Milling Cutter Wear Prediction Based on Feature Extraction and LongShort-term Memory Neural Networks

The wear of milling cutters during high-speed milling processes affects the quality of the work-piece, productivity and manufacturing costs. Accurate tool wear prediction can therefore optimize production decisions and avoid losses due to tool wear. To improve the prediction precision, this paper pr...

Full description

Saved in:
Bibliographic Details
Main Authors: ZHOU Chengpeng, WANG Weijun, HOU Zhicheng, FENG Wei
Format: Article
Language:zho
Published: Editorial Office of Control and Information Technology 2021-01-01
Series:Kongzhi Yu Xinxi Jishu
Subjects:
Online Access:http://ctet.csrzic.com/thesisDetails#10.13889/j.issn.2096-5427.2021.04.100
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849224891589459968
author ZHOU Chengpeng
WANG Weijun
HOU Zhicheng
FENG Wei
author_facet ZHOU Chengpeng
WANG Weijun
HOU Zhicheng
FENG Wei
author_sort ZHOU Chengpeng
collection DOAJ
description The wear of milling cutters during high-speed milling processes affects the quality of the work-piece, productivity and manufacturing costs. Accurate tool wear prediction can therefore optimize production decisions and avoid losses due to tool wear. To improve the prediction precision, this paper proposes a method for predicting the wear of milling tools based on feature extraction and long short-term memory neural networks. By extracting the time domain features, frequency domain features and time-frequency domain features based on time series data generated during industrial processes, and using long short-term memory neural networks to learn the complex mapping relationship between the extracted features and the wear amount, it infer the future wear of the milling cutter. Experimental results show that this method reduces mean square error by 67.07% and 41.31% compared with the SVR model and the BPNN model respectively, and reduces mean square error by 77.09% and mean absolute percentage error by 5.685% compared with the CNN, enables a more accurate and reliable milling cutter wear prediction.
format Article
id doaj-art-8e4c81ded685481fab51723fe032b29d
institution Kabale University
issn 2096-5427
language zho
publishDate 2021-01-01
publisher Editorial Office of Control and Information Technology
record_format Article
series Kongzhi Yu Xinxi Jishu
spelling doaj-art-8e4c81ded685481fab51723fe032b29d2025-08-25T06:50:05ZzhoEditorial Office of Control and Information TechnologyKongzhi Yu Xinxi Jishu2096-54272021-01-0138596582317412Milling Cutter Wear Prediction Based on Feature Extraction and LongShort-term Memory Neural NetworksZHOU ChengpengWANG WeijunHOU ZhichengFENG WeiThe wear of milling cutters during high-speed milling processes affects the quality of the work-piece, productivity and manufacturing costs. Accurate tool wear prediction can therefore optimize production decisions and avoid losses due to tool wear. To improve the prediction precision, this paper proposes a method for predicting the wear of milling tools based on feature extraction and long short-term memory neural networks. By extracting the time domain features, frequency domain features and time-frequency domain features based on time series data generated during industrial processes, and using long short-term memory neural networks to learn the complex mapping relationship between the extracted features and the wear amount, it infer the future wear of the milling cutter. Experimental results show that this method reduces mean square error by 67.07% and 41.31% compared with the SVR model and the BPNN model respectively, and reduces mean square error by 77.09% and mean absolute percentage error by 5.685% compared with the CNN, enables a more accurate and reliable milling cutter wear prediction.http://ctet.csrzic.com/thesisDetails#10.13889/j.issn.2096-5427.2021.04.100prediction controllong short-term memory neural network(LSTM)tool weartime series datafeature extraction
spellingShingle ZHOU Chengpeng
WANG Weijun
HOU Zhicheng
FENG Wei
Milling Cutter Wear Prediction Based on Feature Extraction and LongShort-term Memory Neural Networks
Kongzhi Yu Xinxi Jishu
prediction control
long short-term memory neural network(LSTM)
tool wear
time series data
feature extraction
title Milling Cutter Wear Prediction Based on Feature Extraction and LongShort-term Memory Neural Networks
title_full Milling Cutter Wear Prediction Based on Feature Extraction and LongShort-term Memory Neural Networks
title_fullStr Milling Cutter Wear Prediction Based on Feature Extraction and LongShort-term Memory Neural Networks
title_full_unstemmed Milling Cutter Wear Prediction Based on Feature Extraction and LongShort-term Memory Neural Networks
title_short Milling Cutter Wear Prediction Based on Feature Extraction and LongShort-term Memory Neural Networks
title_sort milling cutter wear prediction based on feature extraction and longshort term memory neural networks
topic prediction control
long short-term memory neural network(LSTM)
tool wear
time series data
feature extraction
url http://ctet.csrzic.com/thesisDetails#10.13889/j.issn.2096-5427.2021.04.100
work_keys_str_mv AT zhouchengpeng millingcutterwearpredictionbasedonfeatureextractionandlongshorttermmemoryneuralnetworks
AT wangweijun millingcutterwearpredictionbasedonfeatureextractionandlongshorttermmemoryneuralnetworks
AT houzhicheng millingcutterwearpredictionbasedonfeatureextractionandlongshorttermmemoryneuralnetworks
AT fengwei millingcutterwearpredictionbasedonfeatureextractionandlongshorttermmemoryneuralnetworks