基于增强特征信息的航空发动机叶片双目视觉测量方法

Binocular vision measurement method of aero engine blade based on enhanced feature information

航空发动机叶片三维面形数据重建是评价发动机叶片加工精度的重要手段.提出一种基于增强特征信息的双目视觉三维重建方法:首先在发动机叶片表面张贴圆形标记以增强叶片表面特征信息;其次通过相机的多角度拍摄获得能够覆盖叶片全貌的图片,并利用圆心特征匹配算法实现左、右图片中对应的圆形标记点的匹配;最后利用双目视觉三维重建原理计算得到三维点云数据,从而重构发动机叶片面形.对重构后的发动机叶片三维数据与白光扫描设备(精度0.05 mm)所得的扫描数据进行对比可得,发动机单叶片的叶背、叶盆的偏差平均值分别为0.1032和-0.1014 mm,标准偏差分别为0.0966和0.0571 mm.

As an important way to evaluate the machining accuracy of aeroengine blades,the reconstruction of three dimensional(3D)surface data of such blades has attracted considerable research attention.In this study,we present a binocular 3D reconstruction method based on enhanced feature information.First,circular marks are posted on the surface of the engine blade to enhance the blade surface feature information.Second,pictures covering the whole picture of the blade are obtained through multi-angle shooting of the cameras.Then,the center feature matching algorithm is used to match corresponding circular markers on the left and right pictures.Finally,the 3D point cloud data are obtained by using the 3D reconstruction principle of binocular vision.The reconstructed 3D data of engine blade can be compared with the scanning data obtained by the commercial white light scanning equipment with the accuracy equaling 0.05 mm.For positive and negative sides of the model,the average deviation equals 0.1032 mm and-0.1014 mm,and the standard deviation equals 0.0966 mm and 0.0571 mm respectively.