Development Of Steel Arch Positioning System Based On LabVIEW

In the process of TBM tunneling,steel arches are needed to support surrounding rock.At present,the splicing and installation of steel arches mainly rely on manual labor,which requires a large amount of installation work and low efficiency.In order to realize the automatic stitching of steel arches,aiming at the positioning problem in the stitching construction process of TBM steel arches,this paper adopts two schemes of monocular Vision and binocular Vision based on NI Vision and LabVIEW visual software development platform to complete the measurement and positioning of steel arches’ hinge holes,and compares the two schemes.The real-time and cost-effective monocular vision scheme was determined,and a steel arch positioning system based on LabVIEW was designed.This paper mainly includes the following research contents:(1)According to the project requirements and the site environment,two measurement schemes of monocular Vision and binocular Vision are adopted,and the steel arch hinge hole is taken as the location feature point.The image acquisition system is designed,and the selection of each hardware is determined.Based on NI Vision and LabVIEW visual software development platform,the algorithm flow of the scheme is determined.(2)Monocular Vision and Binocular Vision camera models and camera Calibration methods were studied.Monocular Vision camera Calibration was performed using the NI Vision Calibration training interface,Based on the LabVIEW binocular stereo vision calibration system,the binocular camera is used to collect images of the plane target at the same time,and the camera parameters are calculated according to the relationship between the homologous points of the left and right cameras,and the calibration of the binocular vision system is completed;(3)For monocular vision image processing,NCC template matching algorithm is used to match the region of interest where the steel arch hinge hole is located;The edge points of the articulated hole contour were determined based on the gray gradient of one-dimensional pixel sequence.The traditional RANSAC algorithm is improved,and the improved RANSAC elliptical fitting method is used to determine the center of the hinge hole of the steel arch frame to realize the positioning of the steel arch frame.At the same time,a monocular image processing software is designed.(4)For binocular vision images,the processing flow is similar to that of monocular vision.Due to the angle between the binocular vision camera and the splicing section of the steel arch,the imaging results are somewhat different from monocular vision.Aiming at the characteristics of binocular vision images,use the improved NCC template matching with rotation invariance is used to determine the hinged hole,and then the edge is extracted by the improved region growing method,and the center of the hinged hole is determined by ellipse fitting.The feasibility of the image processing algorithm is verified through experiments,and the binocular vision image processing software is designed;(5)The stability and measurement positioning accuracy of the monocular vision and binocular vision systems are verified by experiments.The errors are analyzed and the two schemes are compared at the same time.The experimental results show that the measurement error of the plane movement distance of monocular vision system is ±0.2mm.The measurement error of the binocular vision system’s plane moving distance is ±0.2mm,and the measurement error of the depth direction is ±0.3mm.The stability and measurement accuracy of the steel arch positioning system designed in this paper meet the requirements of the project.