基于ILSO-BP神经网络的数控机床主轴热误差建模  

Modeling of Spindle Thermal Error of CNC Machine Tool Based on ILSO-BP Neural Network

作　　者：薛东 袁鑫 王新科 刘宏伟 XUE Dong;YUAN Xin;WANG Xinke;LIU Hongwei(School of Mechanical Engineering,Hubei University of Arts and Science,Xiangyang 441053,China)

机构地区：[1]湖北文理学院机械工程学院,湖北襄阳441053

出　　处：《湖北文理学院学报》2025年第2期23-28,共6页Journal of Hubei University of Arts and Science

基　　金：湖北文理学院科研基金项目(2024pygpzk06)。

摘　　要：为提高数控机床加工精度,以佳时特S7H型数控机床主轴系统为研究对象,构建基于改进狮群算法(ILSO)优化的BP神经网络热误差模型。文章利用基于遗传算法改进的K-means聚类分析和相关分析法,将温度测点从10个减小到5个;结合ILSO算法和BP神经网络算法,在主轴Z向建立ILSO-BP模型。与传统的BP神经网络和LSSVM模型进行对比实验,结果表明:ILSO-BP模型具有精度高和鲁棒性强等优点。In order to improve the machining accuracy of CNC machine tools,a BP neural network thermal error model based on Improved Lion Swarm Optimization Algorithm(ILSO)was proposed,taking the spindle system of Jiashite S7H CNC machine tool as the research object.By using the improved K-means clustering analysis and correlation analysis method based on genetic algorithm,the number of temperature measurement points was reduced from 10 to 5.Combining the optimization ability of ILSO algorithm and the advantages of BP neural network,an ILSO-BP mathematical model was established in the Z-axis direction.Through comparative experiments with traditional BP neural network and LSSVM model,the results showed that the ILSO-BP model has advantages such as high accuracy and strong robustness.

关 键 词：数控机床 主轴热误差 BP神经网络 狮群优化算法 

分 类 号：TG502[金属学及工艺—金属切削加工及机床]