Robot Positioning Error and Verification Analysis Based on Response Surface Model and BP Neural Network Model
Robot positioning accuracy is an important indicator for measuring the quality of work of industrial robot and has a significant impact on the quality of part processing.In order to meet the requirements for manufacturing accuracy of modern industry,the repetitive positioning accuracy of robots needs to be further improved.In this paper,the response surface model and BP neural network model are used to fit the positioning accuracy error of robots,and a comparative study is conducted to improve the repetitive positioning accuracy.Firstly,a response surface model is established,and the central composite design method is used to experimentally simulate the positioning accuracy error of the robot.Then,BP neural network model is used to fit the positioning accuracy error of the robot.After comparison,it was found that the fitting accuracy of BP neural network model is higher than that of response surface model,but the fitting efficiency of response surface model is higher than that of BP neural network model.Finally,an error compensation verification experiment was conducted on the robot by using a laser tracker.The results show that the error value predicted by the error model is reasonable,which verified the correctness of the simulation and the feasibility of compensation.
NETL
NSTL
万方数据
