|本期目录/Table of Contents|

[1]彭煜祺,魏 巍,陈 灯*,等.基于视觉的工业机器人异常动作检测方法研究[J].武汉工程大学学报,2021,43(04):462-467.[doi:10.19843/j.cnki.CN42-1779/TQ.202105013]
 PENG Yuqi,WEI Wei,CHEN Deng*,et al.Vision-Based Fault Action Detection of Industrial Robot[J].Journal of Wuhan Institute of Technology,2021,43(04):462-467.[doi:10.19843/j.cnki.CN42-1779/TQ.202105013]
点击复制

基于视觉的工业机器人异常动作检测方法研究(/HTML)
分享到:

《武汉工程大学学报》[ISSN:1674-2869/CN:42-1779/TQ]

卷:
43
期数:
2021年04期
页码:
462-467
栏目:
机电与信息工程
出版日期:
2021-08-31

文章信息/Info

Title:
Vision-Based Fault Action Detection of Industrial Robot
文章编号:
1674 - 2869(2021)04 - 0462 - 06
作者:
彭煜祺1魏 巍1陈 灯*12杨艺晨1 张典典1彭 丽3
1. 智能机器人湖北省重点实验室(武汉工程大学),湖北 武汉 430205;2. 凌云科技集团有限公司,湖北 武汉 430040;3. 湖北广播电视大学,湖北 武汉 430073
Author(s):
PENG Yuqi1WEI Wei1CHEN Deng*12 YANG Yichen1 ZHANG Diandian1 PENG Li3
1. Hubei Key Laboratory of Intelligent Robot(Wuhan?Institute?of?Technology), Wuhan 430205, China;2. Lingyun Science & Technology Group Co. Ltd, Wuhan 430040,China;3. Hubei Radio & TV University, Wuhan 430073, China
关键词:
工业机器人故障动作检测图像分割图像哈希机器人安全
Keywords:
industrial robot fault action detection image segmentation image hashing robot security
分类号:
TP242.2
DOI:
10.19843/j.cnki.CN42-1779/TQ.202105013
文献标志码:
A
摘要:
工业机器人的突发故障引发的安全问题时有发生。传统的基于数据分析的故障诊断方法存在传感器数据易受干扰,机器人通讯协议不统一,监测系统嵌入在执行系统内部相互影响等问题。提出一种基于机器视觉的工业机器人故障动作检测方法。对工业机器人作业视频进行实时分析,采用图像分割技术分离工业机器人本体并采用图像哈希技术生成工业机器人姿态编码,结合序列模式分析技术检测工业机器人异常动作并进行预警。不依赖于工业机器人通讯协议,以非接触式的方式对工业机器人进行实时监控,具有易于部署和成本低的特点。基于自主构建的工业机器人仿真视频数据集进行了实验研究,结果表明提出的方法可准确识别工业机器人异常动作,精确率和召回率均为100%。
Abstract:
Security problems caused by sudden failures of industrial robots frequently occur. Traditional fault detection methods of industrial robots are mainly based on data analysis techniques which have many limitations: 1) the data received from sensors may be interfered by the external environment;2) industrial robots do not have a unified communication protocol, which increases the cost of collecting sensor data;3) the embedded monitoring component may affect the running of industrial robots. This paper proposes a vision-based detection method of fault actions for industrial robots. The method analyzes the working video of industrial robots and detects fault actions caused by robot failures. Firstly, the image segmentation technique was used to divide industrial robots from the background. Then the posture of robots was encoded into hash codes. Finally, fault actions of robots were detected from the sequence of hash codes of robot postures. The method does not depend on the communication protocols of industrial robots, and can monitor industrial robots in a non-contact way, which is easy to deploy and has a low cost for use. Based on the self-constructed video data set for industrial robots, experiments were conducted. Experimental results show that the proposed method can accurately identify the fault actions of industrial robots. Both the accuracy rate and the recall rate are 100%.

参考文献/References:

[1] 董凯. 2020-2026年中国工业机器人行业现状调研分析与发展趋势预测报告[R]. 北京:智研咨询集团,2019.[2] 汪杰. 2019中国工业机器人市场现状及发展展望[J]. 智慧工厂,2019 (12):30-31.[3] GUIZZO E , ACKERMAN E . When robots decide to kill [J]. IEEE Spectrum, 2016, 53(6):38-43.[4] 蔡博. 基于数据分析的控制系统传感器故障诊断方法研究[D].保定:华北电力大学,2018.[5] 曾祥丹. 工业机器人故障诊断技术的发展趋势[J]. 科技风, 2017(8):10-15.[6] 赵亮. 工业机器人故障诊断方法发展现状及发展方向[J]. 河南科技, 2020, 39(28):41-43.[7] 洪英汉, 余梓民, 罗海城,等. 工业机器人远程故障监测与预警系统[J]. 科技视界, 2017(20):65-66.[8] 郑旭,李亚光,邱辉,等. 工业机器人故障分析及可靠性测试的必要性[J]. 中国仪器仪表,2019(10):19-23.[9] KE J, CHEN X J, CHEN B D, et al. Complex event detection in video streams[J].Service-Oriented System Engineering, 2016(1):172-179.[10] KAUT H, SINGH R. A Review on image segmentation techniques for future research study[J]. International Journal of Engineering Trends and Technology, 2016, 35(11):504-505.[11] TAMMA N A, CHAUDHARY A . Digital signature scheme for image[J].Digital Signature Scheme for Image,2017,3(2):312-328.[12] 童苗苗. 图像哈希算法研究及实现[D]. 济南:山东师范大学,2017.[13] 刘根平. 基于哈希技术的时间序列近似查询研究[D].宁波:宁波大学,2015.[14] KHAVARE S A ,MANJREKAR A A . Robust image hashing algorithm for detecting and localizing image tamper in small region[C]// International Conference on Information Processing.Pune:IEEE, 2016:289-294.[15] WANG F, LYU W L, PAN J S. A robust image authentication scheme with self-repair capability for grayscale source document images via PNG format[J]. Iet Image Processing, 2017, 10(12):971-978.[16] GHARDE N D, THOUNAOJAM D M, SONI B, et al. Robust perceptual image hashing using fuzzy color histogram[J]. Multimedia Tools & Applications, 2018, 77(23):1-26.[17] HUA C J, MA J, CHEN Y, et al. Improved non-local mean denoising algorithm based on difference hash algorithm[J]. Laser & Optoelectronics Progress, 2020,57(14): 141-147.[18] HAN B, LI J. A new zero-watermarking algorithm resisting attacks based on differences hashing[J]. Cybernetics & Information Technologies, 2016, 16(2):135-147.[19] WANG D Z, LIANG J Y. Research and design of theme image crawler based on difference hash algorithm[C]//2019 Advanced Electronic Materials, Computer and Materials Engineering.Changsha:IEEE,2019:563042080.[20] HAN B R, LI J B, LI Y J, et al. Zerowatermarking algorithm for medical volume data based on difference hashing[J]. International Journal of Computers, Communications & Control,2015,10(2): 188-199.

相似文献/References:

[1]林少丹1,傅高升2,李俊达2.磨抛离线编程中修正砂带位姿及加工姿态[J].武汉工程大学学报,2015,37(09):50.[doi:10. 3969/j. issn. 1674-2869. 2015. 09. 009]
 ,Modification of belt position and processing posture in off-line programming of grinding and polishing[J].Journal of Wuhan Institute of Technology,2015,37(04):50.[doi:10. 3969/j. issn. 1674-2869. 2015. 09. 009]

备注/Memo

备注/Memo:
收稿日期:2021-05-13?基金项目:国家自然科学基金(61803286、61771353);湖北省技术创新专项(2019AA045);湖北省教育科学规划课题(2019GA090);湖北省中华职教社调研课题(HBZJ2020016)作者简介:彭煜祺,硕士研究生。E-mail:1807133826@qq.com*通讯作者:陈 灯,博士,副教授。E-mail:dchen@wit.edu.cn 引文格式:彭煜祺,魏巍,陈灯,等. 基于视觉的工业机器人异常动作检测方法研究[J]. 武汉工程大学学报,2021,43(4):462-467.
更新日期/Last Update: 2021-08-07