滚子表面浅磁痕图像处理技术  

Image Processing Technology for Shallow Magnetic Marks on Roller Surfaces

作　　者：杨艳 陈於学[1,2] YANG Yan;CHEN Yuxue(School of Mechanical Science and Engineering,Huazhong University of Science and Technology,Wuhan 430074,China;State Key Laboratory of Precision Instruments,Huazhong University of Science and Technology,Wuhan 430074,China)

机构地区：[1]华中科技大学机械科学与工程学院,武汉430074 [2]华中科技大学.精密仪器国家重点实验室,武汉430074

出　　处：《轴承》2025年第5期33-39,共7页Bearing

摘　　要：针对轴承滚子磁粉检测时表面浅磁痕易漏检的问题,提出一种浅磁痕图像处理方法,使用梯度强化算子提高浅磁痕的对比度,通过双阈值延伸算法去除弱噪声并保留浅磁痕中的弱像素,基于线性度特征提取线状的浅磁痕,将共线的浅磁痕连接实现浅磁痕检测。试验结果表明,该方法能够准确识别轴承滚子表面的浅磁痕。Aimed at the problem of easy missed testing of shallow magnetic marks on bearing roller surfaces during magnetic particle testing,an image processing method for shallow magnetic marks is proposed.The gradient enhancement operator is used to improve the contrast of shallow magnetic marks,and the dual threshold extension algorithm is used to remove the weak noise and preserve the weak pixels in shallow magnetic marks.The linear shallow magnetic marks are extracted based on linearity characteristics,and the collinear shallow magnetic marks are connected to realize the testing of shallow magnetic marks.The test results demonstrate that the method can accurately identify the shallow magnetic marks on bearing roller surfaces.

关 键 词：滚动轴承 滚子 磁粉检测 机器视觉 磁痕 图像处理 

分 类 号：TH133.33[机械工程—机械制造及自动化] TG115.284[金属学及工艺—物理冶金]