AI-based tool wear prediction with feature selection from sound signal analysis

With the advancement of Industry 4.0, there has been a growing demand for the automation and digitalization of manufacturing processes, including machining. One of the core elements of this evolution is tool wear monitoring. In automated production systems, the condition of tools greatly influences...

Full description

Saved in:
Bibliographic Details
Main Authors: Viet Q. Vu, Tien-Ninh Bui, Minh-Quang Tran
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-08-01
Series:Frontiers in Mechanical Engineering
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fmech.2025.1608067/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849233464687067136
author Viet Q. Vu
Tien-Ninh Bui
Minh-Quang Tran
author_facet Viet Q. Vu
Tien-Ninh Bui
Minh-Quang Tran
author_sort Viet Q. Vu
collection DOAJ
description With the advancement of Industry 4.0, there has been a growing demand for the automation and digitalization of manufacturing processes, including machining. One of the core elements of this evolution is tool wear monitoring. In automated production systems, the condition of tools greatly influences production efficiency, cutting stability, and the quality of machined surfaces. The present study proposes an effective tool condition monitoring system based on cutting sound signature analysis and a machine learning model for milling processes. In the proposed system, the correlation between the sound signal and the tool flank wear under various cutting conditions is investigated. First, the measured sound signals in the milling process are extracted into a series of intrinsic mode functions (IMFs) using the ensemble empirical mode decomposition (EEMD). Hilbert transform (HT) is then applied to each IMF to generate the respective instantaneous frequencies, and the most significant statistic features correlated to the tool wear are selected using the collinearity diagnostics. Finally, an artificial neural network (ANN) model is designed to estimate tool wear levels. Experimental results confirm that the developed approach maintains excellent accuracy in tool wear prediction across of various cutting conditions. Moreover, the proposed approach has the potential to be implemented in practical applications as a cost-effective method for tool condition monitoring.
format Article
id doaj-art-44bbe543f1324f8b9d2a478f90dfec64
institution Kabale University
issn 2297-3079
language English
publishDate 2025-08-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Mechanical Engineering
spelling doaj-art-44bbe543f1324f8b9d2a478f90dfec642025-08-20T05:32:35ZengFrontiers Media S.A.Frontiers in Mechanical Engineering2297-30792025-08-011110.3389/fmech.2025.16080671608067AI-based tool wear prediction with feature selection from sound signal analysisViet Q. Vu0Tien-Ninh Bui1Minh-Quang Tran2Department of Engineering and Technology, International Training Faculty, Thai Nguyen University of Technology, Thai Nguyen, VietnamDepartment of Mechanical Engineering, TUETECH University, Thai Nguyen, VietnamDepartment of Mechanical Engineering, TUETECH University, Thai Nguyen, VietnamWith the advancement of Industry 4.0, there has been a growing demand for the automation and digitalization of manufacturing processes, including machining. One of the core elements of this evolution is tool wear monitoring. In automated production systems, the condition of tools greatly influences production efficiency, cutting stability, and the quality of machined surfaces. The present study proposes an effective tool condition monitoring system based on cutting sound signature analysis and a machine learning model for milling processes. In the proposed system, the correlation between the sound signal and the tool flank wear under various cutting conditions is investigated. First, the measured sound signals in the milling process are extracted into a series of intrinsic mode functions (IMFs) using the ensemble empirical mode decomposition (EEMD). Hilbert transform (HT) is then applied to each IMF to generate the respective instantaneous frequencies, and the most significant statistic features correlated to the tool wear are selected using the collinearity diagnostics. Finally, an artificial neural network (ANN) model is designed to estimate tool wear levels. Experimental results confirm that the developed approach maintains excellent accuracy in tool wear prediction across of various cutting conditions. Moreover, the proposed approach has the potential to be implemented in practical applications as a cost-effective method for tool condition monitoring.https://www.frontiersin.org/articles/10.3389/fmech.2025.1608067/fullAI-based tool wear predictionartificial neural networkfeature selectionsound signal analysisintrinsic mode functions
spellingShingle Viet Q. Vu
Tien-Ninh Bui
Minh-Quang Tran
AI-based tool wear prediction with feature selection from sound signal analysis
Frontiers in Mechanical Engineering
AI-based tool wear prediction
artificial neural network
feature selection
sound signal analysis
intrinsic mode functions
title AI-based tool wear prediction with feature selection from sound signal analysis
title_full AI-based tool wear prediction with feature selection from sound signal analysis
title_fullStr AI-based tool wear prediction with feature selection from sound signal analysis
title_full_unstemmed AI-based tool wear prediction with feature selection from sound signal analysis
title_short AI-based tool wear prediction with feature selection from sound signal analysis
title_sort ai based tool wear prediction with feature selection from sound signal analysis
topic AI-based tool wear prediction
artificial neural network
feature selection
sound signal analysis
intrinsic mode functions
url https://www.frontiersin.org/articles/10.3389/fmech.2025.1608067/full
work_keys_str_mv AT vietqvu aibasedtoolwearpredictionwithfeatureselectionfromsoundsignalanalysis
AT tienninhbui aibasedtoolwearpredictionwithfeatureselectionfromsoundsignalanalysis
AT minhquangtran aibasedtoolwearpredictionwithfeatureselectionfromsoundsignalanalysis