Abstract：A set of surface defect inspection system for hot heavy rail was designed, and the character of radiation in high temperature for hot heavy rail was analyzed. As for hardware of the system, six linear CCDs have been adopted to shoot the heavy rail from multi-angle, so that the various surface images could be attained, and multi-channel of images were transmitted to image processing workstation in real time. On this basis, frequent defect for hot heavy rail was presented, the key technique for hot heavy rail was studied, and distinguishing and locating the defect was realized.
［1］ 胡亮,段发阶,丁克勤,叶声华. 基于线阵CCD钢板表面缺陷在线检测系统的研究［J］. 计量学报,2005,26(3):200-203.
［2］ 叶苏茹,胡治民,欧阳奇,等. 基于机器视觉的重轨表面缺陷检测系统的研究［J］. 现代制造工程, 2007, (8): 89-94.
［3］ Ngan C C, Tam H Y. A non-contact technique for the on-site inspection of molds and dies polishing［J］. Journal of Materials Processing Technology, 2004, 155(30): 1184-1188. ［4］ 董永刚,张文志,宋剑锋. 钢轨万能轧制过程轨头宽展规律的理论和实验研究［J］. 中国机械工程,2009,20(8):1004-1007.
［5］ 杨桢,张士成,杨立.非朗伯体红外测温计算研究［J］. 光谱学与光谱分析, 2010,30(8): 2093-2097.
［6］ Shin D, Han C, Moon Y S. Ball stdu inspection system using machine vision［J］. ISA Transactions, 2002,41(1):3-11.
［7］ 陈涛. 热态重轨表面缺陷在线检测系统关键技术研究［D］. 重庆:重庆大学,2011.
［8］ Sun T H, Tseng C C, Chen M S. Electric contacts inspection using machine vision［J］. Image and Vision Computing , 2010,28(6):890-901.
［9］ 徐正光,鲍东来,张利欣. 基于递归的二值图像连通域像素标记算法［J］, 计算机工程, 2006,32(24):186-189.
2013, Vol. 34 
