基于深度卷积神经网络的刀具寿命动态预测研究
作者:
作者单位:

太原科技大学

作者简介:

通讯作者:

中图分类号:

TP391.7

基金项目:

国家自然科学基金项目(面上项目,重点项目,重大项目) 51675363


Research on Dynamic Prediction of Tool Life Based on Deep Convolutional Neural Network
Author:
Affiliation:

Taiyuan University of Science and Technology

Fund Project:

The National Natural Science Foundation of China (General Program, Key Program, Major Research Plan) 51675363

  • 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:

    摘 要:刀具寿命预测对提高工件的加工精度与生产的加工效率具有重要意义.同工况同型号下刀具监测信号数据分布不一致,导致历史寿命预测模型对刀具寿命预测效果有限.文中提出一种基于深度卷积神经网络(DCNN)的刀具寿命动态预测方法.首先,利用DCNN挖掘历史刀具监测信号的退化趋势特征,构建刀具寿命预测模型,并加入注意力机制对DCNN输出进行加权,加强对刀具寿命特征的学习,提高寿命预测准确度;其次,通过基于KL散度对刀具监测信号数据分布不一致进行检测,从而在已有刀具寿命预测模型的基础上进行更新迭代;最后,利用迭代后的模型再次进行刀具寿命预测.该方法更好体现了刀具实际加工过程对刀具寿命的影响.以铣削数据集为例,验证了该方法的有效性.

    Abstract:

    Abstract:Tool life prediction is of great significance for improving the machining accuracy of workpieces and the processing efficiency of production. The data distribution of tool monitoring signals under the same working conditions and models is inconsistent, resulting in the limited effect of historical life prediction models on tool life prediction. This paper proposes a dynamic tool life prediction method based on deep convolutional neural network (DCNN). First,Use DCNN to mine the degradation trend characteristics of historical tool monitoring signals, build a tool life prediction model, and add an attention mechanism to weight the DCNN output to strengthen the tool life characteristics Learn to improve the accuracy of life prediction; Secondly, By detecting the inconsistency of the tool monitoring signal data distribution based on the KL divergence, iteratively update and iterate on the basis of the existing tool life prediction model; Finally, Use the iterated model to perform tool life prediction again. The method better reflects the influence of the actual machining process of the tool on the tool life. Taking the milling data set as an example, the effectiveness of the method is verified.

    参考文献
    相似文献
    引证文献
引用本文
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:2020-11-05
  • 最后修改日期:2021-05-21
  • 录用日期:2021-06-03
  • 在线发布日期: 2021-07-01
  • 出版日期: