基于神经网络的宏/微双驱动运动平台误差预测及补偿技术研究

Research on the Technology of Error Prediction and Compensation for Macro/Micro Dual Drive Motion Platform Using Neural Network

宏/微双驱动平台是一种用于微切削加工的高精度切削平台,其定位精度受多种因素影响。为提高宏/微双驱动定位运动平台的定位精度,提出基于BP神经网络进行宏/微双驱动运动平台定位误差预测的方法。测量运动平台的定位精度,从而建立BP神经网络误差预测模型,并运用该模型对宏/微双驱动运动平台进行定位误差预测试验,最终证明BP神经网络定位误差预测模型精度高、抗变换性能好,适用于对宏/微双驱动运动平台的定位误差进行误差预测及补偿,使得宏/微双驱动平台达到10nm级精度设计要求。

Macro/micro dual drive platform is a high precision cutting platform for micro machining,and its positioning accuracy is affected by many factors.In order to improve the positioning precision of macro/micro dual drive positioning platform,the positioning error prediction method of macro/micro dual drive motion platform based on BP neural networkis proposed.First,we measure the positioning accuracy of motion platform,and establish the error prediction model of BP neural network,and then the model is used to predict the positioning error for the macro/micro dual drive motion platform.Finally,the BP neural network positioning error prediction modelisproved to have high precision and good resistance transformation,and this model can be used to predict and compensate the positioning error of macro/micro dual drive motion platform,making the macro/micro dual drive platform achieve the design requirementsaccuracy of 10nm.