Milling Tool Wear Prediction Method Based on Deep Learning Under Variable Working Conditions

Tool wear prediction is essential to ensure part quality and machining efficiency. Tool wear is affected by factors such as the material, structure, process, and processing time of the parts. Tool wear under the variable working conditions and the above factors show a complex coupling and timing cor...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Mingwei Wang, Jingtao Zhou, Jing Gao, Ziqiu Li, Enming Li
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2020
Materias:	Variable working conditions tool wear prediction long short-term memory stacked auto-encoder Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/620c6b92ee5146e18691fe0ee1546192
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:620c6b92ee5146e18691fe0ee1546192
record_format	dspace
spelling	oai:doaj.org-article:620c6b92ee5146e18691fe0ee15461922021-11-19T00:06:17ZMilling Tool Wear Prediction Method Based on Deep Learning Under Variable Working Conditions2169-353610.1109/ACCESS.2020.3010378https://doaj.org/article/620c6b92ee5146e18691fe0ee15461922020-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9144206/https://doaj.org/toc/2169-3536Tool wear prediction is essential to ensure part quality and machining efficiency. Tool wear is affected by factors such as the material, structure, process, and processing time of the parts. Tool wear under the variable working conditions and the above factors show a complex coupling and timing correlation, which makes it challenging to predict tool wear under variable working conditions. This article aims to resolve this issue. First, we establish a unified representation of working condition factors. The stacked autoencoder (SAE) model adaptively extracts tool wear features from the machining signal. The extracted wear features and respective working conditions then combine into a working condition feature sequence for predicting tool wear. Finally, the advantages of the long short-term memory (LSTM) model to solve memory accumulation effects learn the regular wear pattern of the working condition feature sequence to realize the prediction of the tool wear. An experiment illustrates the effectiveness of the proposed method.Mingwei WangJingtao ZhouJing GaoZiqiu LiEnming LiIEEEarticleVariable working conditionstool wear predictionlong short-term memorystacked auto-encoderElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 8, Pp 140726-140735 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	Variable working conditions tool wear prediction long short-term memory stacked auto-encoder Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Variable working conditions tool wear prediction long short-term memory stacked auto-encoder Electrical engineering. Electronics. Nuclear engineering TK1-9971 Mingwei Wang Jingtao Zhou Jing Gao Ziqiu Li Enming Li Milling Tool Wear Prediction Method Based on Deep Learning Under Variable Working Conditions
description	Tool wear prediction is essential to ensure part quality and machining efficiency. Tool wear is affected by factors such as the material, structure, process, and processing time of the parts. Tool wear under the variable working conditions and the above factors show a complex coupling and timing correlation, which makes it challenging to predict tool wear under variable working conditions. This article aims to resolve this issue. First, we establish a unified representation of working condition factors. The stacked autoencoder (SAE) model adaptively extracts tool wear features from the machining signal. The extracted wear features and respective working conditions then combine into a working condition feature sequence for predicting tool wear. Finally, the advantages of the long short-term memory (LSTM) model to solve memory accumulation effects learn the regular wear pattern of the working condition feature sequence to realize the prediction of the tool wear. An experiment illustrates the effectiveness of the proposed method.
format	article
author	Mingwei Wang Jingtao Zhou Jing Gao Ziqiu Li Enming Li
author_facet	Mingwei Wang Jingtao Zhou Jing Gao Ziqiu Li Enming Li
author_sort	Mingwei Wang
title	Milling Tool Wear Prediction Method Based on Deep Learning Under Variable Working Conditions
title_short	Milling Tool Wear Prediction Method Based on Deep Learning Under Variable Working Conditions
title_full	Milling Tool Wear Prediction Method Based on Deep Learning Under Variable Working Conditions
title_fullStr	Milling Tool Wear Prediction Method Based on Deep Learning Under Variable Working Conditions
title_full_unstemmed	Milling Tool Wear Prediction Method Based on Deep Learning Under Variable Working Conditions
title_sort	milling tool wear prediction method based on deep learning under variable working conditions
publisher	IEEE
publishDate	2020
url	https://doaj.org/article/620c6b92ee5146e18691fe0ee1546192
work_keys_str_mv	AT mingweiwang millingtoolwearpredictionmethodbasedondeeplearningundervariableworkingconditions AT jingtaozhou millingtoolwearpredictionmethodbasedondeeplearningundervariableworkingconditions AT jinggao millingtoolwearpredictionmethodbasedondeeplearningundervariableworkingconditions AT ziqiuli millingtoolwearpredictionmethodbasedondeeplearningundervariableworkingconditions AT enmingli millingtoolwearpredictionmethodbasedondeeplearningundervariableworkingconditions
_version_	1718420611904045056

Milling Tool Wear Prediction Method Based on Deep Learning Under Variable Working Conditions

Ejemplares similares