基于机器视觉的沉头孔质量检测方法

Quality inspection method of counterbore based on machine vision

针对沉头孔质量的检测效率低下和检测精度不稳定等问题,提出一种基于机器视觉的沉头孔质量检测方法。该方法使用工业相机采集沉头孔图像,并用高斯滤波等方法处理图像并提取所需特征值;通过建立沉头孔的平行投影计算模型得到其垂直度法矢偏差与锪窝深度的计算公式,结合透视投影计算模型对透视畸变引起的误差进行修正;最后,为验证方法的有效性进行测量试验。试验结果表明,该检测方法测得沉头孔垂直度矢量偏差的误差约为0.04°,锪窝深度的误差约为0.03 mm。

Aiming at the problems of low inspection efficiency and unstable inspection accuracy of counterbore quality,a quality inspection method of countersunk hole based on machine vision was proposed.In this method,the image of counterbore is collected by an industrial camera,and the image is processed by Gaussian filtering and the required eigenvalues are extracted.By establishing the mathematical model of parallel projection of counterbore and modifying it with perspective projection,the vertical normal vector deviation and dimple depth of countersunk hole are obtained.Finally,the measurement test is carried out to verify the effectiveness of the method.The test results show that the error of verticality vector deviation is about 0.04°and the error of dimple depth is about 0.03 mm,which can meet the engineering requirements.