Visual seam tracking system for butt weld of thin plate

An image-based visual seam tracking system is designed for butt weld of thin plate in this paper. The torch deviation from the joint in the horizontal direction is measured from the seam image. Since the weld seam is so narrow, its image is based on natural lighting. Due to the hardness of measuring depth information using monocular vision, structured laser light is used for detecting the torch deviation in the vertical direction. For steady seam tracking, a robust and fast feature extraction algorithm is developed. Moreover, a reliable controller is designed with error filtering and output pulse verification. Finally, experiments are conducted to verify the proposed seam tracking system.     

Passive vision based seam tracking system for pulse-MAG welding

Welding robots have been widely used in manufacturing process to substitute for human welders. However, most of them are rigid and cannot adjust to variations in the weld seam positions caused by natural welding environmental factors. To address this problem, this paper presents a passive vision-based robotic welding system, which can realize the seam tracking function for pulse-MAG welding. In this paper, the light spectrum of the welding process is analyzed to determine the optical filters used during the image capture. Then, a robust image processing method is proposed to extract the offset from the image which contains much noise. The transformation formula is calibrated to obtain the relationship between the image coordinate system and the robot coordinate system. The tracking strategy is designed to improve the tracking precision and the stability of the welding process. Finally, experiments are conducted on straight line and curved line seam to verify the feasibility of the developed system.     

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.     

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.     

薄板TIG对接焊温度场的有限元模拟

焊件中的温度场分布反映了复杂的焊接热过程，是研究焊接变形、焊后残余应力等状况的基础。焊接数值模拟技术的出现，为焊接技术的深入发展创造了有力的条件。针对低碳钢薄板件TIG对接焊时，应用双椭圆分布热源模型，建立了TIG对接焊三维温度场有限元数值分析模型，将有限元解同实验结果进行了比较，两者基本吻合，表明了该分析模型的有效性，并以此有限元模型为基础，分析了两焊板间存在间隙和焊枪偏离焊缝中心这一实际情形下，温度场分布的不均匀性。     

微细对接焊缝初始点定位方法

为了解决焊接机器人对薄板微细焊缝的自动定位和焊接问题,研究了一种基于视觉的高精度微细对接焊缝初始点定位方法。提出一种局部范围内两步精确定位方法,第一步,获取工件在不同尺度及旋转角度下的图像,建立典型的模板匹配库,利用模板匹配方法提取出焊缝初始点位置区域;第二步,采用Shi-Tomasi算法在此局部范围内进行角点检测,计算亚像素级角点位置并进行初始点精确定位。通过对现场拍摄的50幅不同高度和旋转角度的图像进行初始点检测,实现了对所有图像的准确检测。实验结果表明,两步定位方法鲁棒性强,可以精确定位出规则边界和不规则边界焊缝的初始点,解决了微细对接焊缝初始点定位问题,达到了期望结果。     

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。     

焊接顺序对中厚板对接焊残余应力的影响

针对同种材料,但几何结构不同的中厚板结构件之间的对接焊,运用有限元软件进行模拟,分析多层多道焊各层焊缝的焊接顺序对焊缝区域横、纵向残余应力的影响。采用内生热的加载方式模拟热源,采用生死单元法模拟多层多道焊缝的焊接过程。模拟结果表明,从几何尺寸小的一边向几何尺寸大的一边焊,沿焊缝底部和顶部中心线方向产生的横纵向残余应力峰值最小;底层的几道焊缝的焊接顺序对焊缝底部和顶部中心线方向所产生的横纵向残余应力的影响不大。     

基于薄板样条函数的无人机多目标跟踪算法

针对无人机单机载相机运动下的多目标跟踪存在目标位置漂移和状态预测失效等问题,提出了一种基于薄板样条函数的无人机多目标跟踪方法.利用空间变换函数刻画无人机运动,构建无人机运动下的目标状态空间模型,利用外观特征初始化轨迹与量测对应关系,根据初始对应关系并计算薄板样条函数的最小二乘解求解出模型未知参数,进而根据模型预测轨迹运...     

Friction stir butt welding thin aluminum alloy sheets

0.8-mm-thick alclad 2024-T4 aluminum alloy sheets were friction stir butt welded. A 15-mm diameter shoulder tool was used to guarantee sufficient heat input during welding. A 0.08-mm shoulder plunge depth was adopted to reduce sheet thickness reduction. Sound joints were obtained at rotating speeds from 400 to 1000 rpm and welding speeds from 50 to 150 mm/min. A thickness reduction of 6% was achieved at 1000 rpm and 50 mm/min. Secondary phases firstly precipitated at the black lines in the stir zone (SZ). The hardness of the SZ showed a decrease about 6% compared with the base metal. A maximum tensile strength of 399.5 MPa and an elongation of 5.6% were achieved at 1000 rpm and 150 mm/min. The fracture morphologies showed typical ductile fracture mode.     

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。     

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。     

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.     

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.     

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。     

基于机器视觉的多旋翼无人机追踪方法研究

为了解决现阶段视频中物体检测方法对目标较小的多旋翼无人机识别能力差、检测不准确等问题,提出一种基于神经网络多层级特征识别及跟踪无人机的方法.该方法包含前向跨阶段连接和反向特征构建两部分:前向跨阶段连接将神经网络每一阶段的输出层输入到其余阶段的输入层,反向特征构建部分是把上采样得到特征图与前向传播得到的特征图进行相加进而...     

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.     

基于双目视觉的智能监控系统运动目标自动化跟踪方法

传统方法无法对目标精准定位,在动态环境下跟踪精准度低,提出基于双目视觉的智能监控系统运动目标自动化跟踪方法。采用背景差分法构建背景模型,通过计算二值差分图像比较差分图像像素和某特定阈值,确定检测目标具体位置。研究以双目视觉安全防护为基础的监控示意图,利用特征向量线性组合表达不同人脸变化或特性,根据具体实施步骤设计人脸监测与识别流程,采用CamShift跟踪算法求局部最优解,获取重投影矩阵,在监控系统运动目标发生遮挡后再次进行自动化跟踪。以Python为语言基础进行实验对比分析,由实验结果可知,基于双目视觉方法跟踪精准度较高,能够实现对运动目标的精准定位。     

基于斜率约束和回溯搜索的水下多目标跟踪方法

针对复杂水域环境下的多目标跟踪问题,本文提出了一种基于斜率约束和回溯搜索的多目标跟踪方法。首先,基于方位测量数据和水下目标运动学分析,利用门限阈值的方法检测目标。然后,基于传统多假设跟踪算法框架设计一种新的斜率约束和共用量测的假设生成规则。在航迹中断时,通过回溯搜索的方法确定中断起始航迹点,利用容积卡尔曼滤波对中断航迹预测和补偿,同时对假设生成结果减枝,以达到降低算法空间复杂度的目的。试验结果表明:该方案能够实现多目标自动关联跟踪、中断航迹自动预测、自动航迹终止等任务,目标跟踪平均均方根误差0.594 4°,算法平均运行时间0.826 5 s。