Abstract

Knowing machine tool dynamics and cutting force is critical to machining process optimization, tool life prediction, and in-process monitoring. Identifying system dynamics and estimating dynamic cutting forces often require dedicated procedures and extensive execution effort. This article presents a Fourier neural operator (FNO)-inspired end-to-end architecture for the rapid estimation of dynamic forces by inferring system characteristics through interpretable operator learning in the frequency domain using system excitation and response data. This machine learning method learns to approximate the system frequency response function (FRF) as an intermediate step and subsequently produces a functional mapping from acceleration to dynamic force. For validation, both a numerical study with a theoretical two degrees-of-freedom model and a field experiment on an actual machine tool are conducted. Results demonstrate that this FNO-based method predicts dynamic forces with over 90% accuracy in terms of R2 value for both validation cases, with the approximated FRF offering insights into the underlying machine tool dynamic behavior. Model training considerations, limitations, and practicality of this method, including the approximate nature of the inferred system characteristics, are also discussed in this article.

References

1.
Teti
,
R.
,
Mourtzis
,
D.
,
D’Addona
,
D. M.
, and
Caggiano
,
A.
,
2022
, “
Process Monitoring of Machining
,”
CIRP Ann.
,
71
(
2
), pp.
529
552
.
2.
Albrecht
,
A.
,
Park
,
S. S.
,
Altintas
,
Y.
, and
Pritschow
,
G.
,
2005
, “
High Frequency Bandwidth Cutting Force Measurement in Milling Using Capacitance Displacement Sensors
,”
Int. J. Mach. Tools Manuf.
,
45
(
9
), pp.
993
1008
.
3.
Mostaghimi
,
H.
,
Park
,
C. I.
,
Kang
,
G.
,
Park
,
S. S.
, and
Lee
,
D. Y.
,
2021
, “
Reconstruction of Cutting Forces Through Fusion of Accelerometer and Spindle Current Signals
,”
J. Manuf. Processes
,
68
, pp.
990
1003
.
4.
Wang
,
C.
,
Zhang
,
X.
,
Qiao
,
B.
,
Chen
,
X.
, and
Cao
,
H.
,
2018
, “
Milling Force Identification From Acceleration Signals Using Regularization Method Based on TSVD in Peripheral Milling
,”
Procedia CIRP
,
77
, pp.
18
21
.
5.
Wang
,
W.
,
Guo
,
Q.
,
Yang
,
Z.
,
Jiang
,
Y.
, and
Xu
,
J.
,
2023
, “
A State-of-the-Art Review on Robotic Milling of Complex Parts With High Efficiency and Precision
,”
Rob. Comput. Integr. Manuf.
,
79
, p.
102436
.
6.
Minis
,
I. E.
,
Magrab
,
E. B.
, and
Pandelidis
,
I. O.
,
1990
, “
Improved Methods for the Prediction of Chatter in Turning, Part 1: Determination of Structural Response Parameters
,”
J. Eng. Ind.
,
112
(
1
), pp.
12
20
.
7.
Özşahin
,
O.
,
Budak
,
E.
, and
Özgüven
,
H. N.
,
2011
, “
Investigating Dynamics of Machine Tool Spindles Under Operational Conditions
,”
Adv. Mater. Res.
,
223
, pp.
610
621
.
8.
Mohammadi
,
Y.
, and
Ahmadi
,
K.
,
2023
, “
In-Process Frequency Response Function Measurement for Robotic Milling
,”
Exp. Tech.
,
47
(
4
), pp.
797
816
.
9.
Iglesias
,
A.
,
Munoa
,
J.
,
Ramírez
,
C.
,
Ciurana
,
J.
, and
Dombovari
,
Z.
,
2016
, “
FRF Estimation Through Sweep Milling Force Excitation (SMFE)
,”
Proc. CIRP
,
46
, pp.
504
507
.
10.
Takasugi
,
K.
,
Fukuda
,
T.
,
Kito
,
R.
,
Asakawa
,
N.
, and
Morimoto
,
Y.
,
2020
, “
Fast Swept Sine Cutting Test for CNC Lathes
,”
J. Adv. Mech. Des. Syst. Manuf.
,
14
(
6
), pp.
JAMDSM0092
JAMDSM0092
.
11.
Zaghbani
,
I.
, and
Songmene
,
V.
,
2009
, “
Estimation of Machine-Tool Dynamic Parameters During Machining Operation Through Operational Modal Analysis
,”
Int. J. Mach. Tools Manuf.
,
49
(
12
), pp.
947
957
.
12.
Li
,
B.
,
Cai
,
H.
,
Mao
,
X.
,
Huang
,
J.
, and
Luo
,
B.
,
2013
, “
Estimation of CNC Machine–Tool Dynamic Parameters Based on Random Cutting Excitation Through Operational Modal Analysis
,”
Int. J. Mach. Tools Manuf.
,
71
, pp.
26
40
.
13.
Cai
,
H.
,
Luo
,
B.
,
Mao
,
X.
,
Gui
,
L.
,
Song
,
B.
,
Li
,
B.
, and
Peng
,
F.
,
2015
, “
A Method for Identification of Machine-Tool Dynamics Under Machining
,”
Proc. CIRP
,
31
, pp.
502
507
.
14.
Peng
,
Y.
,
Li
,
B.
,
Mao
,
X.
,
Liu
,
H.
,
Qin
,
C.
, and
He
,
H.
,
2018
, “
A Method to Obtain the In-Process FRF of a Machine Tool Based on Operational Modal Analysis and Experiment Modal Analysis
,”
Int. J. Adv. Manuf. Technol.
,
95
(
9
), pp.
3599
3607
.
15.
Liu
,
Y.-P.
, and
Altintas
,
Y.
,
2021
, “
In-Process Identification of Machine Tool Dynamics
,”
CIRP J. Manuf. Sci. Technol.
,
32
, pp.
322
337
.
16.
Ostad Ali Akbari
,
V.
,
Mohammadi
,
Y.
,
Kuffa
,
M.
, and
Wegener
,
K.
,
2023
, “
Identification of In-Process Machine Tool Dynamics Using Forced Vibrations in Milling Process
,”
Int. J. Mech. Sci.
,
239
, p.
107887
.
17.
Suzuki
,
N.
,
Kurata
,
Y.
,
Kato
,
T.
,
Hino
,
R.
, and
Shamoto
,
E.
,
2012
, “
Identification of Transfer Function by Inverse Analysis of Self-Excited Chatter Vibration in Milling Operations
,”
Precis. Eng.
,
36
(
4
), pp.
568
575
.
18.
Özşahin
,
O.
,
Budak
,
E.
, and
Özgüven
,
H. N.
,
2015
, “
In-Process Tool Point FRF Identification Under Operational Conditions Using Inverse Stability Solution
,”
Int. J. Mach. Tools Manuf.
,
89
, pp.
64
73
.
19.
Grossi
,
N.
,
Sallese
,
L.
,
Scippa
,
A.
, and
Campatelli
,
G.
,
2017
, “
Improved Experimental-Analytical Approach to Compute Speed-Varying Tool-Tip FRF
,”
Precis. Eng.
,
48
, pp.
114
122
.
20.
Li
,
Z.
,
Kovachki
,
N.
,
Azizzadenesheli
,
K.
,
Liu
,
B.
,
Bhattacharya
,
K.
,
Stuart
,
A.
, and
Anandkumar
,
A.
,
2021
, “
Fourier Neural Operator for Parametric Partial Differential Equations
.”
arXiv preprint arXiv:2010.08895v3
https://arxiv.org/abs/2010.08895
21.
Wang
,
Y.
,
Li
,
Z.
,
Yuan
,
Z.
,
Peng
,
W.
,
Liu
,
T.
, and
Wang
,
J.
,
2024
, “
Prediction of Turbulent Channel Flow Using Fourier Neural Operator-Based Machine-Learning Strategy
,”
Phys. Rev. Fluids
,
9
(
8
), p.
084604
.
22.
You
,
H.
,
Zhang
,
Q.
,
Ross
,
C. J.
,
Lee
,
C.-H.
, and
Yu
,
Y.
,
2022
, “
Learning Deep Implicit Fourier Neural Operators (IFNOs) With Applications to Heterogeneous Material Modeling
,”
Comput. Methods Appl. Mech. Eng.
,
398
, p.
115296
.
23.
Li
,
B.
,
Wang
,
H.
,
Feng
,
S.
,
Yang
,
X.
, and
Lin
,
Y.
,
2023
, “
Solving Seismic Wave Equations on Variable Velocity Models With Fourier Neural Operator
,”
IEEE Trans. Geosci. Remote Sens.
,
61
, pp.
1
18
.
24.
Kingma
,
D. P.
, and
Ba
,
J.
,
2017
, “
Adam: A Method for Stochastic Optimization
.”
arXiv preprint arXiv:1412.6980v9
. https://arxiv.org/abs/1412.6980
25.
Schmitz
,
T. L.
, and
Smith
,
K. S.
,
2021
,
Mechanical Vibrations: Modeling and Measurement
,
Springer International Publishing
,
Cham, Switzerland
.
26.
Avitabile
,
P.
,
2017
, “General Signal Processing and Measurements Related to Experimental Modal Analysis,”
Modal Testing
,
John Wiley & Sons, Ltd
, pp.
93
129
.
27.
Pillonetto
,
G.
, and
De Nicolao
,
G.
,
2010
, “
A New Kernel-Based Approach for Linear System Identification
,”
Automatica
,
46
(
1
), pp.
81
93
.
28.
Pillonetto
,
G.
,
Dinuzzo
,
F.
,
Chen
,
T.
,
De Nicolao
,
G.
, and
Ljung
,
L.
,
2014
, “
Kernel Methods in System Identification, Machine Learning and Function Estimation: A Survey
,”
Automatica
,
50
(
3
), pp.
657
682
.
29.
Vogl
,
G. W.
,
Regli
,
D. A.
, and
Corson
,
G. M.
,
2022
, “
Real-Time Estimation of Cutting Forces Via Physics-Inspired Data-Driven Model
,”
CIRP Ann.
,
71
(
1
), pp.
317
320
.
30.
Kronenberg
,
M.
,
1966
,
Machining Science and Application: Theory and Practice for Operation and Development of Machining Processes
,
Pergamon Press
,
Oxford, UK
.
31.
Kuljanic
,
E.
,
Sortino
,
M.
, and
Miani
,
F.
,
2002
, “Application of a Rotating Dynamometer for Cutting Force Measurement in Milling,”
AMST’02 Advanced Manufacturing Systems and Technology
,
E.
Kulianic
, ed.,
Springer
,
Vienna, Austria
, pp.
159
166
.
32.
Pan
,
S.
,
Brunton
,
S. L.
, and
Kutz
,
J. N.
,
2023
, “
Neural Implicit Flow: A Mesh-Agnostic Dimensionality Reduction Paradigm of Spatio-Temporal Data
.”
arXiv preprint arXiv:2204.03216v5
. https://arxiv.org/abs/2204.03216
You do not currently have access to this content.