Method And Application Of Coal Mine Tunnel Arch Surface Reconstruction And Re-Spraying Area Location

Anchor-plate retaining is an engineering retain method for reinforcing rock mass and enhancing the stability of underground structures in tunnels,which can effectively improve the construction environment and increase construction efficiency.Aiming at the problems of low work efficiency,unstable quality,and many potential safety risks caused by manual shotcreting currently used in tunnel shotcreting,this thesis around the development project of shotcreting robots,and conducts research on the 3D reconstruction and re-shotcreting area locating technology involved in the project.This is of great significance for implementing automated shotcreting robots to reduce workers’ construction risks,improve the construction environment,and increase work efficiency.A shotcreting robot needs to reconstruct the arch surface in three dimensions(3D)during the process of spraying a tunnel.To solve this problem,this thesis propose an improved marching cubes(MC)reconstruction method based on a point cloud splice and normal re-orient.First,explosion-proof LIDAR is used to acquire the point cloud data of the tunnel arch,followed by the use of the ICP algorithm,a Pass Through filter,and a Statistical Outlier Removal filter for point cloud splicing,data segmentation,and simplification,respectively.In order to improve the reconstruction accuracy,this thesis adjusted the estimated point cloud normal for normal consistency and obtained the geometric features of the complex point cloud surface.Furthermore,combined with the improved MC algorithm,the 3D reconstruction of the tunnel arch is realized.The experimental results show that the proposed method can reconstruct the 3D model of the tunnel arch surface quickly and accurately,which lays a foundation for further research on a trajectory plan and control strategies.In order to further improve the quality of spraying,a re-shotcreting area localization method based on point cloud feature extraction and segmentation is proposed.Firstly,the simulation experiment environment is set up,and the filler was used as the re-shotcreting area;Then,the Fast Point Feature Histogram(FPFH)based on the Open MP development mode is utilized to extract features of the re-shotcreting area.Simultaneously,the feature region is segmented using the Euclidean clustering algorithm based on smoothness.The extracted features and segmented point cloud blocks are registered using the ICP algorithm to identify the re-shotcreting area;Next,the tunnel arch model is reconstructed,and the identified point clouds are mapped onto the model to verify the effectiveness of the re-shotcrete area identification.Finally,the centroid coordinates of the point clouds are calculated to achieve the locating of the re-shotcreting area.The experimental results show that the algorithm solves the localization problem of the re-shotcreting area on the arch surface of the coal mine tunnel,and proposes an algorithm reference for subsequent experimental optimization.Finally,according to the requirements of the shotcrete craft,the system analysis and design of the shotcreting robot are carried out,including the workflow of the shotcreting robot,the structural design of the robot,and the lidar protection system.The research objectives and the role of the research results were summarized,and the feasibility of the shotcrete manipulator work was verified through a physical experimental environment.