Autonomous seam acquisition and tracking system for multi-pass welding based on vision sensor

Automatic welding technology is a solution to increase welding productivity and improve welding quality, especially in thick plate welding. In order to obtain high-quality multi-pass welds, it is necessary to maintain a stable welding bead in each pass. In the multi-pass welding, it is difficult to obtain a stable weld bead by using a traditional teaching and playback arc welding robot. To overcome these traditional limitations, an automatic welding tracking system of arc welding robot is proposed for multi-pass welding. The developed system includes an image acquisition module, an image processing module, a tracking control unit, and their software interfaces. The vision sensor, which includes a CCD camera, is mounted on the welding torch. In order to minimize the inevitable misalignment between the center line of welding seam and the welding torch for each welding pass, a robust algorithm of welding image processing is proposed, which was proved to be suitable for the root pass, filling passes, and the cap passes. In order to accurately track the welding seam, a Fuzzy-P controller is designed to control the arc welding robot to adjust the torch. The Microsoft Visual C++6.0 software is used to develop the application programs and user interface. The welding experiments are carried out to verify the validity of the multi-pass welding tracking system.     

Robot welding seam tracking method based on passive vision for thin plate closed-gap butt welding

A passive vision sensor is added to a teaching and playback welding robot for pulsed gas tungsten arc welding, which is normally used in the welding of thin plate closed-gap butts. This paper presents a seam tracking method based on this sensor through period visual measurement of the offset between the torch and the seam center. A robust image processing algorithm is developed to extract the seam center. A kind of ARX(auto-regressive with exogenous input) model is studied to describe the relationship between the rectifying voltage and the offset. The fuzzy PID(proportional-integral-derivative) seam tracking controller is analyzed and designed in consideration of various offsets based on the ARX model. The experimental results on straight line weld display a good seam tracking capability of the proposed method.     

Arc welding robot system with seam tracking and weld pool control based on passive vision

The automatic control in square-wave alternating current (AC) gas tungsten arc welding (GTAW) is significant for a “teach and playback” robot to overcome the variation of the seam trajectory and the seam gap in the welding process. This paper presents a welding robot system based on the real-time visual measurement in the different levels of the welding current. The primary objective is to measure the offset of the torch to the seam center and the size of seam gap by passive vision, track the seam and control the weld pool in real time. A novel visual image analysis algorithm was developed for seam tracking and seam gap measuring, free from robot calibration. The control algorithm based on the knowledge base was established to control the weld formation by regulating the welding current and wire feed rate. The welding practice for the rocket storage tank demonstrates the efficiency of the proposed system.     

A visual seam tracking system for robotic arc welding

A novel circular laser three-dimensional (3D) scanner is developed instead of a one-dimensional laser spot scanner (1D) and two-dimensional (2D) striped laser light. Using the proposed circular laser scanner, a seam tracking system is constructed, and architecture based on the Visual C++ and RAPID languages which determines the cooperation among image processing modules is carried out. Finally, real seam tracking experiments are investigated and the error analysis is carried out. The results show that: (1) the proposed system can realize seam tracking; (2) the precision of this system is affected by the light scanning system, calibration results, image processing, and the welding seam 3D algorithm—the tracking accuracy is satisfied for robotic arc welding; (3) this system can be used in a welding robot system as a weld seam finder, flatness detector, and weld seam tracker.     

基于双目视觉的水下焊缝图像采集与识别

文章根据水下焊缝跟踪的要求,设计了一套双目立体视觉传感器。采用卤钨灯辅助光源加复合滤光系统,较好的去除了弧光、飞溅等干扰,拍摄到较为清晰的焊缝图像。针对水下焊缝图像模糊,对比度低的特点,采用模糊增强的图像处理技术,并对Pal处理算法进行了改进,提高了图像处理的效率,获取了清晰的边缘图像．边缘检测后,对左右焊缝特征点进行扫描,准确地提取了焊缝中心。从而为水下空间缝自动化跟踪打下了基础。     

基于手眼系统的线结构光焊缝跟踪系统设计

为了实现一般手眼系统与线结构光焊缝跟踪系统主要部件的复用,在一般手眼系统的基础上,加装激光器、滤光片、保护装置等设备,将其用作焊缝跟踪系统中的线激光结构光焊缝跟踪传感器。通过实验对原手眼系统的标定结果进行实验修正,使其可以替代线结构光焊缝跟踪传感器的标定。详细分析了安装激光器、滤光片、保护装置等对原手眼标定结果造成的影响,使用数据逼近的方法提高线激光结构光焊缝跟踪传感器的手眼标定精度;实验时先对手眼系统进行标定,得到相机坐标系到工具坐标系的原外参矩阵;再对使用原外参矩阵得到的焊点数据,与焊点的实际坐标的误差进行分析,修正手眼系统标定结果。通过实验验证了本方法在手眼系统标定结果基础上,进行加装机构后的线结构光焊缝跟踪传感器的手眼标定的平均精度可达0.53 mm,能够满足机器人焊接的需求。     

具有模式识别功能的焊接自动跟踪系统

所研制的焊接自动跟踪系统,通过对不同焊道的模式自动识别,很好地实现了对多道埋弧焊的自动跟踪。     

一种适合焊接专机的激光焊缝跟踪应用

为确保焊接过程中焊枪始终沿焊缝运动,提升焊接质量,采用基于主动视觉传感技术的新一代激光视觉传感器实时采集焊缝轮廓的图像,由传感器控制柜按在PC界面上选定的算法进行图像处理与特征识别,提取焊缝跟踪点的位置坐标,并根据标定的参考位置和预设的比例关系转化为模拟电压量输出,进而驱动十字滑台上的伺服电机带动焊枪做出相应的纠偏动作。可编程逻辑控制器(PLC)被用来实现焊枪初始定位、滑台的手动控制与自动跟踪模式切换、安全互锁等功能。最终建立了一套适用于焊接专机的焊缝自动跟踪应用系统。实验结果表明,该系统安全实用,具备了良好的实时跟踪能力。     

基于结构光的螺旋钢管埋弧焊焊缝跟踪系统研究

介绍了基于结构光的螺旋钢管焊缝跟踪系统,利用LOG滤波和二值化法消除图像中的噪声并把光带图像从背景中提取出来.采用边界取平均值法抽取光带的中心线,用斜率分析法检测出特征点.该图像处理方法处理速度快,能够满足跟踪系统的要求.     

图像处理方法在焊缝自动跟踪系统中的应用研究

以基于视觉传感器的焊缝自动跟踪系统为研究对象,论述了相应的焊缝图像处理方法,有效地消除了焊接过程中的飞溅和弧光对焊缝图像的干扰.主要包括转灰度图、图像滤波、图像分割、图像边缘检测、图像细化以及HOUGH变换等.其中采用卷积滤波和中值滤波相结合的方法,提高了中值滤波能力和处理速度;采用Sobel算子,较好地保留了焊缝图像的边缘.并将这些方法综合应用成功地识别出焊缝的两条边缘,进而提取出焊缝中心,并仿真出焊枪在纠偏过程中的运动轨迹.试验表明方法处理效果好,处理速度快,能够满足跟踪系统的实时性要求.     

Automatic seam tracking in pipeline welding with narrow groove

Grain structure is an important and readily observable feature in aluminum alloy castings. Depending on the constitutional and heat-flow conditions in a solidified aluminum alloy, various morphologies are possible. Grain refining is one of the predominant techniques in controlling the quality of castings. It plays a vital role in improving metallurgical characteristics and mechanical properties of aluminum alloys. Fine equiaxed grains ensure remarkable benefits. There are a number of techniques to achieve fine equiaxed grain structure, but grain refinement by the addition of grain refiners referred to as inoculation is the most popular due to its simplicity. Grain refinement has been studied extensively by researchers for several decades, not only for developing efficient grain refiners but also for achieving an understanding of the mechanism of grain refinement. In spite of its commercial importance, benefits and numerous scientific studies in this area, the grain refinement of aluminum and its alloys is still a controversial subject. Solute elements like titanium segregate to the inoculants/melt interface affecting the dendrites and also affect the constitutional undercooling at the solid–liquid interface. This segregating power of an element is quantified by the growth restricting factor (GRF). In the present investigation, the effect of GRF on grain refinement of aluminum-silicon alloys was studied by the addition of Al-5Ti-1B master alloy. It is evident from this investigation that the growth rate of grains is inversely proportional to the GRF.     

基于电弧传感器的焊缝自动跟踪系统的研究

研制电弧传感器的焊缝自动跟踪系统 ,采用具有先进性能的开关型MIG MAG脉冲焊接电源 ,将电流和电压信号同时用作传感信号 ,通过电弧的扫描 ,既实现了焊接过程的自动跟踪 ,又解决了打底焊道的熔透问题 ,大大提高了产品焊接质量。     

一种基于DSP的焊缝跟踪模糊控制器系统的设计

本文阐述了焊缝跟踪参数自整定模糊控制器的工作原理．提出了比例因子和量化因子自动调节的方案和实现方法．介绍了模糊控制器的具体设计步骤和DSP参数自整定模糊控制系统的硬件．软件设计，结果表明，在焊缝跟踪中采用参数自整定模糊控制可以明显改善系统的性能。     

基于FPGA+DSP架构的嵌入式视觉跟踪系统

针对视觉监控应用的实时性需求,提出了一种基于FPGA+DSP架构的嵌入式视觉跟踪系统。以FPGA作为主控制器,负责视频的采集,并对图像进行了自动调光、色彩插值、中值滤波和白平衡预处理,通过PCIE接口将DSP的处理结果输出至上位机进行了显示。DSP通过EMIFA接口从FPGA接口获得了高质量的图像,采用基于均值漂移的跟踪算法进行了目标跟踪。阐述了系统各个模块的接口设计及主要算法的实现,并进行了系统的优化设计。实验结果表明,经过预处理后,图像亮度适中,图像色温得到了校正,系统能够获得高质量的图像。经过代码优化后,跟踪算法能够稳定跟踪目标,算法处理每帧图像平均时间为13ms,能够满足实时性要求。     

An image acquisition system for real-time seam tracking

Process planning is a function that establishes the technological requirements necessary to convert a part from its raw material to the finished form. Generally, the result of process planning is delivered to the workshop to guide the manufacturing process in the form of process plan. However, a part always has multi alternative process plans for the processing means and techniques are not unique, therefore, optimization and selection of process plans is an important task of flexible process planning. In this paper, the flexibility of process planning and the AND/OR network adopted to represent the flexibility of process plans were described, and a mathematical model for the optimization of flexible process planning based on the AND/OR network was established. On this basis, a new heuristic method, called cross-entropy (CE) approach, was proposed to optimize flexible process planning. In order to facilitate the implementation of the CE-based approach, the new sample representation and probability distribution parameter were introduced; meanwhile, the new sample generation mechanism was presented and the updating expression of probability distribution parameter was deduced. Case studies, used for comparing this approach with genetic algorithm (GA) and genetic programming (GP)-based approach, were discussed to indicate the performance and adaptability of the proposed CE-based approach in terms of the solution quality and computational efficiency of the algorithm. The results show that the CE-based approach is effective for the optimization research of flexible process planning.     

基于极线约束的机器人双目视觉水下焊缝特征匹配研究

本文设计了一种相交光轴的双目视觉结构形式,采用大红+紫红色复合滤光系统获取了较为清晰的水下焊缝图像。采用极线约束的立体匹配方法对水下空间焊缝进行匹配,匹配时先采用糊模增强及模糊边缘检测对水下焊缝图像进行处理,提取了焊缝的边缘及中心线作为匹配特征。然后建立极线方程,找出两图像对应的匹配点,最后求取二匹配点对应的空间坐标。水下匹配实验表明,空间直线的匹配平均误差控制在0.59mm以内,空间折线的匹配平均误差控制在0.65mm以内,能够满足机器人水下焊缝跟踪的要求。     

Laser visual sensing for seam tracking in robotic arc welding of titanium alloys

Sensor errors arose from detecting the weld-seam profile of titanium alloys with laser-based vision sensors because the surface of such a material is highly reflective to a laser light. In this study, the correct weld-seam profile was established from the distorted raw data by signal processing. Furthermore, a fully automatic seam-tracking system was developed. This system featured training and saving of the template, autofinding of the starting welding point, auto–calibration, detection of seam position and groove dimensions and tracking control. The system was capable of tracking V-groove, fillet, lap and butt joints of titanium alloys with high accuracy of less than 0.4 mm.     

基于焊缝碾压预成型的长焊缝激光拼焊系统设计

提出基于焊缝碾压预成型的长焊缝激光拼焊系统,其通过焊前对较厚板材边缘进行碾压使材料向焊缝方向塑性变形来填补焊缝间隙,极大地降低了长焊缝激光拼焊对板材直线度的要求。系统结构简便,成本较低,可有效提高焊接速度和焊接质量。介绍了系统组成结构、工作原理及控制方法。焊接结果表明,对于焊前间隙0.5mm板材的焊接,系统能大大提高焊接速度并保证焊接质量。     

焊缝跟踪应用的线激光视觉伺服控制系统

设计了一套由三轴直角坐标机器人、线激光传感器和工业计算机组成的焊缝跟踪系统。研究了该系统所涉及的测量原理、特征点测量方法和基于模糊自适应的控制方法。通过高斯核相关算法(KCF)在焊接过程中实时检测焊缝特征点,并根据测量原理计算获得特征点相对于相机坐标系的三维坐标值。设计了一种自适应模糊控制器,通过自适应模糊控制器计算坐标的偏差值和偏差变化率得到焊枪末端运动轨迹的控制量,同时对模糊控制器的输入输出论域、模糊规则和隶属函数进行实时动态更新。实施了焊缝跟踪实验。结果显示:采用最大焊接电流为350 A的惰性气体保护焊(MIG),在强烈弧光和飞溅的干扰下,该系统能实时跟踪焊接工件,跟踪精度为0.325 3mm,传感器测量频率为20Hz。焊接过程中焊枪末端运行平稳,焊缝轨迹跟踪准确,且抗干扰能力,能满足焊接应用要求。     

基于免疫模糊的机器人焊缝跟踪系统智能控制

针对传统控制理论在视觉跟踪焊接机器人随动系统中难以取很良好控制效果的问题,提出了基于免疫学的智能控制方法.并运用该方法将随动系统跟踪焊缝所需的转动角度作为免疫抗原,以随动系统的输入电压作为免疫抗体,对焊缝跟踪系统的跟踪性能进行了仿真实验,结果表明该控制方法具有良好的快速性和稳定性,满足随动系统快速旋转跟踪焊缝的要求.