摘要
提出了一种基于混合视觉的封严蜂窝磨痕测量数据自适应处理与量化评估方法,考虑蜂窝磨痕的边缘模糊及截面复杂的特性,通过点云和图像的融合分析实现了蜂窝磨痕的自适应识别、特征提取与量化评估。在点云数据中,根据蜂窝结构的先验几何特征,对实测点云进行重新定位与主平面提取,实现测量坐标系与理论坐标系的位姿对齐;在图像数据中,通过图像形态学算法解决蜂窝空洞较多、深孔等干扰下的蜂窝区域精准提取问题,实现划痕几何的量化计算。对多组磨损烧蚀后的蜂窝实测数据测试,能够实现所有划痕的精准辨识,在划痕宽度与深度上与人工测量结果偏差小于5%,识别速度提升7倍以上;结果表明所提出的方法能够利用表面形貌点云数据对碰磨及烧蚀的蜂窝磨痕进行自适应识别与量化评估。
A hybrid vision-based method for adaptive processing and quantitative evaluation of sealing honeycomb scratch measurement data was proposed.Taking into account the characteristics of edge blurring and complex cross-sections in honeycomb scratches,the method integrated point cloud and image data through fusion analysis to achieve adaptive scratch identification,feature extraction,and quantitative evaluation.In point cloud data analysis,the measured point cloud was realigned,and the primary plane was extracted based on the prior geometric features of the honeycomb structure,enabling alignment of the measurement coordinate system with the theoretical coordinate system.In image data analysis,image morphology algorithms were employed to address challenges such as the abundance of honeycomb cavities and deep holes,ensuring precise extraction of the honeycomb regions and quantitative computation of the scratch geometry.Testing on multiple sets of measured data from worn and ablated honeycomb surfaces demonstrated the ability of the proposed method to accurately identify all scratches,with deviations in scratch width and depth measurements being less than 5%compared with manual measurements.Moreover,the identification speed was improved by more than sevenfold.The results indicated that the proposed method effectively utilized surface morphology point cloud data for the adaptive identification and quantitative evaluation of honeycomb scratches caused by wear and ablation.
作者
张鹏飞
徐茂程
赵罡
ZHANG Pengfei;XU Maocheng;ZHAO Gang(Research Institute of Aero-Engine,Beihang University,Beijing 102206,China;School of Mechanical Engineering and Automation,Beihang University,Beijing 102206,China)
出处
《航空动力学报》
北大核心
2025年第8期53-60,共8页
Journal of Aerospace Power
基金
国家科技重大专项(J2022-Ⅶ-0001-0043)。
关键词
封严蜂窝
混合视觉
智能识别
三维测量
点云变换
图像处理
honeycomb seal
hybrid vision
intelligent recognition
three-dimensional measurement
point cloud transformation
image processing
