基于响应面模型和BP-神经网络模型的机器人定位误差及验证分析

Robot Positioning Error and Verification Analysis Based on Response Surface Model and BP Neural Network Model

机器人定位精度是衡量工业机器人工作质量的一项重要指标,对零件加工质量有着重要影响。为满足现代工业的制造精度要求,机器人重复定位精度需要进一步提升,因此,通过响应面模型与BP-神经网络模型对机器人定位精度误差进行拟合,对比研究提升机器人重复定位精度的方法。首先建立响应面模型,采用中心复合设计方法,对机器人定位精度误差进行实验仿真,接着用BP-神经网络对机器人定位精度误差进行拟合。经过比对得知,BP-神经网络的拟合精度高于响应面模型,但响应面模型拟合效率高于BP-神经网络。最后借助激光跟踪仪对机器人进行误差补偿验证实验,结果表明,误差模型预测得到的误差值是合理的,验证了仿真的正确性及补偿的可行性。

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.