Research on Tool Wear Prediction Based on Deep Residual Network

DOI

10.2991/iwmecs-18.2018.68How to use a DOI?

Keywords

Tool wear, convolutional neural network, residual network.

Abstract

The convolution neural network with deep residual network structure is applied to the prediction of milling tool wear, and the high prediction accuracy is obtained. Based on the data set of the 2010 PHM data competition, this paper constructs 64000 data samples from the total life cycle wear data of three milling tools. Then a 12-layer deep residual network is trained based on these data. Compared with the classical signal analysis method, this method is more convenient for modeling and application because no signal feature extraction is needed, and the generalization ability of the model is better.

Copyright

© 2018, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Kai Tang
AU  - Xiaodong Wang
AU  - Wenzhi Hu
AU  - Yuan Yang
PY  - 2018/04
DA  - 2018/04
TI  - Research on Tool Wear Prediction Based on Deep Residual Network
BT  - Proceedings of the 2018 3rd International Workshop on Materials Engineering and Computer Sciences (IWMECS 2018)
PB  - Atlantis Press
SP  - 314
EP  - 318
SN  - 2352-538X
UR  - https://doi.org/10.2991/iwmecs-18.2018.68
DO  - 10.2991/iwmecs-18.2018.68
ID  - Tang2018/04
ER  -