[1]朱胜龙,李宾宾,张晨晨,等.隔离断路器金具自动化解接机器人视觉引导定位方法研究[J].高压电器,2020,56(07):205-211.[doi:10.13296/j.1001-1609.hva.2020.07.030]
 ZHU Shenglong,LI Binbin,ZHANG Chenchen,et al.Study on Visual Guidance and Positioning Method of Automatic Make-up and Disassembly Robot of Isolation Circuit Breaker Fittings[J].High Voltage Apparatus,2020,56(07):205-211.[doi:10.13296/j.1001-1609.hva.2020.07.030]
点击复制

隔离断路器金具自动化解接机器人视觉引导定位方法研究()
分享到:

《高压电器》[ISSN:1001-1609/CN:61-11271/TM]

卷:
第56卷
期数:
2020年07期
页码:
205-211
栏目:
技术讨论
出版日期:
2020-07-20

文章信息/Info

Title:
Study on Visual Guidance and Positioning Method of Automatic Make-up and Disassembly Robot of Isolation Circuit Breaker Fittings
作者:
朱胜龙1 李宾宾1 张晨晨1 秦少瑞1 卢山富2 朱徐峰2
(1. 国网安徽省电力有限公司电力科学研究院, 合肥 230601; 2. 浙江清华长三角研究院信息技术研究所, 浙江 嘉兴 314000)
Author(s):
ZHU Shenglong1 LI Binbin1 ZHANG Chenchen1 QIN Shaorui1 LU Shanfu2 ZHU Xufeng2
(1.Anhui Electric Power Research Institute, Hefei 230601, China; 2.Yangtze Delta Region Institute of Tsinghua University, Zhejiang Department of Information Technology, Zhejiang Jiaxing 314000, China)
关键词:
隔离断路器 深度学习 目标检测 机械手 视觉引导定位
Keywords:
isolation circuit breaker deep learning object detection mechanical arm visual guidance and positioning
DOI:
10.13296/j.1001-1609.hva.2020.07.030
摘要:
变电站中主要使用隔离断路器来隔离电压,使待检修设备与带电部分隔离形成安全的操作空间;而目前主要的检修作业方式为人工带电操作,费时费力且具有极高的安全隐患。基于此,文中提出了一种隔离断路器金具自动化解接机器人视觉引导定位方法。该方法由像机实时采集图像数据,利用深度学习目标检测算法进行金具粗定位;并在粗定位的基础上使用图像分割技术精确拟合作业点位置;通过精确的图像坐标点、工具坐标系、机器人本体之间的坐标关系,计算作业点在机器人坐标系下的坐标位置,并控制机械手运动。实验表明,算法具有精度高、稳定性好、速度快等优点。
Abstract:
Isolation circuit breakers are used in power stations to isolate voltages, and isolate the equipment to be repaired from live parts to form a safe operating space. At present, the main method of overhaul is manual operation, which is time-consuming and labor-intensive and has high safety risks. Based on this, our paper proposes a visual guidance and positioning method of automatic make-up and disassembly robot of isolated circuit breaker. Image data is collected in real time through a camera, and rough positioning of the fittings is performed through a deep learning object detection algorithm; based on the relationship between the precise image coordinate points, the tool coordinate system, and the robot body, the coordinate position of the operating point in the robot coordinate system is calculated, and the manipulator movement is controlled. The experimental show that the algorithm has the advantages of high accuracy, good stability and fast speed.

参考文献/References:

[1] 王 艳,陈 芳,尹自力. 隔离断路器在新一代变电站中的应用[J]. 现代工业经济和信息化,2018,8(2):70-72.
WANG Yan, CHEN Fang, YIN Zili. Application of isolated circuit breaker in intelligent substation of new generation[J]. Modern Industrial Economy and Information,2018,8(2):70-72.
[2] 王灿飞,李以然,王军慧,等. 基于隔离开关检修的隔离断路器分析研究[J]. 电工电气,2015(3):32-37.
WANG Canfei, LI Yiran, WANG JunHui,et al. Analysis of disconnecting circuit breakers based on disconnectors overhaul[J]. Electrotechnics Electric,2015(3):32-37.
[3] 张云剑,李世成,王石刚,等. 隔离断路器连接金具装拆机器人视觉定位方法研究[J]. 机电一体化,2017,23(1):3-10.
ZHANG Yunjian,LI Shicheng,WANG Junhui,et al. Research of positioning method for assembling and de-assembling the hardware connected on isolation circuit breaker[J]. Mechatronics,2017,23(1):3-10.
[4] VIOLA P, JONES M. Rapid object detection using a boosted cascade of simple features[C]//IEEE Conference on Computer Vision and Pattern Recognitino.[S.l.]:IEEE,2001:511.
[5] VIOLA P,JONES M J. Robust real-time face detection[J]. International Journal of Computer Vision,2004,57(2):137-154.
[6] DALAL N,TRIGGS B. Histograms of oriented gradients for human detection in computer vision and pattern recognition[C]//2005 IEEE Computer Society Conference on CVPR.[S.l.]:IEEE,2005:886-893.
[7] FELZENSZWALB P,MCALLESTER D,RAMANAN D, A discriminatively trained, multiscale, deformable part model in computer vision and pattern recognition[C]//2008 IEEE Conference on CVPR.[S.l.]: IEEE,2008:1-8.
[8] GIRSHICK R,DONAHUE J,DARRELL T,et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//IEEE Conference on Computer Vision and Pattern Recognition.[S.l.]:IEEE,2014:580- 587.
[9] GIRSHICK R,DONAHUE J,DARRELL T, et al. Regionbased convolutional networks for accurate object detection and segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,38(1):142-158.
[10] HE K, ZHANG X,REN S,et al. Patial pyramid pooling in deep convolutional networks for visual 29 recognition[C]//European Conference on Computer vision.[S.l.]:Springer, 2014:346-361.
[11] GIRSHICK R. Fast-cnn[C]//IEEE International Conference on Computer Vision.[S.l.]:IEEE,2015:1440-1448.
[12] REN S,HE K,GIRSHICK R,et al. Faster r-cnn: Towards real-time object detection with region proposal networks in advances in neural information processing systems.[S.l.]:[s.n.], 2015:91-99.
[13] REDMON J, DIVVALA S, GIRSHICK R,et al. You only look once: Unified, real-time object detection[C]//IEEE Conference on Computer Vision and Pattern Recognition.[S.l.]:IEEE,2016:779-788.
[14] REDMON J,FARHADI A. YOLOv3: An incremental improvement[EB/OL]. 2018-02-07. https://arxiv.org/arxiv:1804.
02767.2018.
[15] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2018,42(2):318-327.
[16] DENG J, DONG W,SOCHER R, et al. A large-scale hierarchical image database[C]//IEEE conference on computer vision and pattern recognition.[S.l.]:[s.n.],2009:248-255.
[17] 朱胜龙,李宾宾,邱欣杰,等. 变电站侧拔式管式金具:CN110635311A[P]. 2019-12-31.
ZHU ShengLong, LI BinBin, QIU XinJie, et al. Substation side-pull pipe fittings:CN110635311A[P]. 2019-12-31.
[18] ZHANG Z Y. Camera calibiration translation[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence,2000,22(11):1330-1334.
[19] GAO X S, HOU X R,TANG J, et al. Complete solution classifition for the perspective-three-point problem[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2003,25(8):930-943.
[20] LEPETIT V, MORENO-NOGUER F, FUA P. An accurate on solution to the pnp problem[J]. International Journal of Compute Vision, 2008,81(3):155-166.

备注/Memo

备注/Memo:
收稿日期:2020-01-06; 修回日期:2020-03-05朱胜龙(1980—),男,硕士,高级工程师,主要从事变电设备专业管理及技术监督工作。 李宾宾(1986—),男,硕士,高级工程师,主要从事高压开关设备状态检修与检测分析工作。 卢山富(1992—),男,硕士,工程师,主要从事计算机视觉、图像处理相关研究工作(通讯作者)。
更新日期/Last Update: 2020-07-25