Intelligent System Design For Boom-type Roadheader And Its Pose Estimation And Kinematic Modeling

Coal occupies a dominant position in my country's energy consumption structure.At present,in the process of coal mining,the underground operating environment is harsh,the work efficiency is low,and accidents occur from time to time.Promoting unmanned and intelligent coal mining is the way for the sustainable development of my country's coal industry.Boom-type roadheader is an important equipment in the process of coal mining.Realizing its intelligence helps to improve work efficiency,reduce the number of workers in the tunneling face,and improve the accuracy of roadway forming.This paper designs a system for coal mine excavation and for the intelligence of the cantilever roadheader.Based on this,the pose estimation and kinematics modeling are studied.The main work and conclusions include the following aspects:The working process of the Boom-type roadheader and the characteristics of the coal roadway environment are analyzed,and the overall scheme of the intelligent system of the Boom-type roadheader is proposed.The system includes a UWB-based positioning system,a lidar-based working face perception system,a walking servo system and a cutting servo system.In the positioning system,inertial measurement and laser SLAM are integrated to improve the accuracy of attitude measurement and reduce the positioning error in the vertical direction.A method for estimating the position and attitude of the roadheader based on machine learning is proposed,and the nonlinear mapping relationship between the UWB ranging value and the position and attitude of the roadheader is established.The machine learning model is trained with a self-constructed data set,and the cross-testing experiment verifies that the fitting accuracy of the model meets the requirements.In the actual ranging data experiment,the maximum mean absolute error of the machine learning model's position estimation is 0.13 m,and the maximum mean absolute error of the attitude angle estimation is 3.8°,which can meet the requirements of the roadheader's autonomous walking and autonomous cutting.The kinematics model of the roadheader chassis under the conditions of twodimensional plane,no sideslip,and pure rolling is established,and the simulation experiment of the track tracking of the double kink line is completed,which verifies the correctness of the chassis kinematics model.Based on the improved D-H parameter method,the coordinate system of each connecting rod of the cutting arm is established,and the forward and inverse solutions of the cutting arm kinematics are deduced.correctness of the model.