基于RIME-BP神经网络的磨齿机进给系统热误差预测  

Thermal error prediction of gear grinding machine feed system based on RIME-BP neural network

作　　者：肖捷 王志永[1] 于水琴 张宇[1] 薛芮 Xiao Jie;Wang Zhiyong;Yu Shuiqin;Zhang Yu;Xue Rui(College of Mechanical and Intelligent Manufacturing,Central South University of Forestry and Technology,Changsha 410004,China;School of Mechanical Engineering,Hefei University of Technology,Hefei 230009,China)

机构地区：[1]中南林业科技大学机械与智能制造学院,长沙410004 [2]合肥工业大学机械工程学院,合肥230009

出　　处：《仪器仪表学报》2024年第11期277-286,共10页Chinese Journal of Scientific Instrument

基　　金：国家自然科学基金企业创新发展联合基金项目(U22B2084);湖南省重点研发计划项目(2023GK2053);湖南省自然科学基金项目(2024JJ5643)资助。

摘　　要：为了减少热致误差对数控机床进给系统定位精度的影响,提高被加工产品的一致性,提出一种基于霜冰算法(RIME)优化后的BP神经网络热误差预测模型。在不同工况下,布置温度传感器和激光干涉仪以采集温度和丝杆热误差数据。结合模糊C均值聚类和灰色关联度算法对温度样本进行特征选择,筛选出关键温度特征点。以温度和丝杆位置坐标作为输入,丝杆热误差作为输出,构建RIME-BP热误差预测模型。针对H650GA型磨齿机,利用K折交叉验证法对该模型预测精度进行实例验证,并与GA-BP、BP和SVM模型进行对比。结果表明,该模型的平均决定系数R~2高达0.995,相对于GA-BP、BP和SVM模型,分别提高了3.54%、9.58%和17.75%。所提出方法为热误差补偿提供了理论和技术指导,具有工程应用价值。To mitigate the impact of thermal errors on the positioning accuracy of the CNC machine tool feed system and improve the consistency of processed products,a thermal error prediction model based on the RIME-optimized BP neural network is introduced.Temperature sensors and a laser interferometer are arranged under various operating conditions to collect temperature and lead screw thermal error data.Fuzzy C-means clustering and grey relational analysis are applied for feature selection from temperature samples,identifying key temperature feature points.The RIME-BP thermal error prediction model is constructed using temperature and screw position coordinates as inputs and screw thermal error as the output.For the H650GA gear grinding machine,the K-fold cross-validation method is used to validate the model′s prediction accuracy,and compared with GA-BP,BP,and SVM models.The results show that the proposed model′s average coefficient of determination R 2 is as high as 0.995,which is 3.54%,9.58%,and 17.75%higher than GA-BP,BP,and SVM models,respectively.The proposed method provides theoretical and technical guidance for thermal error compensation and holds significant engineering application value.To mitigate the impact of thermal errors on the positioning accuracy of the CNC machine tool feed system and improve the consistency of processed products,a thermal error prediction model based on the RIME-optimized BP neural network is introduced.Temperature sensors and a laser interferometer are deployed under various operating conditions to collect temperature and lead screw thermal error data.Fuzzy C-means clustering and grey relational analysis are applied to select features from temperature samples,identifying key temperature feature points.The RIME-BP thermal error prediction model is constructed using temperature and screw position coordinates as inputs and screw thermal error as the output.For the H650GA gear grinding machine,the K-fold cross-validation method is used to validate the model′s prediction accuracy,wh

关 键 词：热误差预测 进给系统 特征选择 霜冰算法 神经网络 

分 类 号：TH161[机械工程—机械制造及自动化]