针对光伏阵列积灰效应带来的光电转换效率下降问题,依据中国西北地区安装地形特点和清洁作业环境设计一款车载式光伏阵列清洁机器人。清洁机械臂逆运动学分析是末端清洁器轨迹规划的难点,针对解析法求解逆运动学方法复杂且得不到最优解,提出基于BP神经网络求解机械臂逆运动学的方法,建立BP神经网络模型并利用Matlab进行仿真验证。为了提高光伏阵列清洁效率,针对清洁机械臂点到点运动的时间最优问题进行时间最短运动规划。利用五次多项式插值法对机械臂各个关节变量在关节空间坐标系中进行路径拟合,并利用遗传算法对清洁机械臂运动时间进行优化。最终根据优化结果对机械臂进行轨迹规划仿真。结果表明,建立的机械臂运动学模型及使用的BP神经网络求解清洁机械臂逆运动学方法符合清洁机械臂时间最优运动规划,提高了光伏阵列清洁效率,在一定程度上为光伏阵列清洁机器人机械臂提供了时间最优控制规划。
Abstract
Aiming at the problem of photoelectric conversion efficiency decline caused by the ash deposition effect of photovoltaic panels, a vehicle mounted photovoltaic panel cleaning robot is designed according to the installation terrain characteristics and clean working environment in Northwest China. Inverse kinematics analysis of cleaning manipulator is the difficulty problem of trajectory planning of end cleaner. In view of the complexity of analytical method to solve inverse kinematics and the lack of optimal solution, a method based on BP neural network to solve inverse kinematics of cleaning manipulator is proposed. BP neural network model is established and simulated by MATLAB. In order to improve the cleaning efficiency of photovoltaic panels, the shortest time motion planning is carried out for the point-to-point motion time optimization problem of cleaning manipulator. The quintic polynomial interpolation method is used to fit the path of each joint variable of the manipulator in the joint space coordinate system, and the genetic algorithm is used to optimize the motion time of the cleaning manipulator. Finally, according to the optimization results, the trajectory planning of the manipulator is simulated. The results show that the established kinematics model of the manipulator and the BP neural network used to solve the inverse kinematics method of the cleaning manipulator accord with the time optimal motion planning of the cleaning manipulator, which improves the cleaning efficiency of photovoltaic panels, and provides the time optimal control planning for the cleaning robot arm of photovoltaic panels to a certain extent.
关键词
光伏阵列 /
移动机器人 /
逆运动学 /
遗传算法 /
运动规划 /
BP神经网络
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Al-MAAMARY H M S, KAZEM H A, CHAICHAN M T. The impact of oil price fluctuations on common renewable energies in GCC countries[J]. Renewable and sustainable energy reviews, 2017, 75: 989-1007.
[2] MANI M, PILLAI R.Impact of dust on solar photovoltaic (PV) performance: research status, challenges and recommendations[J]. Renewable and sustainable energy reviews, 2010, 14(9): 3124-3131.
[3] LASFAR S, HAIDARA F, MAYOUF C, et al.Study of the influence of dust deposits on photovoltaic solar panels: case of Nouakchott[J]. Energy for sustainable development, 2021, 63: 7-15.
[4] 余操, 许盛之, 姚建曦, 等. 灰尘导致的光伏电站发电损失的对比实验[J]. 太阳能学报, 2022, 43(4): 243-248.
YU C, XU S Z, YAO J X, et al.Comparative experiment on power loss of photovoltaic power station caused by dust[J]. Acta energiae solaris sinica, 2022, 43(4): 243-248.
[5] HASAN A T, ISMAIL N, HAMOUDA A M S, et al. Artificial neural network-based kinematics Jacobian solution for serial manipulator passing through singular configurations[J]. Advances in engineering software, 2010, 41(2): 359-367.
[6] 刘世平, 曹俊峰. 基于BP神经网络的冗余机械臂逆运动学分析[J]. 中国机械工程, 2019, 30(24): 2974-2977, 2985.
LIU S P, CAO J F.Inverse kinematics analysis of redundant manipulator based on BP neural network[J]. China mechanical engineering, 2019, 30(24): 2974-2977, 2985.
[7] 李光, 章晓峰, 杨加超, 等. 基于残差BP神经网络的6自由度机器人视觉标定[J]. 农业机械学报, 2021, 52(4): 366-374.
LI G, ZHANG X F, YANG J C, et al.Vision calibration of 6-DOF robot based on residual BP neural network[J]. Transactions of the Chinese Society for Agricultural Machinery, 2021, 52(4): 366-374.
[8] MONASTERO A, FIORINI P.Target pose computation for nonholonomic mobile manipulators[C]//International Conference on Advanced Robotics, Munich, IEEE, 2009: 1-8.
[9] OSMAN M, MEHREZ M W, YANG S, et al.End-effector stabilization of a 10-DOF mobile manipulator using nonlinear model predictive control[J]. IFAC-papers on line, 2020, 53(2): 9772-9777.
[10] 黄博, 赵建文, 姚玉峰, 等. 面向可避障域的移动操作机运动规划解析方法[J]. 机械工程学报, 2010, 46(15): 8-16.
HUANG B, ZHAO J W, YAO Y F, et al.An analytical method for motion planning of mobile manipulator oriented to obstacle-avoidable domain[J]. Journal of mechanical engineering, 2010, 46(15): 8-16.
[11] 张新荣, 杨江涛, 冯坤鹏. 混凝土湿喷台车机械臂的运动学与动力学研究[J]. 机械设计, 2021, 38(1): 27-33.
ZHANG X R, YANG J T, FENG K P.Research on kinematics and dynamics of concrete wet shotcrete truck manipulator[J]. Journal of machine design, 2021, 38(1): 27-33.
[12] LIU C, CAO G H, QU Y Y, et al.An improved PSO algorithm for time-optimal trajectory planning of Delta robot in intelligent packaging[J]. The international journal of advanced manufacturing technology, 2020, 107(3-4): 1091-1099.
[13] 康代轲, 陈明. 基于改迚混沌搜索算法的机器人轨迹规[J]. 计算机工程与应用, 2017, 53(14): 143-147.
KANG D K, CHEN M.Robot trajectory gage based on chaotic search algorithm at HBS[J]. Computer engineering and applications, 2017, 53(14): 143-147.
[14] 欧新, 周璐, 张鸷, 等. 电能表检验台体串联机械臂时间最优轨迹规划[J]. 计算机工程与应用, 2022, 58(6): 250-255.
OU X, ZHOU L, ZHANG J, et al.Time optimal trajectory planning for power meter test bench serial manipulator[J]. Computer engineering and applications, 2022, 58(6): 250-255.
[15] 宁会峰, 鄢志彬, 李晓, 等. 移动式光伏组件清扫机械臂D-H模型与运动规划[J]. 太阳能学报, 2019, 40(12): 3541-3547.
NING H F, YAN Z B, LI X, et al.D-H model and motion planning of mobile photovoltaic module cleaning manipulator[J]. Acta energiae solaris sinica, 2019, 40(12): 3541-3547
[16] 芮宏斌, 曹伟, 王天赐. 基于改进型自抗扰控制的光伏板清洁机器人路径跟踪控制研究[J]. 机械设计, 2021, 38(S2): 79-83.
RUI H B, CAO W, WANG T C.Research on path tracking control of photovoltaic panel cleaning robot based on improved active disturbance rejection control[J]. Journal of machine design, 2021, 38(S2):79-83.
[17] 蔡自兴. 机器人学[M]. 北京: 清华大学出版社, 2000.
CAI Z X.Robotics[M]. Beijing: Tsinghua University Press, 2000.
[18] 夏炎. 多关节机械臂轨迹规划和轨迹跟踪控制研究[D]. 哈尔滨: 哈尔滨工业大学, 2017.
XIA Y.Research on trajectory planning and trajectory tracking control of multi-joint manipulator[D]. Harbin: Harbin Institute of Technology, 2017.
[19] 孙瑛, 程文韬, 李公法, 等. 关节型机器人轨迹规划算法及轨迹规划研究现状[J]. 长江大学学报(自科版), 2016, 13(28): 32-38, 5.
SUN Y, CHENG W T, LI G F, et al.Research status of trajectory planning algorithm and trajectory planning for articulated robot[J]. Journal of Yangtze University (natural science edition), 2016, 13(28): 32-38, 5.
[20] ZHA X F.Optimal pose trajectory planning for robot manipulators[J]. Mechanism and machine theory,2002, 37(10): 1063-1086.
基金
国家科学自然基金面上项目（51775432）; 陕西省技术创新引导专项（2018ZKC-160）
PDF(2991 KB)
