|国家科技期刊平台
| 注册
首页|期刊导航|光学精密工程|基于改进GRU神经网络的刀具磨损状态预测

基于改进GRU神经网络的刀具磨损状态预测

CHAO Yuan ZHANG Junjie TAN Qifeng ZHANG Yijun DAI Guohong XIA Zhijie ZHANG Zhisheng

光学精密工程2025，Vol.33Issue(23)：3765-3783,19.
✕
光学精密工程2025，Vol.33Issue(23)：3765-3783,19.DOI:10.37188/OPE.20253323.3765

基于改进GRU神经网络的刀具磨损状态预测

Tool wear state prediction based on improved GRU neural network

CHAO Yuan 1ZHANG Junjie 2TAN Qifeng 2ZHANG Yijun 2DAI Guohong 2XIA Zhijie 3ZHANG Zhisheng3

作者信息

  • 1. School of Mechanical Engineering,Jiangsu University of Technology,Changzhou 213001,China||School of Mechanical Engineering,Southeast University,Nanjing 211189,China||Jiangsu Nangao High-end CNC Machine Tools and Complete Equipment Manufacturing Industry Innovation Center,Nanjing 211189,China
  • 2. School of Mechanical Engineering,Jiangsu University of Technology,Changzhou 213001,China
  • 3. School of Mechanical Engineering,Southeast University,Nanjing 211189,China||Jiangsu Nangao High-end CNC Machine Tools and Complete Equipment Manufacturing Industry Innovation Center,Nanjing 211189,China
  • 折叠

摘要

Abstract

To address the challenges of cumbersome signal feature extraction in traditional intelligent moni-toring methods and the adverse effects of tool wear on workpiece quality and production efficiency during milling,a tool wear state prediction method based on an improved GRU neural network(BiGRU-1 DCNN-CBAM)is proposed.Using statistical methods,time-domain analysis,frequency-domain analy-sis,and wavelet transform,24 feature parameters of the tool signals-such as mean,kurtosis,and power spectral density-are extracted,and the resulting multimodal time-series data are converted into time-series images of tool features.A convolutional neural network(CNN)is then introduced to mine deep features of the signal data,and a convolutional block attention module(CBAM)is integrated to enhance the capa-bility of the model to capture feature maps of vibration and cutting force signals.After flattening and con-catenating the feature layers,the fused features are fed into a bidirectional GRU(BiGRU)to capture long-term dependencies,and the tool wear amount is predicted through a fully connected layer,thereby en-abling remaining useful life prediction of the tool wear state during CNC machining.Experimental results on the PHM2010 dataset show that the RMSE and MAE of the proposed model are 2.17 μm and 1.29 μm,respectively.Compared with Bayesian-MCMC-Prognostics,SBiLSTM,RIME-CNN-SVM,Mo-bileNetV3,TDConvLSTM,ISABO-IBiLSTM,IWOA-IECA-BiLSTM,and LSTM-CNN-CBAM models,the prediction accuracy in terms of RMSE and MAE is improved by more than 40.5%and 52.1%,respectively,while the time consumption is reduced by at least 2.8%relative to similar models.These results demonstrate that the proposed model can effectively characterize tool wear,reduce predic-tion errors,and achieve superior prediction performance.

关键词

刀具磨损/深度学习/卷积神经网络(CNN)/门控循环单元(GRU)/注意力模块/状态预测

Key words

tool wear/deep learning/Convolutional Neural Network(CNN)/Gate Recurrent Unit(GRU)/attention module/state prediction

分类

信息技术与安全科学

引用本文复制引用

CHAO Yuan,ZHANG Junjie,TAN Qifeng,ZHANG Yijun,DAI Guohong,XIA Zhijie,ZHANG Zhisheng..基于改进GRU神经网络的刀具磨损状态预测[J].光学精密工程,2025,33(23):3765-3783,19.

基金项目

国家自然科学基金资助项目(No.51905235) （No.51905235）

江苏省自然科学基金资助项目(No.BK20191037) （No.BK20191037）

江苏高校"青蓝工程"项目(No.KYQ23002) （No.KYQ23002）

光学精密工程

OA北大核心

1004-924X

访问量0
|
下载量0
段落导航相关论文