基于视觉传感器的移动焊接机器人测控系统  

A measurement and control system of welding mobile robot based on vision sensor

作　　者：李慨[1] 张庭[1] 

机构地区：[1]河北工业大学机器人及自动化研究所,天津300130

出　　处：《中南大学学报（自然科学版）》2011年第4期1050-1055,共6页Journal of Central South University:Science and Technology

基　　金：河北省教育厅科学研究计划项目(2007309);国家高技术研究发展计划("863"计划)项目(2007AA04Z209);国家反恐科技专项基金资助项目(2005FK230002)

摘　　要：设计焊枪侧置的轮式移动焊接机器人并搭建基于虚拟仪器的移动焊接机器人测控系统。在分析移动焊接机器人特点的基础上,设计由PC,NI-PCI7344,NI-DAQ6015以及图像采集卡等组成的硬件系统结构,采用LabVIEW编程平台编制测控系统软件。设计自适应模糊控制器和高斯基模糊神经网络控制器对十字滑块和车轮进行协调控制。采用高斯函数作为模糊神经网络的隶属函数,利用BP算法实现模糊隶属函数和控制规则的在线修改。实验结果表明：该测控系统运行稳定可靠,其跟踪精度可始终控制在-0.4~0.4 mm以内,满足实际焊接工程的需要。A prototype of mobile welding robot with welding torch positioned at one side of welding robot was developed,and a virtual instrument based measurement and control system for mobile welding robot was presented.By analyzing the characteristics of mobile welding robot,the hardware framework including PC,NI-PCI7344,NI-DAQ6015 and image capture card was designed.The software framework of measurement and control system was put forward based on LabVIEW.Adaptive fuzzy controller and fuzzy-gaussian neural network controller were designed to complete coordinately controlling of cross-slider and wheels,and exactly welding seam tracking was realized by use of the controller.The fuzzy-neural control algorithm was described by applying a Gaussia function as an activation function.A BP rule was used so that membership function would be tuned in real time by applying the FGNN controller.The results show that the measurement and control system is effective,and the proposed controller has excellent tracing accuracy（within-0.4—0.4 mm）,and can satisfy the requirement of practical welding project.

关 键 词：移动焊接机器人 焊缝跟踪 高斯基模糊神经网络 模糊控制 

分 类 号：TP24[自动化与计算机技术—检测技术与自动化装置]