【作者】 马超；

【导师】 赵军；

【作者基本信息】 燕山大学 ， 材料加工工程， 2010， 硕士

【摘要】 自从河北青县巨龙钢管有限公司引进了我国第一条大口径直缝埋弧焊管JCO生产线后,我国开始对管坯JCO成形工艺及相关技术进行了消化及吸收,由于关键技术和设备从国外引进,对管坯成形质量控制及工艺参数调整仅停留在经验层面上,存在着工艺参数调整误差大、人员工作强度大及产品质量波动大等现实情况。为此,本文提出了大口径直缝埋弧焊管JCO成形后管端几何特征识别技术,以实现管端成形质量的检测。本文在板材弯曲智能化控制技术的研究成果基础上,对基于机器视觉的管端矫圆几何特征识别系统的关键问题进行解决。利用机器视觉和传感器技术,开发了基于机器视觉的管端矫圆几何特征识别系统,实现了管端几何特征参数的非接触、高精度的测量。详细研究了管坯端面图像处理和椭圆检测算法,在试验和结果比较基础上,提出了适合管坯端面的图像处理流程。本文用了适合现场使用的正三角形标定方法。在上述研究基础上,利用Visual C++编程语言开发了基于机器视觉的管端矫圆几何特征识别系统软件,主要包括:管坯端面图像处理及椭圆检测、拟合的程序开发。最后利用PCI总线数据采集卡、面阵CCD及相关硬件,完成了基于机器视觉的管端矫圆的几何特征识别的硬件系统开发。利用基于机器视觉的管端矫圆几何特征识别系统进行了物理模拟实验,实验结果表明系统运行稳定,检测精度高。方便和高精度的管端几何形状测量是研究工作的最终成果。更多还原

【Abstract】 Since the first longitudinal-seam submerged arc welded (LSAW) pipes production line with JCO forming process was established in Julong Steel Pipe Co., Ltd, the unfinished pipe forming process and the correlated technology have been investigated by the researchers. Due to the key technology and the forming press from abroad, the systematical basic research on the forming process has not been conducted yet. And the pipe quality and processing parameters adjustment are conducted according to accumulated experience with the characteristics of large error, high personnel working strength and unstable production quality. As one of the effective method to improve the pipe-end quality, the technology of geometric feature recognition of the pipe-end is introduced to detect the pipe quality.Based on the research achievements of the intelligent control technology for the sheet metal bending, the key issue of the geometric feature recognition system of correcting pipe-end based on machine vision is resolved in this paper.Based on machine vision and sensor technology, the geometric feature recognition system of correcting pipe-end based on machine vision is developed, which can measure parameters of geometric feature of the pipe-end with contactless and high precision. The processing algorithms of image pre-processing and ellipse detection, which are simple, efficient and suitable for the pipe-end surface image, are studied in detail. Focused on the live condition, a new camera calibration method has been used to transform the angle in image into the actual angle.Based on these studies, the use of Visual C + + programming language developed the research of the geometric feature recognition system of correcting pipe-end based on machine vision, main contents: tube-end image processing, program development of detection and fitting of the ellipse. At last, employing the portble DAQ card and camera CCD and other hardware, the recognition system of geometric feature of correcting pipe-end based on machine vision is established.The physical simulated experiments have been conducted with the system, which showed that the system operated stably and was high-precision, the punch displacement predicted is reliable. The culmination of the research work is convenient and high-precision measurement of the pipe-end geometry.更多还原