一种改进的Canny边缘检测算法

针对Canny边缘检测算法存在的缺陷,提出了一种改进型Canny边缘检测算法。首先采用非线性扩散滤波减少了图像噪声,同时保持图像的边缘信息;在邻域梯度幅值计算中,考虑像素对角线方向的梯度,进一步抑制了噪声的影响;最后采用平均方差阈值法选取阈值,从而提高了对不同图像的自适应性。通过对实验图像的分析表明,该改进算法对含噪图像的边缘提取具有较好的检测精度和准确性。     

Welding deviation detection algorithm based on extremum of molten pool image contour

The welding deviation detection is the basis of robotic tracking welding, but the on-line real-time measurement of welding deviation is still not well solved by the existing methods. There is plenty of information in the gas metal arc welding(GMAW) molten pool images that is very important for the control of welding seam tracking. The physical meaning for the curvature extremum of molten pool contour is revealed by researching the molten pool images, that is, the deviation information points of welding wire center and the molten tip center are the maxima and the local maxima of the contour curvature, and the horizontal welding deviation is the position difference of these two extremum points. A new method of weld deviation detection is presented, including the process of preprocessing molten pool images, extracting and segmenting the contours, obtaining the contour extremum points, and calculating the welding deviation, etc. Extracting the contours is the premise, segmenting the contour lines is the foundation, and obtaining the contour extremum points is the key. The contour images can be extracted with the method of discrete dyadic wavelet transform, which is divided into two sub contours including welding wire and molten tip separately. The curvature value of each point of the two sub contour lines is calculated based on the approximate curvature formula of multi-points for plane curve, and the two points of the curvature extremum are the characteristics needed for the welding deviation calculation. The results of the tests and analyses show that the maximum error of the obtained on-line welding deviation is 2 pixels(0.16 mm), and the algorithm is stable enough to meet the requirements of the pipeline in real-time control at a speed of less than 500 mm/min. The method can be applied to the on-line automatic welding deviation detection.     

基于边缘信息和局部直方图的视频文字检测法

视频中的标题文字通常在视频信息索引和检索中起到重要的作用。针对视频中文本的检测问题,提出了一种基于边缘和局部直方图的由粗到精的视频标题文字检测算法,首先采用边缘聚集提取文字的粗略位置,然后利用局部直方图特征对候选的文字区域精确定位。实验结果表明,该方法简单,效果良好,能快速地定位文本区域,且不受文本颜色、语种、文本字体大小的限制。     

Leak detection in pipe using transient flow and genetic algorithm

An inverse transient method with genetic algorithm (GA) was applied to leak detection in pipeline. Transient flow caused by valve operation was calculated using the characteristics method. The location and discharge of leak were determined so that the difference of the calculated pressure may be minimized from the reference pressure calculated under a given leak condition. Calculations were done for the leak at one and two locations in pipeline. Furthermore, the effect of noise in pressure data was discussed, and the leak locations and leak discharges can be predicted precisely even in the case of noisy data. This paper was presented at the 9^th Asian International Conference on Fluid Machinery (AICFM9), Jeju Korea, October 16–19, 2007.     

钽薄板TIG氦弧焊热过程的数值分析

针对钽薄板氦弧焊接的特点,基于有限元分析软件ANSYS,对钽薄板TIG氦弧焊接的温度场进行三维数值动态模拟,并将计算量控制在可接受的范围内。建模时采用实体单元和表面单元结合,并采用焊缝处细密、远离焊缝处粗略的不均匀网格,热载荷施加过程中采取了一系列非线性措施,分析了焊接结束后温度场在工件上的分布规律及冷却时间对工件温度场分布的影响,并据此提出了提高钽薄板TIG氦弧焊接接头质量的方案。计算结果表明熔池的尺寸随焊接时间的变化较为明显。计算所得熔池大小与实验结果基本吻合。     

一种基于统计排序滤波的图像边缘检测算法

提出一种基于统计排序滤波的新的边缘检测算法OFE。说明了算法原理,给出了算法实现的步骤和方法,通过人造图像和自然图像进行仿真实验,对仿真结果进行主客观对比评价分析,表明该边缘检测算法不仅有效,且效果与Sobel等算子相当,高于LOG算子,在处理含脉冲噪声污染的图像时有一定的优势。     

Online detection method of weld penetration based on molten pool morphology and metallic vapor radiation for fiber laser welding

A novel detection method of penetration status was presented for a high-power fiber laser welding. The metallic vapor and molten pool was recorded by a high-speed camera during welding process. The radiation intensity of metallic vapor, as well as the morphology of molten pool end, was calculated by image processing algorithm as image features. Four image features, the radiation intensity of metallic vapor (RIMV), the area of molten pool end (AMPE), the rear angle of molten pool end (RAMPE), and the aspect ratio of molten pool end (ARMPE), were extracted. The mean value, relative range, variation coefficient, and frequency ratio were computed for the four features to obtain the 16 characteristic parameters. Aiming at penetration status, the characteristic parameters were reorganized to form two complex indicators by the principal component analysis. Experimental results showed that the detection method was potential for online detection on the penetration status in a high-power laser welding process.     

Effect of gap on plasma and molten pool dynamics during laser lap welding for T-joints

The aim of the present research is to discuss the effect of gap on plasma plume, keyhole, and molten pool dynamics during laser lap welding for T-joints. The authors observe plasma plume, keyhole opening, and molten pool images by high-speed camera in different gaps during CO₂ laser overlap welding of T-joints. The results show that gap causes beam energy fluctuations in the keyhole and leads to the instability of welding process. In laser spot welding, zero-gap and small gap greatly affect the stability of plasma and keyhole, which causes the formation of cavities in the weld metal, while a proper gap can help prevent porosity formation. In laser continuous welding, the disruption and closure of front keyhole wall at the gap periodically changes with the gap, which causes the formation of plenty of porosities at the gap. The instability of keyhole is closely related to dynamics of plume and molten pool, which gives an insight into the mechanism of porosity formation during laser overlap welding.     

一种改进的六边形结构的Canny边缘检测算法

在图像处理过程中,为了获取更精确的边缘轮廓,将直线插补运算与六边形图像结构相结合,提出了一种简单高效的边缘检测方法.先用高斯滤波器对图像进行滤波,再使用Sobel算子进行边缘检测,最后按给定阚值对边缘进行精确提取,经过这三个步骤完成图像的边缘检测.通过实验验证了六边形图像结构的Canny边缘检测算法比常见的Canny边...     

基于边缘检测小波变换的红外与可见光图像融合方法

简要地论述了图像融合中主要的三种像素级融合算法,即简单方法、基于塔形分解以及基于小波分解的融合方法,在现有的红外与可见光图像融合方法之上,提出了以边缘检测为基础的一种小波变换图像融合方法,并对融合效果进行了评价。实验结果表明,经该方法对红外与可见光图像的融合可以提供更多、更有效的信息,提高了图像的分辨效果和人眼对场景目标的发现和识别概率,融合效果较为理想。     

Analysis of characteristics of molten pool using cast shadow during high-power disk laser welding

On-line monitoring and control of laser welding process play an important role in welding quality assessment. The morphology of molten pool during welding process influences welding quality. Volume, tilt, and height were characteristics of molten pool, but they cannot be measured directly during the welding process. An experiment of surfacing weld of Type 304 austenitic stainless steel with high-power disk laser welding was implemented. An active vision system with an auxiliary laser light source was designed to acquire the images of molten pool and its shadow during the welding process. The images were pre-processed to analyze the characteristics of the casting shadow of molten pool instead of analyzing the characteristics of the molten pool itself. The area, maximal distance between the shadow and keyhole, maximal width, and the tilt of the shadow were selected as the characteristics to analyze the relationship between the morphology of molten pool and welding quality by linear and 10th non-linear fitting. The results indicated that the welding quality could be dynamically detected by observing these characteristics. A different welding process was also conducted to confirm the proposed method. The research in this paper provides a method for on-line monitoring and control during high-power disk laser welding.     

冷凝器清洗机器人的奇Gabor边缘检测算法研究

冷凝器管口的边缘检测是实现清洗机器人喷枪口精确定位的关键步骤。由于二维Gabor函数是能够取得空域和频域联合测不准原理下限的唯一函数,本文提出了二维奇Gabor算法应用于大型冷凝器清洗机器人清洗中的边缘检测,它克服了傅里叶变换对信号的局部特征没有分析能力的缺陷,可以在多个尺度上对图像的边缘进行检测。文章对检测的性能做了详细分析,实验结果证明该方法具有良好的边缘检测效果,其性能优于Sobel、Prewitt、Roberts、Log等传统边缘检测算法。     

一种改进的Pal和King模糊边缘检测算法

针对Pal和King提出的模糊边缘检测算法易导致图像灰度信息丢失这一缺陷,提出一种改进的图像模糊边缘检测算法.该算法首先通过阈值来定义一个新的隶属函数将原始图像映射到模糊特征平面;然后利用模糊增强处理来提高区域之间的层次,加强边缘两侧的对比度;最后根据一定的判别准则提取出图像的边缘.实验结果表明,采用改进的方法边缘检测质量显著提高,算法速度大大加快.新算法中具有唯一的参数且可以自动确定,保证了算法的自适应性.     

一种基于小波变换的照明无关边缘检测和模糊增强方法

提出了一种基于小波变换的照明无关边缘检测和模糊增强算法,用于从不均匀的弱照明图像中提取目标边缘。依据照明反射图像形成模板和CCD相机成像公式,推导出图像的小波变换公式。对图像局部区域中边缘与背景像素的小波系数进行比较分析,设计了一种照明无关的小波边缘检测公式。给出一种同时考虑小波模值大小和梯度方向的模糊算子来增强边缘并抑制噪声。最后,采用仿真和真实的图像对该算法进行验证,利用此算法检测阶梯边缘,得到该算法的边缘检测评价标准F系数值为0.984 3,边缘定位精度评价系数E_d值为0.126 5,通过被检测的特征球边缘计算得到的交比值误差为3.72×10^-3。实验结果证实,该边缘检测方法能够很好地工作于非均匀的弱照明图像。     

BGA焊球视觉检测算法及系统设计

为了实现对BGA焊球的自动检测,建立了自动视觉检测系统。对系统所采用的焊球特征进行提取及缺陷识别,基于高斯混合模型的分类器对检测算法进行研究。根据焊球的形状和尺寸特征设计了焊球缺陷识别和分类算法,并以锡多、锡少和毛刺缺陷为例,分析典型缺陷的识别算法。以焊球形状的圆度和特征区域的面积等特征参数为评价标准,构建二维特征空间。在二维特征空间线性组合的基础上,构建基于高斯混合模型的分类器。构建了训练样本集,并对该分类器进行训练,根据训练结果并结合应用实际修正了模型,并采用测试集对该分类器进行测试验证。实验结果表明,焊球缺陷检测算法的准确度为97.06%,漏判率为0%,检测可靠度为100%。该视觉检测系统满足了工程运用中对识别准确度、稳定性、可靠性等方面的要求。     

Effect of the process parameters on the three-dimensional shape of molten pool during full-penetration laser welding process

Slow tool servo (STS) turning is superior in machining precision and in complicated surface. However, STS turning is a complex process in which many variables can affect the desired results. This paper focuses on surface roughness prediction in lenses STS turning. An exponential model, based on the five main cutting parameters including tool nose radius, feed rate, depth of cut, C-axis speed, and discretization angle, for surface roughness prediction of lenses is developed by means of orthogonal experiment regression analysis. Meanwhile, a prediction model of surface roughness based on least squares support vector machines (LS-SVM) with radial basis function is constructed. Orthogonal experiment swatches are studied, and chaotic particle swarm optimization and leave-one-out cross-validation are applied to determine the model parameters. The comparison of LS-SVM model and exponential model is also carried out. Predictive LS-SVM model is found to be capable of better predictions for surface roughness and has absolute fraction of variance R² of 0.99887, the mean absolute percent error e_M of 8.96 %, and the root mean square error e_R of 10.68 %. The experimental results and prediction of LS-SVM model show that effects of tool nose radius and feed rate are more significant than that of depth of cut on surface roughness of lenses turning.     

机械零件尺寸图象测量中的边缘检测算法

这里提出了一种应用于机械零件图象测量领域的边缘检测算法：使用基于Sobel算子的改进的方向算子,综合利用图像灰度信息和灰度梯度信息对目标边缘进行检测和亚像素精确定位。在文章的最后,用实例说明了本算法的可行性。     

机载仪表图像边缘检测算法的优化

针对机载仪表视频图像存在边缘模糊,字符不清,传统算法难于识别的缺点,提出了一种基于梯度锐化的图像边缘检测的优化算法。实验表明,该优化算法能较好地解决传统算法所造成的图像变暗的问题。在不破坏原始背景的情况下,满足对图像的边缘增强及根据需要增强边缘的需求。     

基于改进Canny算法的LED晶片边缘提取

为了提高固晶机对LED晶片边缘提取的自动化程度和边缘质量,避免固定阈值Canny所必须的人工调整,增大检测方法的适应范围和稳定性,提出了一种基于大津法的Canny边缘检测算法进行晶片边缘提取。在分析了LED晶片的图像灰度分布特征之后,通过求得最大类间方差找到了自适应的分割阈值,并将其作为Canny算法的低阈值进行边缘的检测提取。实验结果证明,这种方法适合LED晶片的边缘提取,能够快速得到较为精确的晶片边缘轮廓和晶片两极边缘,对光线变化的鲁棒性好。     

求解作业车间调度问题的一种改进遗传算法

为克服传统遗传算法解决车间作业调度问题的局限性,综合遗传算法和局部搜索的优点,提出一种改进的遗传算法。为基于工序的编码提出了一种新的POX交叉算子。同时,为克服传统遗传算法在求解车间作业调度问题时的早熟收敛,设计了一种子代交替模式的交叉方式,并运用局部搜索改善交叉和变异后得到的调度解,将提出的改进遗传算法应用于MuthandThompson基准问题的实验运行,显示了该算法的有效性。