PARK, Jin Ho ;YOON, Hae-Sung .
Tool wear estimation under different feed conditions via cutting force coefficients derived from cutting power consumption.
Articles in Press, [S.l.], v. 0, n.0, p. , september 2026.
ISSN 0039-2480.
Available at: <https://www.sv-jme.eu/article/tool-wear-estimation-under-different-feed-conditions-via-cutting-force-coefficients-derived-from-cutting-power-consumption/>. Date accessed: 10 nov. 2026.
doi:http://dx.doi.org/.
Park, J., & Yoon, H.
(0).
Tool wear estimation under different feed conditions via cutting force coefficients derived from cutting power consumption.
Articles in Press, 0(0), .
doi:http://dx.doi.org/
@article{.,
author = {Jin Ho Park and Hae-Sung Yoon},
title = {Tool wear estimation under different feed conditions via cutting force coefficients derived from cutting power consumption},
journal = {Articles in Press},
volume = {0},
number = {0},
year = {0},
keywords = {},
abstract = {This study proposes a compact power consumption-based framework for estimating flank wear width (VB) in full-slot end-milling of Ti-6Al-4V under various feed conditions, without the need for additional sensors such as a dynamometer or accelerometer. Although extensive research has been conducted on tool wear, most existing approaches rely on data acquired under fixed process conditions, which limits their adaptability to varying process conditions. While some machine learning-based methods have been proposed to address this issue, their practical application in industry is often constrained by the need for large, labeled datasets. Therefore, a robust and low-order modeling approach requiring minimal calibration is desirable for practical deployment. This study proposes a simple analytical modeling framework that accounts for the influence of process conditions on tool wear by estimating cutting force coefficients from cutting power consumption. This enables practical implementation using readily available machine-tool signals. Milling experiments were conducted on titanium alloys at spindle speeds of 800, 1025, and 1250 rpm, and feed per tooth values of 0.03, 0.035, and 0.04 mm/tooth. The model was calibrated using two boundary feed conditions and validated at an intermediate, previously unseen condition. The model was calibrated using the two boundary feed conditions and validated at an unseen intermediate feed condition within the calibrated range. The results showed that the proposed model predicted VB at the intermediate feed condition with RMSE values of 4.41, 21.33, and 18.16 μm at spindle speeds of 800, 1025, and 1250 rpm, respectively. Although prediction accuracy varied with spindle speed and some underestimation was observed, the proposed approach demonstrated the feasibility of practically meaningful tool wear estimation using only machine-tool power signals and a small calibration dataset, thereby providing a simple and calibration-efficient basis for industrial tool condition monitoring.},
issn = {0039-2480}, pages = {}, doi = {},
url = {https://www.sv-jme.eu/article/tool-wear-estimation-under-different-feed-conditions-via-cutting-force-coefficients-derived-from-cutting-power-consumption/}
}
Park, J.,Yoon, H.
0 September 0. Tool wear estimation under different feed conditions via cutting force coefficients derived from cutting power consumption. Articles in Press. [Online] 0:0
%A Park, Jin Ho
%A Yoon, Hae-Sung
%D 0
%T Tool wear estimation under different feed conditions via cutting force coefficients derived from cutting power consumption
%B 0
%9
%! Tool wear estimation under different feed conditions via cutting force coefficients derived from cutting power consumption
%K
%X This study proposes a compact power consumption-based framework for estimating flank wear width (VB) in full-slot end-milling of Ti-6Al-4V under various feed conditions, without the need for additional sensors such as a dynamometer or accelerometer. Although extensive research has been conducted on tool wear, most existing approaches rely on data acquired under fixed process conditions, which limits their adaptability to varying process conditions. While some machine learning-based methods have been proposed to address this issue, their practical application in industry is often constrained by the need for large, labeled datasets. Therefore, a robust and low-order modeling approach requiring minimal calibration is desirable for practical deployment. This study proposes a simple analytical modeling framework that accounts for the influence of process conditions on tool wear by estimating cutting force coefficients from cutting power consumption. This enables practical implementation using readily available machine-tool signals. Milling experiments were conducted on titanium alloys at spindle speeds of 800, 1025, and 1250 rpm, and feed per tooth values of 0.03, 0.035, and 0.04 mm/tooth. The model was calibrated using two boundary feed conditions and validated at an intermediate, previously unseen condition. The model was calibrated using the two boundary feed conditions and validated at an unseen intermediate feed condition within the calibrated range. The results showed that the proposed model predicted VB at the intermediate feed condition with RMSE values of 4.41, 21.33, and 18.16 μm at spindle speeds of 800, 1025, and 1250 rpm, respectively. Although prediction accuracy varied with spindle speed and some underestimation was observed, the proposed approach demonstrated the feasibility of practically meaningful tool wear estimation using only machine-tool power signals and a small calibration dataset, thereby providing a simple and calibration-efficient basis for industrial tool condition monitoring.
%U https://www.sv-jme.eu/article/tool-wear-estimation-under-different-feed-conditions-via-cutting-force-coefficients-derived-from-cutting-power-consumption/
%0 Journal Article
%R
%&
%P 1
%J Articles in Press
%V 0
%N 0
%@ 0039-2480
%8 2026-09-21
%7 2026-09-21
Park, Jin Ho, & Hae-Sung Yoon.
"Tool wear estimation under different feed conditions via cutting force coefficients derived from cutting power consumption." Articles in Press [Online], 0.0 (0): . Web. 10 Nov. 2026
TY - JOUR
AU - Park, Jin Ho
AU - Yoon, Hae-Sung
PY - 0
TI - Tool wear estimation under different feed conditions via cutting force coefficients derived from cutting power consumption
JF - Articles in Press
DO -
KW -
N2 - This study proposes a compact power consumption-based framework for estimating flank wear width (VB) in full-slot end-milling of Ti-6Al-4V under various feed conditions, without the need for additional sensors such as a dynamometer or accelerometer. Although extensive research has been conducted on tool wear, most existing approaches rely on data acquired under fixed process conditions, which limits their adaptability to varying process conditions. While some machine learning-based methods have been proposed to address this issue, their practical application in industry is often constrained by the need for large, labeled datasets. Therefore, a robust and low-order modeling approach requiring minimal calibration is desirable for practical deployment. This study proposes a simple analytical modeling framework that accounts for the influence of process conditions on tool wear by estimating cutting force coefficients from cutting power consumption. This enables practical implementation using readily available machine-tool signals. Milling experiments were conducted on titanium alloys at spindle speeds of 800, 1025, and 1250 rpm, and feed per tooth values of 0.03, 0.035, and 0.04 mm/tooth. The model was calibrated using two boundary feed conditions and validated at an intermediate, previously unseen condition. The model was calibrated using the two boundary feed conditions and validated at an unseen intermediate feed condition within the calibrated range. The results showed that the proposed model predicted VB at the intermediate feed condition with RMSE values of 4.41, 21.33, and 18.16 μm at spindle speeds of 800, 1025, and 1250 rpm, respectively. Although prediction accuracy varied with spindle speed and some underestimation was observed, the proposed approach demonstrated the feasibility of practically meaningful tool wear estimation using only machine-tool power signals and a small calibration dataset, thereby providing a simple and calibration-efficient basis for industrial tool condition monitoring.
UR - https://www.sv-jme.eu/article/tool-wear-estimation-under-different-feed-conditions-via-cutting-force-coefficients-derived-from-cutting-power-consumption/
@article{{}{.},
author = {Park, J., Yoon, H.},
title = {Tool wear estimation under different feed conditions via cutting force coefficients derived from cutting power consumption},
journal = {Articles in Press},
volume = {0},
number = {0},
year = {0},
doi = {},
url = {https://www.sv-jme.eu/article/tool-wear-estimation-under-different-feed-conditions-via-cutting-force-coefficients-derived-from-cutting-power-consumption/}
}
TY - JOUR
AU - Park, Jin Ho
AU - Yoon, Hae-Sung
PY - 2026/09/21
TI - Tool wear estimation under different feed conditions via cutting force coefficients derived from cutting power consumption
JF - Articles in Press; Vol 0, No 0 (0): Articles in Press
DO -
KW -
N2 - This study proposes a compact power consumption-based framework for estimating flank wear width (VB) in full-slot end-milling of Ti-6Al-4V under various feed conditions, without the need for additional sensors such as a dynamometer or accelerometer. Although extensive research has been conducted on tool wear, most existing approaches rely on data acquired under fixed process conditions, which limits their adaptability to varying process conditions. While some machine learning-based methods have been proposed to address this issue, their practical application in industry is often constrained by the need for large, labeled datasets. Therefore, a robust and low-order modeling approach requiring minimal calibration is desirable for practical deployment. This study proposes a simple analytical modeling framework that accounts for the influence of process conditions on tool wear by estimating cutting force coefficients from cutting power consumption. This enables practical implementation using readily available machine-tool signals. Milling experiments were conducted on titanium alloys at spindle speeds of 800, 1025, and 1250 rpm, and feed per tooth values of 0.03, 0.035, and 0.04 mm/tooth. The model was calibrated using two boundary feed conditions and validated at an intermediate, previously unseen condition. The model was calibrated using the two boundary feed conditions and validated at an unseen intermediate feed condition within the calibrated range. The results showed that the proposed model predicted VB at the intermediate feed condition with RMSE values of 4.41, 21.33, and 18.16 μm at spindle speeds of 800, 1025, and 1250 rpm, respectively. Although prediction accuracy varied with spindle speed and some underestimation was observed, the proposed approach demonstrated the feasibility of practically meaningful tool wear estimation using only machine-tool power signals and a small calibration dataset, thereby providing a simple and calibration-efficient basis for industrial tool condition monitoring.
UR - https://www.sv-jme.eu/article/tool-wear-estimation-under-different-feed-conditions-via-cutting-force-coefficients-derived-from-cutting-power-consumption/
Park, Jin Ho, AND Yoon, Hae-Sung.
"Tool wear estimation under different feed conditions via cutting force coefficients derived from cutting power consumption" Articles in Press [Online], Volume 0 Number 0 (21 September 2026)
