| Nuclear decommissioning is one of the key applications of nuclear industrial robots,among which intelligent n uclear decommissioning project is the most important.In the nuclear decommissioning project involves a complex nuclear industry decommissioning process,which is a very important one is the surface pollution detection,the test results will affect the dec ommissioning nuclear facilities disposal program implementation.Based on the current research situation of nuclear decommissioning technology,robot technology and surface pollution detection technology at home and abroad,this paper mainly focuses on how to make the detection instrument of the robot arm at the end of the surface of the robot,and to meet the requirement of surface pollution related detection,You can successfully complete the task of surface pollution detection research.The purpose of the research is to design a feasible solution.In this scheme,the line-structured optical scanning system is used to complete the collection of point cloud data on the surface of the test object.After the normal estimation and the point cloud method,whic h is suitable for the surface pollution detection characteristic,the point cloud of the surface where the trajectory is located is obtained.Through the method of point cloud slicing and other methods to plan the robot task space detection trajectory,the robot according to the generated trajectory to complete the detection target surface pollution detection task.In this paper,the radiation characteristics of radioactive pollution sources and the commonly used detection methods,which focus on the pollut ion detection of ? and ?,are mainly studied.Combined with the detection methods of the nuclear reactor and its surrounding auxiliary facilities Site inspection,the object to be tested and the surface pollution detection project specific conditions and needs of the in-depth analysis and summary.The method of DH is used to establish the linkage model of MOTOMAN-MH6 S manipulator to solve its positive kinematics equation.For the traditional method,the inverse kinematics of the manipulator is relatively large,and the traditional BP(Back Propagation)neural network is used In this paper,a BP neural network based on PSO optimization is used to solve the problem of inverse kinematics of the robot.In this paper,the BP neural network based on PSO optimization is used to solve the inverse kinematics of the robot.the study.In order to obtain the detection trajectory of the task space,the surface depth information is scanned in the process of research,and the point cloud data is obtained.After the point cloud data is obtained,Preprocessing,get more conducive to generate the task space detection trajectory point cloud data.And then through the point cloud data surface normal estimation,to be detected on the surface of the normals,through the normal bias algorithm,respectively,for ?,? detection of these two sources of detection distance detection path where the surface of the point cloud The data is processed on the surface point cloud by the point cloud slicing and so on,and finally the trajectory of the t ask space is completed,and the generated trajectory is experimentally verified.In this paper,the surface pollution detection characteristics and the research of nuclear radiation detection method,the kinematics research of manipulator and the trajectory generation in the task space are studied.Based on the C ++ language and the PCL open source library,the algorithm is carried out under the VS2010 platform.Design and implementation,and the experimental results of this paper are verified experimentally.The experimental results show that the detection trajectories generated by the scheme are simulated by ? and ? when the simulated surface is cut on the diameter of 60 cm,70cm,80 cm,90cm and 100 cm.The average efficiency of the detection range was 70.25 % and 81.27%,71.83% and 82.67%,72.41% and 83.24%,73.76% and 84.57%,75.03% and 85.88% respectively,thus verifying the feasibility and effectiveness of the scheme. |
PDF Full Text Request