悬臂式掘进机位姿测量方法研究  

Research on Pose Measurement Method for Cantilever Roadheader

作　　者：郑瑞东 韩燮[1,2,3] 高波 ZHENG Ruidong;HAN Xie;GAO Bo(School of Computer Science and Technology,North University of China,Taiyuan 030051,China;Shanxi Key Laboratory of Machine Vision and Virtual Reality,North University of China,Taiyuan 030051,China;Shanxi Province’s Vision Information Processing and Intelligent Robot Engineering Research Center,North University of China,Taiyuan 030051,China;Shanxi Keda Automatic Control Co.,Ltd.,Taiyuan 030006,China)

机构地区：[1]中北大学计算机科学与技术学院,山西太原030051 [2]中北大学机器视觉与虚拟现实山西省重点实验室,山西太原030051 [3]中北大学山西省视觉信息处理及智能机器人工程研究中心,山西太原030051 [4]山西科达自控股份有限公司,山西太原030006

出　　处：《中北大学学报（自然科学版）》2024年第6期823-831,共9页Journal of North University of China(Natural Science Edition)

基　　金：山西省自然科学基金资助项目(202203021222027)。

摘　　要：针对复杂地质条件下煤矿巷道施工中悬臂掘进机位姿检测精度的提升难题,本文提出了一种基于激光投影与机器视觉的掘进机位姿检测算法。该算法聚焦于克服高粉尘、强震动环境下位姿测量的不稳定性,确保掘进机的精确导航与控制。测量系统集成了激光发射装置和工业级防爆摄像机,其利用摄像机捕获激光线序列图像,然后通过图像处理技术计算掘进机的航向角,实现行进方向的即时校正。倾角传感器用于协助测量摄像机拍摄时的倾斜角度,同时运用三角测量法来准确测定掘进机的水平位移。该设计采用在掘进过程中随机抽样图像的策略,有效抑制了强震动干扰;同时,高粉尘环境反而增强了激光线亮度,提高了检测性能。通过建立模拟巷道进行了仿真测试,结果表明,该技术在水平位移测量时的航向角误差≤0.5°。通过分析科达自控公司提供的实际矿井数据,证明了算法在真实工况下的稳健性和有效性。与现行技术相比,本算法不仅保持了一定的检测精度,还简化了实施步骤,增强了采矿作业的安全性与效率。In response to the difficulty of improving the accuracy of cantilever roadheader pose measurement in coal mine roadway construction under complex geological conditions,this paper proposed a kind of roadheader pose detection algorithm based on laser projection and machine vision.This algorithm focused on overcoming the instability of pose measurement in high dust and strong vibration environments,and ensured accurate navigation and control of the roadheader.The measurement system integrated a laser emitting device with an industrial grade explosion-proof camera,and the camera captured a sequence of laser line images,then the heading angle of the roadheader was calculated through image processing technology to achieve real-time correction of the travel direction.Inclination angle sensors was used to measure the inclination angle of the camera,and the triangulation method was used to accurately measured the horizontal displacement of the roadheader.The images were randomly sampled during excavation,which was took as the design strategy to effectively suppress strong vibration interference;meanwhile,the high dust environment actually enhanced the brightness of the laser line,which could improve the measurement performance.A simulated tunnel was built to make to simulation test.The results show that theheading angle error of the technology is less than or equal 0.5°in horizontal displacement measurement.The robustness and effectiveness of the algorithm under real working conditions is verified by analyzing the mine data provided by Keda Automation Company.Compared with current technology,this algorithm not only maintains considerable detection accuracy,but also simplifies implementation steps,and enhances the safety and efficiency of mining operations.

关 键 词：悬臂式掘进机 位姿检测 三角测量法 机器视觉 特征提取 

分 类 号：TD672[矿业工程—矿山机电]