微间隙焊缝磁光成像卡尔曼滤波跟踪算法

在激光对接焊过程中,实时控制激光束准确对中焊缝是保证焊接质量的前提。针对紧密对接激光焊,研究一种用于微间隙(不大于0.1 mm)焊缝位置识别及跟踪的磁光成像卡尔曼滤波算法。采用磁光传感器实时获取焊接区域的微间隙焊缝磁光图像序列,利用微间隙焊缝磁光图像的灰度梯度特征提取焊缝位置坐标。以焊缝位置及位移量构成状态矢量,建立描述焊缝位置的状态方程和测量方程。同时,假设系统动态噪声和测量噪声为零均值随机分布的高斯白噪声,建立噪声环境下的卡尔曼滤波跟踪算法,计算最小均方差条件下焊缝中心最优预测值,减小系统噪声和过程噪声对焊缝位置测量的影响。试验结果显示,该方法能有效实现激光对接焊微间隙焊缝位置的识别与跟踪。     

焊接缺陷磁光成像动态检测与识别

为了实现焊接缺陷的自动检测,研究一种交变磁场激励下焊缝表面及亚表面缺陷的磁光成像动态无损检测方法。分析了基于法拉第磁致旋光效应的焊接缺陷磁光成像机理,并结合交变磁场原理推导出励磁变化与动态磁光成像的关系。探索低碳钢板的亚表面焊缝磁光成像特征试验,验证了所提方法可用于检测焊缝亚表面的未熔合缺陷。最后对高强钢焊缝特征的动态磁光图像进行分析,采用主成分分析法和支持向量机(PCA-SVM)模式识别方法建立了焊接缺陷分类模型。试验结果表明,所提方法可以识别高强钢焊件中的焊缝特征(未熔透、裂纹、凹坑和无缺陷),缺陷分类模型的整体识别率达到92.6%,能够实现焊缝表面及亚表面缺陷的自动检测。     

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。     

交变磁场下焊接缺陷磁光成像特征分析

研究焊接缺陷磁光成像检测方法,基于法拉第旋转效应,分析交变磁场下焊接缺陷磁光成像特征与漏磁场之间的关系.建立焊接缺陷的三维有限元模型,对不同类型和宽度的焊接缺陷漏磁场分布进行模拟,并在交变磁场激励下对不同焊接缺陷进行磁光成像无损检测试验,通过试验验证了焊接缺陷检测模型的有效性.研究结果表明,漏磁场分布与缺陷的类型和宽度...     

Study of laser butt welding of SUS301L stainless steel and welding joint analysis

This paper describes a study on laser butt welding of 4 and 2 mm SUS301L stainless steel and a detailed analysis of welding joints. The gap tolerance of butt joint was also studied with optimized process parameters. The electrolytic etching in 10 % oxalate solution was used to test the intergranular corrosion of the 4 mm SUS301L welded joint. Fatigue property of the 2 mm SUS301L welded joint was tested under the conditional cycle times of 1?×?10⁷. Using optical microscopy, the changes of metallurgical microstructure in the weld zone of 4 mm SUS301L were also studied. It has been found that laser butt welding of 4 mm SUS301L is able to achieve sound metallurgical morphology and high strength weld joint when the butt gap is within certain tolerance. The weld joint also has good resistance to intergranular corrosion and has a fatigue limit of 310 MPa.     

低功率激光诱导电弧复合焊接钛合金薄板工艺研究

采用低功率脉冲YAG激光诱导非熔化极惰性气体保护(Tungsten inert gas,TIG)焊电弧复合热源实现了1 mm厚TC4钛合金薄板的优质焊接,研究激光诱导电弧复合焊接过程中热源能量匹配、热源间角度、对接间隙对焊缝成形的影响规律。结果表明,钛合金薄板低功率脉冲YAG激光诱导TIG电弧复合热源焊接过程中,激光能量与电弧能量之间的相互匹配将显著影响焊缝的表面成形。相对于电弧功率的变化,焊缝成形对激光功率变化的敏感度更高。随着热源间角度减小,激光诱导电弧复合热源传热能力增强;由于复合焊接速度快、热输入小、焊接试板横向变形小,当对接间隙为0~0.5 mm范围内时均能获得良好的焊缝成形。为了使焊缝成形均匀连续,焊接过程中需要对焊缝背面采用氩气进行保护,当保护气体流量为5~8L/min时获得最佳焊接接头。     

基于图像处理的爬壁机器人焊缝识别与跟踪

基于爬壁机器人移动平台和单目相机的图像采集系统,设计了一种焊后焊缝图像处理方法,将改进的自适应中值滤波算法与灰度形态学方法结合,实现从信噪比较高的图像中提取特征。采用基于边缘检测和Hough变换的焊缝位置提取算法,经测试识别准确率达70%,且单幅图像平均处理时间为200ms,能满足管道爬壁机器人行进过程中的实时焊缝跟踪,并提供了一种引导机器人沿焊缝前进的自主定向方案。     

CO2 laser welding of zinc-coated steel sheets

Welding of zinc-coated steel sheets for the automotive industry has been investigated experimentally and theoretically, using a continuous wave 2 kW CO₂ laser. The specimens of 0.8, 1.0 and 1.2 mm thickness were welded as butt joint and lap joint. Argon gas was shielded co-axially to reduce the plasma and to protect the molten, pool from atmosphere. The mechanical tests of specimens were carried out to investigate the ductility of welds in butt joint and lap joint, using the Erichsen test, ball punch test and tensile shear test. The value of transverse weld pattern is higher than others. The fatigue life of longitudinal weld is superior, but that of circular weld pattern is inferior due to the high tensile residual stresses in the weld. The maximum Erichsen value was obtained as 96% and the deformability of zinc coated steel butt-welded was found to be 80% in the ball punch test. The high pressure formed by vaporization of zinc with the low boiling temperature during laser lap-joint welding splattered the molten pool and created porosities in the weld. The optimum gap was calculated to be 0.1 mm in the lap joint welding of zinc-coated steel sheet which was a good agreement with the experimental result.     

对接TIG焊熔池正面几何形状参数的检测

研制出连续电流对接TIG焊熔池正面形状参数实验检测装置。利用普通CCD摄像机,通过光学参数的优化和采集参数的动态调整,拍摄出了清晰度和分辨率都较高的对接TIG焊熔池正面图像。根据对接TIG焊熔池图像特点,设计出图像处理算法,检测出了焊接熔池的整个边缘,得到了不同工艺条件下对接TIG,焊熔池几何形状参数的实际尺寸。     

接管对接TIG自动焊工艺研究

针对加氢反应器制造中接管或弯管的对接焊缝,以1.25Cr-0.5Mo材料为例进行焊接试验,探究一种合理的自动TIG焊工艺。     

Laser vision sensing based on adaptive welding for aluminum alloy

A laser vision sensing based on the adaptive tungsten inert gas (TIG) welding system for large-scale aluminum alloy components was established to fit various weld groove conditions. A new type of laser vision sensor was used to precisely measure the weld groove. The joint geometry data, such as the bevel angle, the gap, the area, and the mismatch, etc., aided in assembling large-scale aerospace components before welding. They were also applied for automatic seam tracking, such as automatic torch transverse alignment and torch height adjustment in welding. An adaptive welding process was realized by automatically adjusting the wire feeding speed and the welding current according to the groove conditions. The process results in a good weld formation and high welding quality, which meet the requirements of related standards. Translated from Journal of Beijing University of Technology, 2006, 32(8): 714–718 [译自: 北京工业大学学报]     

Practical method to locate the initial weld position using visual technology

The autonomous localization of initial weld position is one of the key technologies to realize intellectualized welding. This paper presented a practical system and method to guide the welding robot to the initial position of the weld seam. Using template matching and polynomial interpolation technology of pixel, the position of initial weld position is located at the sub-pixel level in the image plane. Simple and practical calibration technology avoids the using of complicated algorithms and costly measuring apparatus. Aluminium and its alloys reflect the light strongly, which make the recognition of the weld seam more difficult than steel. Taking the butt joint weld seam of a curve aluminium alloy sheet as an example, the autonomous localization function is realized accurately. For those instances with bigger errors, we advanced a method to rectify the deviation. The welding robot can be guided to the initial position of planar weld seam and meets the requirements to execute welding operation directly. The whole procedure has the characters of simple, practical, and strong anti-jamming.     

Porosity in fiber laser formation of 5A06 aluminum alloy

The mechanism of porosity formation and its suppression methods in laser formation of aluminum alloy have been studied using a 4kW fiber laser to weld 5A06 aluminum alloy with SAl-Mg5 filler. It was found that the porosity formation is closely related to the stability of the keyhole and fluctuation of the molten pool in the laser welding aluminum alloy. The filling wire increased the instability of the keyhole and weld pool, thus further increasing the amount of gas cavities in the joint. Prefabrication of a suitable gap for the butt joint can provide a natural passage for the flow of the liquid metal, which can weaken, and even completely eliminate the disturbance of the filling wire on the formation of keyhole. The gap can also provide a passage for the escape of the bubble. Thus, this method can greatly decrease the sheet’s susceptibility to porosity. Moreover, for a thin sheet, if the power of the laser is sufficient to form a keyhole with stable penetration through the weld sheet, a weld bead without porosity can also be obtained because closing the keyhole is almost impossible.     

交变/旋转磁场下焊接缺陷磁光成像检测与分类

针对任意角度焊接缺陷难以检测的问题,研究在不同磁场激励下焊接缺陷磁光成像无损检测系统。重点介绍了由U形磁轭产生的交变磁场和平面交叉磁轭产生的旋转磁场激励焊件的机理,比较了交变/旋转磁场激励下不同焊接缺陷的磁光成像效果。基于法拉第旋转效应分析磁光成像特性与磁场强度之间的关系,磁光图像的灰度值可以匹配相应的漏磁场强度。采用主成分分析法提取融合图像列像素灰度特征和通过灰度共生矩阵提取磁光图像纹理特征,建立BP神经网络模型和支持向量机模型识别这些缺陷特征。试验结果表明,在旋转磁场激励下,BP神经网络模型和支持向量机模型的分类精度分别为94.1%和98.6%,相比交变磁场,分类精度分别提高了10.7%和8.5%。旋转磁场激励下的磁光成像克服了定向检测的局限性,能够实现对任意角度焊接缺陷的检测及分类。     

Discerning Weld Seam Pro les from Strong Arc Background for the Robotic Automated Welding Process via Visual Attention Features

In the robotic welding process with thick steel plates, laser vision sensors are widely used to profile the weld seam to implement automatic seam tracking. The weld seam profile extraction(WSPE) result is a crucial step for identifying the feature points of the extracted profile to guide the welding torch in real time. The visual information processing system may collapse when interference data points in the image survive during the phase of feature point identification, which results in low tracking accuracy and poor welding quality. This paper presents a visual attention featurebased method to extract the weld seam profile(WSP) from the strong arc background using clustering results. First, a binary image is obtained through the preprocessing stage. Second, all data points with a gray value 255 are clustered with the nearest neighborhood clustering algorithm. Third, a strategy is developed to discern one cluster belonging to the WSP from the appointed candidate clusters in each loop, and a scheme is proposed to extract the entire WSP using visual continuity. Compared with the previous methods the proposed method in this paper can extract more useful details of the WSP and has better stability in terms of removing the interference data. Considerable WSPE tests with butt joints and T-joints show the anti-interference ability of the proposed method, which contributes to smoothing the welding process and shows its practical value in robotic automated welding with thick steel plates.     

Development of a real-time laser-based machine vision system to monitor and control welding processes

In this study, a laser-based machine vision system is developed and implemented to monitor and control welding processes. The system consists of three main modules: a laser-based vision sensor module, an image processing module, and a multi-axis motion control module. The laser-based vision sensor is designed and fabricated based on the principle of laser triangulation. By developing and implementing a new image processing algorithm on the platform of LabVIEW, the image processing module is capable of processing the images captured by the vision sensor, identifying the different types of weld joints, and detecting the feature points. Based on the detected feature points, the position information and geometrical features of the weld joint such as its depth, width, plates mismatch, and cross-sectional area can be obtained and monitored in real time. Meanwhile, by feeding these data into the multi-axis motion control module, a non-contact seam tracking is achieved by adaptively adjusting the position of the welding torch with respect to the depth and width variations of the weld joint. A 3D profile of the weld joint is also obtained in real time for the purposes of in-process weld joint monitoring and post-weld quality inspection. The results indicate that the developed laser-based machine vision system can be well suited for the measurement of weld joint geometrical features, seam tracking, and 3D profiling.     

焊接缺陷的磁光成像小波多尺度识别及分类

针对焊缝微小凹陷、未熔合和焊偏等焊接缺陷,提出了基于磁光成像无损探伤的小波多尺度边缘提取算法及主成分分析-误差反向传播神经网络(PCA-BP)缺陷分类模型;研究了焊件表面及近表面缺陷的可视化无损检测及分类方法。首先,通过对焊件施加感应磁场,利用法拉第磁致旋光原理构成磁光传感器,获取焊接缺陷磁光图像。然后,针对焊接缺陷磁光图像存在噪声干扰、对比度低且成像背景复杂等特征,基于小波模极大值的多尺度边缘信息融合方法,设计了具有高抗噪性的缺陷边缘检测算法。最后,通过PCA法对磁光图像列方向灰度变量进行预处理,得到能表征95%磁光图像列方向灰度变量信息的256个特征点作为输入特征量,构建了三层BP神经网络模型,对焊接缺陷样本进行分类。试验结果表明,所提方法能准确识别微小凹陷、未熔合和焊偏等焊接缺陷,模型分类准确率可达90.80%。     

大功率盘形激光焊焊缝背面宽度预测

提出了通过视觉传感获取焊接过程中的焊接特征信息并利用神经网络模型预测焊缝背面宽度的方法。利用大功率盘形激光器焊接了低碳钢SS400焊件,在焊接过程中改变焊接功率、焊接速度和焊接路径,并利用两台高速摄像机同步获取焊件正面和侧面出现的焊接特征信息。对获取的图像进行色彩空间转换、分层、滤波去噪和空域图像处理,提取飞溅、熔池和金属蒸气等焊接特征信息,观察焊接路径对各个特征的影响。最后,建立了一个三层的LMBP(LevenbergMarquardt Back Propagation)神经网络模型,将提取的特征信息作为输入量,预测焊缝的背面宽度。结果显示:当熔透不稳定或出现未熔透状态时,LMBP神经网络拟合度大于0.83,最大训练误差均值为0.002 8mm,最大实际误差均值为0.225 6mm。试验结果表明所建立的预测模型具有良好的准确性和稳定性。     

Real-time image processing for vision-based weld seam tracking in robotic GMAW

Image capturing and processing is important in using vision sensor to effectively track the weld seam and control the weld quality in robotic gas metal arc welding (GMAW). Using vision techniques to track weld seam, the key is to acquire clear weld images and process them accurately. In this paper, a method for real-time image capturing and processing is presented for the application in robotic seam tracking. By analyzing the characteristic of robotic GMAW, the real-time weld images are captured clearly by the passive vision sensor. Utilizing the main characteristics of the gray gradient in the weld image, a new improved Canny edge detection algorithm was proposed to detect the edges of weld image and extract the seam and pool characteristic parameters. The image processing precision was further verified by using the random welding experiments. Results showed that the precision range of the image processing can be controlled to be within ±0.3 mm in robotic GMAW, which can meet the requirement of real-time seam tracking.     

水电站合拢焊缝接头形式研究

坝后式引水压力钢管取消伸缩节后合拢焊缝接头形式有对接和搭接两种接头形式。对两种接头形式进行了试验研究,结果表明:对接和搭接两种接头形式都有各自的特点,对接接头形式优点较为明显,采用一些工艺措施可以减少焊接拘束应力和防止裂纹的产生,采用对接接头形式有利于引水压力钢管安全运行。