基于机器视觉的涡轮尺寸测量技术研究  

Technical Research of Turbine Size Measurement Based on Machine Vision

作　　者：刘时言 侯永涛[1] 袁浩[1] 王渊 Liu Shiyan;Hou Yongtao;Yuan Hao;Wang Yuan(School of Mechanical Engineering,Jiangsu University,Zhenjiang,Jiangsu 212013,China)

机构地区：[1]江苏大学机械工程学院,江苏省镇江市212013

出　　处：《工具技术》2024年第12期147-152,共6页Tool Engineering

摘　　要：针对铝铸件涡轮尺寸人工测量方式存在效率低、成本高的问题,提出了一种基于机器视觉的涡轮尺寸测量方法。在Halcon中完成对相机的标定,对图像进行RGB转灰度处理,通过灰度值增强来增加图像对比度,采用改进的双边滤波进行降噪处理。应用基于改进的Sobel梯度模板的Canny算法来提取边缘信息,以提高边缘的定位精度,并完成对图像边缘的检测。结合相机内外参数,将图像坐标信息转换到世界坐标系中得到相应尺寸。实验结果表明,基于本文算法的测量精度可达±0.003mm,符合工业要求标准。Aiming at the problems of low efficiency and high cost of manual measurement of aluminum casting turbine size,a turbine size measurement method based on machine vision is proposed.The camera is calibrated in Halcon,the image is processed from RGB to gray level,the image contrast is increased by gray value enhancement,and the improved bilateral filter is used for noise reduction.Canny algorithm based on improved Sobel gradient template is applied to extract edge information to improve edge positioning accuracy and complete image edge detection.Finally,according to the internal and external parameters of the camera,the image coordinate information is converted into the world coordinate system,and the corresponding size is obtained.The experimental results show that the measurement accuracy based on the proposed algorithm can reach±0.003mm,which is in line with the industrial standard.

关 键 词：涡轮 双边滤波 CANNY算法 

分 类 号：TG27[金属学及工艺—铸造] TH161.1[机械工程—机械制造及自动化]