基于三维激光点云曲率突变的航空发动机进气道异物检测方法  

Method for Detecting Foreign Objects in the Intake Duct of a Three-Dimensional LaserPoint Cloud Aircraft Engine Based on Curvature Mutation

作　　者：武星[1] 李兴达 汤凯 李杨志 张航瑛 陈中文 WU Xing;LI Xingda;TANG Kai;LI Yangzhi;ZHANG Hangying;CHEN Zhongwen(College of Mechanical and Electrical Engineering,Nanjing University of Aeronautics and Astronautics,Nanjing 210016,China;Avionics Department,State-operated Wuhu Machinery Plant,Wuhu 241000,China)

机构地区：[1]南京航空航天大学机电学院,南京210016 [2]国营芜湖机械厂航电部,安徽芜湖241000

出　　处：《计算机测量与控制》2024年第12期67-72,80,共7页Computer Measurement &Control

基　　金：国家自然科学基金面上项目(52475521,61973154);国防基础科研计划重点项目(JCKY2022209B001);江苏高校"青蓝工程"优秀青年骨干教师项目(2022)。

摘　　要：为了解决目前人工巡检航空发动机进气道时存在的准确性差、效率较低等问题,提出一种基于三维激光点云曲率突变的进气道异物检测方法;设计一种基于体素网络的点云数据压缩方法,计算压缩点云数据在进气道深度方向上的曲率变化;利用迭代阈值法计算分割曲率突变点云的动态阈值,通过阈值分割识别曲率突变的异物点云;采用区域生长法将离散的异物点云聚类分割为整体的异物目标;参考航空发动机进气道实物搭建了进气道模拟件测试环境,对3种不同尺寸的异物进行了检测定位,异物识别准确率达到95.4%,异物定位精度达到1.46 cm,实验结果验证了该方法的准确性与高效性。In order to solve the problems of low accuracy and efficiency in manual inspection of aircraft engine intake ducts,a foreign object detection method based on curvature mutation of three-dimensional laser point cloud is proposed for intake ducts.A voxel network-based point cloud data compression method is designed,and the curvature change of the compressed point cloud data is calculated in the depth direction of the inlet.The iterative threshold method is used to calculate the dynamic threshold for segmenting the point cloud of curvature mutation,and the point cloud of foreign object is then identified by means of threshold segmentation for curvature mutation.The region growth method is used to cluster the discrete point cloud of foreign object into the whole foreign object.An analog test environment is constructed for the intake duct of aircraft engine,in which three different sizes of foreign objects are detected and located.The recognition rate for foreign object reaches 95.4%,and the locating accuracy for foreign object reaches 1.46 cm.The experimental results verify the accuracy and efficiency of the method.

关 键 词：异物检测 点云压缩 目标分割 迭代阈值法 区域生长法 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]