针对激光熔覆过程中存在弧光、熔融金属液滴等干扰导致激光熔覆熔池边缘难以准确提取的问题，提出了基于相位一致模型的熔池边缘提取方法。为了得到完整、精准的熔池边缘，对获取的熔池图像进行预处理后，使用基于阈值的方法，对熔池进行初步分割，对剪裁后的熔池图像采用相位一致性模型进行边缘检测，将其边缘在粗分割区域进行标记，对标记图进行进一步分割并用sobel算子对精分割区域进行边缘提取。相关试验的对比分析表明，该方法具有良好的熔池边缘提取精度和干扰鲁棒性。
Aiming at the problem of being difficult in weld pool edge extraction in laser cladding due to the interference such as arc, molten metal drop and so on. A method for extracting the edge based on phase congruency is presented. In order to extract complete and accurate weld pool edge, the molten pool is roughly divided by using the method based on threshold after preprocessing the acquired weld pool image. Phase consistency model is adopted to execute the edge detection for the clipped molten pool image and its edge is marked in coarse segmentation region. Then make further segmentation for the marked image and extract the weld pool edge with sobel operator. Comparison and analysis of the related experiments show that this method has good performance in the accuracy and robustness of weld pool edge extraction.
[1] 肖军艳. 环形激光光内送粉熔池特征与熔层性能[D]. 苏州:苏州大学,2009. XIAO Junyan. Study on the characteristics of molten pool based on inside-ring laser coaxial powder feeding and properties of cladding layers[D]. Suzhou:Soochow University,2009.
[2] HOFMAN J T, PATHIRAJ B, VAN DIJK J,et al. A camera based feedback control strategy for the laser cladding process[J]. Journal of Materials Processing Technology,2012,212(11):2455-2462.
[3] IRAVANI-TABRIZIPOUR M, TOYSERKANI E. An image-based feature tracking algorithm for real-time measurement of clad height[J]. Machine Vision and Applications,2007,18(6):343-354.
[4] ARAUJO J R,RODRIGUEZ-ANDINA J J,FARINA J,et el. FPGA-based laser cladding system with increased robustness to optical defects[C]//Conference of the IEEE Industrial Electronics Society. New York:IEEE Industrial Electronics Society,2012:4688-4693.
[5] OCYLOK S,ALEXEEV E,MANN S,et el. Correlations of melt pool geometry and process parameters during laser metal deposition by coaxial process monitoring[C]//Physics Procedia. Amsterdam:Elsevier,2014:228-238.
[6] 于栋,钟敏霖,刘文今,等. 激光熔覆过程中熔池图像的实时检测[J]. 中国激光,2007,34(S1):86-90. YU Dong, ZHONG Minlin, LI Wenjin, et al. Realtime monitoring research of melt pool images in laser cladding process[J]. Chinese Journal of Lasers,2007, 34(S1):86-90.
[7] 杨柳杉. 基于CCD的激光熔覆在线检测系统的开发与应用研究[D]. 长沙:湖南大学,2011. YANG Liushan. Study on CCD-based detection system for laser cladding[D]. Changsha:Hunan University,2011.
[8] NIXON M S,AGUADO A S. 计算机视觉特征提取与图像处理[M]. 李实英,杨高波,译. 北京:电子工业出版社,2014. NIXON M S,AGUADO A S. Feature extraction & image processing for computer vision,third edition[M]. Translated by LI Shiying,YANG Gaobo. Beijing:Publishing House of Electronic Industry,2014.
[9] KOVESI P. Image features from phase congruency[J]. Journal of Computer Vision Research,1999,1(3):1-26.
[10] 李雪非. 基于相位一致性的图像轮廓提取算法研究[D].成都:电子科技大学,2011. LI Xuefei. A contour detection model based on phase congruency[D]. Chengdu:University of Electronic Science and Technology of China,2011.
[11] VENKATESH S,OWENS R. On the classification of image features[J].Pattern Recognition Letters,1990, 11(5):339-349.
[12] FIELD D J. Relations between the statistics of natural images and the response properties of cortical cells[J]. Journal of the Optical Society of America A-Optics Image Science and Vision,1987,4(12):2379-2394.
[13] 郑相锋,王庆,牛晓光. 灰度形态学提取焊接熔池图像边缘技术[J]. 焊接学报,2007,28(1):105-108. ZHENG Xiangfeng, WANG Qing, NIU Xiaoguang. Extracting borderline of CO2 arc welding molten pool image using gray-scale morphology[J]. Transactions of the China Welding Institution,2007,28(1):105-108.
[14] 李静,秦小麟,李芳,等. 基于区域粗定位与Chan-Vese主动轮廓模型的MAG焊视觉图像熔池边缘提取[J]. 机械工程学报,2011,47(12):74-78. LI Jing,QIN Xiaolin,LI Fang,et al. New method based on region coarse localization and Chan-Vese model for weld pool edge extraction in MAG welding[J]. Journal of Mechanical Engineering,2011,47(12):74-78.
