欢迎访问机床与液压官方网站!

咨询热线:020-32385312 32385313 RSS EMAIL-ALERT
数控机床主轴的神经网络热评价模型研究
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

基金项目:

北京市科技计划项目课题(D171100005717001)


Research on Neural Network Thermal Evaluation Model for CNC Machine Tool Spindle
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    热误差作为影响机床加工精度的重要因素之一,严重制约着机床加工精度的提高。而主轴是数控机床的关键功能部件,对其进行热特性研究对提高机床的加工精度具有重要的意义。将同一类型、不同使用年限的机床主轴温度值和热变形值作为评价指标,建立数控机床主轴的神经网络热评价模型;针对BP神经网络易陷入局部最优值、收敛速度慢等问题,采用粒子群优化(PSO)算法优化加权朴素贝叶斯(WNB)的初始权值,获取权值全局最优解,构建了粒子群优化加权朴素贝叶斯机床主轴热评价模型,实现对机床主轴热特性的评价。MATLAB仿真结果表明:PSO-WNB模型精度为941%,收敛速度快,预测精度高,优于BP神经网络,为数控机床热特性评价提供了新思路。

    Abstract:

    As one of the important factors affecting the machining accuracy of the machine tool, thermal error seriously restricts the improvement of machine tool machining accuracy. The spindle is a key functional part of the CNC machine tool, and it is of great significance to study its thermal characteristics to improve the machining accuracy of the machine tool. The temperature values and thermal deformation values of the machine tool spindle with the same type and different service life were used as evaluation indexes, and the neural network thermal evaluation model of the CNC machine tool spindle was established. Because BP neural network is easy to fall into local optimum value and the convergence speed is slow, the particle swarm optimization (PSO) algorithm was used to optimize the initial weight of weighted naive Bayesian (WNB), and the global optimal solution of 〖JP2〗weights was obtained. The thermal evaluation model〖JP〗 of the particle swarm optimization weighted naive Bayes machine tool spindle was constructed to realize the spindle thermal characteristics evaluation. The MATLAB simulation results show that the accuracy of PSO-WNB model is 941%, the convergence speed is fast and the prediction accuracy is high, which is better than BP neural network. It provides a new idea for the evaluation of thermal characteristics of CNC machine tools.

    参考文献
    相似文献
    引证文献
引用本文

涂怡蓉,陈秀梅,史晨阳,张世珍.数控机床主轴的神经网络热评价模型研究[J].机床与液压,2020,48(22):24-28.
TU Yirong, CHEN Xiumei, SHI Chenyang, ZHANG Shizhen. Research on Neural Network Thermal Evaluation Model for CNC Machine Tool Spindle[J]. Machine Tool & Hydraulics,2020,48(22):24-28

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2021-04-22
  • 出版日期: