Aiming at the problems of manual pushing, difficult operation and low work efficiency of loading arm docking, a machine vision-based automatic docking system of LNG land loading arm is designed and studied, including target detection, positioning and control methods for automatic docking in the delimited parking area to realize intelligent docking in unmanned state. The first is to control the joint angle through the servo motor position ring and record the rotation position; Secondly, based on the geometric projection method and the structural characteristics of the loading arm, the kinematics algorithm is simplified to improve the calculation efficiency, and the kinematic model is established by the D-H method, the motion range is calculated and the geometric projection method is verified. Subsequently, object detection is realized based on deep learning and image processing algorithms. Finally, according to the camera internal parameters, multi-point depth information and target detection results obtained by camera’s calibration, three-dimensional vision is realized through the principle of monocular positioning, and finally automatic docking is realized. The test of the flange in the parking area of the vehicle shows that the success rate of the system docking is 99%, and the time is shortened by 40% compared with the manual docking. The automatic docking system of loading arm can be effectively applied to the loading and unloading truck work of the LNG receiving station, and has certain reference value for realizing automatic docking.
CAOliang, WEIYi, YAOSiqin. Machine vision technology and its development and application[J]. China Science and Technology Information, 2008(11): 40-41. (in Chinese)
[3]
NIKU SAEEDB.Introduction to robotics: analysis, control, applications, second edition[M]. 2th ed.Beijing: Publishing House of Electronics Industry, 2013.
ZHUYun, LINGZhigang, ZHANGYuqiang. Research progress and prospect of machine vision technology[J]. Journal of Graphics, 2020, 41(6): 871-890. (in Chinese)
PENGCong, LIUBin, ZHOUQian.Mechanical fault detection based on machine vision and blind source separation[J]. Journal of Shanghai Jiaotong University, 2020, 54(9): 953-960. (in Chinese)
[8]
SHRIVAKSHANG T, CHANDRASEKAC. A comparison of various edge detection techniques used in image processing[J]. International Journal of Computer Science Issues, 2012, 9(1): 269-276.
[9]
MENGC, LIZ, BAIX, et al. Arc adjacency matrix-based fast ellipse detection[J]. IEEE Transactions on Image Processing: a Publication of the IEEE Signal Processing Society, 2020, 29: 4406-4420.
WEIZhenzhong, FENGGuangkun, ZHOUDanya, et al. Review of posture visual measurement methods and applications[J]. Advances in lasers and optoelectronics, 2023, 60(3): 144-176. (in Chinese)