, the response time and relative error of joint 1 of the two-bar manipulator was reduced by 91% and 88%, the response time and relative error of joint 2 was reduced by 92% and 77%; compared with the traditional fuzzy control method, the relative error of joint 1 and joint 2 was reduced by 65% and 10%. The research results show that the control effect of fuzzy RBF neural network is better than that of conventional RBF neural network identification method and traditional fuzzy control, which can provides a high precision and effective control method for the underwater manipulator control.
|
|
Received: 24 June 2019
Published: 28 December 2019
|
|
|
基于模糊RBF神经网络的水下机械臂控制研究
针对水下复杂工作环境下机械臂控制性能易受影响，而传统控制方法效果不佳的问题，提出了一种基于模糊RBF（radial basis function，径向基函数）神经网络的智能控制器，用于精确、稳定地控制水下机械臂。考虑到在水扰动环境下，机械臂通常受到附加质量力、水阻力和浮力的影响，运用拉格朗日法和Morison方程，建立包含水动力项的二杆机械臂动力学模型，通过模糊RBF神经网络对水下机械臂动力学方程中的水动力不确定项进行总体识别并拟合，利用模糊系统启发式搜索和RBF神经网络推理速度较快的优点，使水下机械臂系统具有较高的控制精度和较强的自适应性。考虑到水动力项，采用Lyapunov稳定性理论验证了水下机械臂系统的稳定性。最后利用MATLAB对二杆机械臂进行轨迹跟踪控制仿真实验，并对比模糊RBF神经网络与常规RBF神经网络识别方法和传统模糊控制方法的控制效果。仿真结果表明：与常规RBF神经网络识别方法相比，模糊RBF神经网络控制下二杆机械臂关节1的响应时间缩短了91%，相对误差减小了88%，关节2的响应时间缩短了92%，相对误差降低了77%；与传统模糊控制方法相比，关节1的相对误差减小了65%，关节2的相对误差减小了10%。研究结果表明模糊RBF神经网络的控制效果优于常规RBF神经网络识别方法和传统模糊控制方法，可为水下机械臂的控制提供一种精度较高、较有效的方法。
关键词：
模糊控制,
RBF神经网络,
水下机械臂,
控制特性
|
|
[1] MOHAN Santhakumar, KIM Jinwhan. Indirect adaptive control of an autonomous underwater vehicle-manipulator system for underwater manipulation tasks[J]. Ocean Engineering, 2012, 54(4): 233-243. doi:10.1016/j. oceaneng.2012.07. 022
[2] YUH J. A neural net controller for underwater robotic vehicles[J]. IEEE Journal of Oceanic Engineering, 1990, 15(3): 161-166. doi:10.1109/48.107144
[3] YANG Xu, LIU Hai-tao, XIAO Ju-liang, et al. Continuous friction feedforward sliding mode controller for a Trimule hybrid robot[J]. IEEE/ASME Transactions on Mechatronics, 2018, 23(4): 1673-1683. doi: 10. 1109/TMECH.2018. 2853764
[4] YANG X, ZHU L M, NI Y, et al. Modified robust dynamic control for a diamond parallel robot[J]. IEEE/ASME Transactions on Mechatronics, 2019, 24(3): 959-968. doi:10.1109/TMECH.2019.2914165
[5] 李敏, 王家序, 肖科, 等. 基于模糊RBF神经网络动态摩擦分块补偿的机器人数字鲁棒滑模控制算法[J].中国机械工程,2012,23(23):2792-2796. doi:10.3969/j.issn. 1004-132X.2012.23.005 LI Min, WANG Jia-xu, XIAO Ke, et al. Digital robust sliding mode control of robot manipulator with dynamic friction block compensation using fuzzy RBF neural network[J]. China Mechanical Engineering, 2012, 23(23): 2792-2796.
[6] 袁伟杰, 刘贵杰, 朱绍锋. 基于遗传算法的自治水下机器人水动力参数辨识方法[J].机械工程学报,2010,46(11): 96-100. doi:10.3901/JME.2010.11.096 YUAN Wei-jie, LIU Gui-jie, ZHU Shao-feng. Identification method of hydrodynamic parameters of autonomous underwater vehicle based on genetic algorithm[J]. Journal of Mechanical Engineering, 2010, 46(11): 96-100.
[7] GONG Cheng-long, JIANG Yuan, LU Ke. RBF neural network control based on parameter adjustable CNF for robot manipulators behaviors[C]//Chinese Automation Congress (CAC), Xi'an: IEEE, 2018: 2859-2864.
[8] 肖凡, 李光, 周鑫林. 多连杆机械臂GA-RBF神经网络轨迹跟踪控制[J].机械科学与技术,2018,37(5):669-674. doi:10.13433/j.cnki.1003-8728.2018.0503 XIAO Fan, LI Guang, ZHOU Xin-lin. GA-RBF neural network control for trajectory tracking of multilink robot arm[J]. Mechanical Science and Technology for Aerospace Engineering, 2018, 37(5): 669-674.
[9] 俞建成, 李强, 张艾群， 等. 水下机器人的神经网络自适应控制[J].控制理论与应用,2008,25(1):9-13. doi:10.1038/cgt.2008.5 YU Jian-cheng, LI Qiang, ZHANG Ai-qun, et al. Neural network adaptive control for underwater vehicles[J]. Control Theory & Applications, 2008, 37(5): 669-674.
[10] 余胜威. MATLAB优化算法案例分析与应用[M].北京:清华大学出版社,2014:138-144. YU Sheng-wei. Case analysis and application of MATLAB optimization algorithm[M]. Beijing: Tsinghua University Press, 2014: 138-144.
[11] 刘金琨. 机器人控制系统的设计与MATLAB仿真[M]. 北京:清华大学出版社,2008:27-42. LIU Jin-kun. Robot control system design and MATLAB simulation[M]. Beijing: Tsinghua University Press, 2008: 27-42.
[12] 魏循中. 水下机械手结构设计及动力学研究[D].青岛：中国海洋大学工程学院,2014:44-45. WEI Xun-zhong. Structure design and dynamic research of underwater manipulator[D]. Qingdao: Ocean University of China, School of Engineering, 2014: 44-45.
[13] MORISON J R, JOHNSON J W, SCHAAF S A. The force exerted by surface waves on piles[J]. Journal of Petroleum Technology, 1950, 2(5): 149-154. doi:10.2118/950149-g
[14] 高涵, 张明路, 张小俊, 等. 水下机械手动力学模型及力矩影响研究[J]. 机械设计与制造, 2017 (3): 68-71. doi: 10.3969/j.issn.1001-3997.2017.03.018 GAO Han, ZHANG Ming-lu, ZHANG Xiao-jun, et al. Research on underwater manipulator dynamics model and torque influence[J]. Machinery Design & Manufacture, 2017 (3): 68-71.
[15] 陈萍. 水下机械手阻抗控制技术研究[D].哈尔滨:哈尔滨工程大学机电工程学院,2009:26. CHEN Ping. Research on impedance control of underwater manipulator[D]. Harbin: Harbin Engineering University, College of Mechanical and Electrical Engineering, 2009: 26.
[16] 王华, 孟庆鑫, 王立权. 基于切片理论的水下灵巧手手指动力学分析[J].机器人,2007,29(2):160-166. doi:10.3321/j.issn:1002-0446.2007.02.012 WANG Hua, MENG Qing-xin, WANG Li-quan. Analysis on finger dynamics of dexterous underwater hand based on strip theory [J]. Robot, 2007, 29(2): 160-166.
[17] 李忠秋, 赵春雨, 洪洋, 等. 基于模糊RBF网络补偿的控制输入受限滑模控制[J]. 电子世界,2018(12):8-10. doi: 10.19353/j.cnki.dzsj.2018.12.002 LI Zhong-qiu, ZHAO Chun-yu, HONG Yang, et al. Control of input limited sliding mode based on fuzzy RBF network compensation[J]. Electronics World, 2018(12): 8-10.
[18] WOLF A, SWIFT J B, SWINNEY H L, et al. Determining Lyapunov exponents from a time series[J]. Physica D: Nonlinear Phenomena, 1985, 16(3): 285-317. doi:10.1016/0167-2789(85)90011-9 |
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
| |
Shared |
|
|
|
|
| |
Discussed |
|
|
|
|
