卷积自编码器和残差循环神经网络在刀具剩余寿命预测中的应用

周学良; 潘晓明; 吴瑶

doi:10.13433/j.cnki.1003-8728.20230229

Chinese

您当前的位置：

首页 >

文章列表页 >

卷积自编码器和残差循环神经网络在刀具剩余寿命预测中的应用

更新时间：2026-04-23

- 卷积自编码器和残差循环神经网络在刀具剩余寿命预测中的应用
- Application of Convolutional Self-Encoder and Residual Recurrent Neural Network in Remaining Life Prediction of Tool
- 机械科学与技术 2025年44卷第5期页码：806-813
- 作者机构：
  
  湖北汽车工业学院机构机械工程学院,湖北,十堰,442002
- 作者简介：
  
  [ "周学良，教授，硕士生导师，博士，" ]
- 基金信息：
  
  湖北省高等学校优秀中青年科技创新团队计划（T2020018）与第64批中国博士后科学基金项目（2018M6409120）
- DOI：10.13433/j.cnki.1003-8728.20230229
  中图分类号：
- 纸质出版：2025
- 稿件说明：
移动端阅览
周学良, 潘晓明, 吴瑶. 卷积自编码器和残差循环神经网络在刀具剩余寿命预测中的应用[J]. 机械科学与技术, 2025,44(5):806-813.

周学良, 潘晓明, 吴瑶. Application of Convolutional Self-Encoder and Residual Recurrent Neural Network in Remaining Life Prediction of Tool[J]. Mechanical Science and Technology for Aerospace Engineering, 2025, 44(5): 806-813.
周学良, 潘晓明, 吴瑶. 卷积自编码器和残差循环神经网络在刀具剩余寿命预测中的应用[J]. 机械科学与技术, 2025,44(5):806-813. DOI： 10.13433/j.cnki.1003-8728.20230229.

周学良, 潘晓明, 吴瑶. Application of Convolutional Self-Encoder and Residual Recurrent Neural Network in Remaining Life Prediction of Tool[J]. Mechanical Science and Technology for Aerospace Engineering, 2025, 44(5): 806-813. DOI： 10.13433/j.cnki.1003-8728.20230229.

摘要

针对刀具剩余寿命预测问题，提出了一种将一维卷积自编码器（One-dimensional convolutional auto encoder，1DCAE）和残差双向门控循环单元（Residual bidirectional gated recurrent unit，RBGRU）相结合的预测方法。通过1DCAE连续卷积池化和反卷积上采样方法获取工况信号的深层特征，并将其与分段后的原始信号融合后作为刀具剩余寿命的表征；同时结合残差网络的思想对双向门控循环单元（Bidirectional gated recurrent unit，BiGRU）的结构进行改进以增强对时序特征的捕获能力。实验结果表明，该方法比其他算法具有更高的预测精度。

Abstract

Focusing on the remaining useful life prediction of cutting tool

a method combining one-dimensional convolutional auto encoder (1DCAE) with residual bidirectional gated recurrent unit (RBGRU) is proposed. The underlying features of the working condition data are obtained by using 1DCAE continuous convolution pooling and deconvolution upsampling methods

and fused with the segmented original signal. And the fused data is used to characterize the remaining life of tool. Meanwhile

the structure of the bidirectional gated recurrent unit (BiGRU) is improved by combining the idea of residual network to enhance the capability of capturing the timing features. The experimental results show that the prediction accuracy of the present method is better than that via the other algorithms.

关键词

Keywords

references

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

改进Faster R-CNN的钢材表面缺陷检测