Abstract

Tool condition monitoring (TCM) has become a research area of interest due to its potential to significantly reduce manufacturing costs while increasing process visibility and efficiency. Machine learning (ML) is one analysis technique which has demonstrated advantages for TCM applications. However, the commonly studied individual ML models lack generalizability to new machining and environmental conditions, as well as robustness to the unbalanced datasets which are common in TCM. Ensemble ML models have demonstrated superior performance in other fields, but have only begun to be evaluated for TCM. As a result, it is not well understood how their TCM performance compares to that of individual models, or how homogeneous and heterogeneous ensemble models’ performances compare to one another. To fill in these research gaps, milling experiments were conducted using various cutting conditions, and the model groups were compared across several performance metrics. Statistical t-tests were also used to evaluate the significance of model performance differences. Through the analysis of four individual ML models and five ensemble models, all based on the processes’ sound, spindle power, and axial load signals, it was found that on average, the ensemble models performed better than the individual models, and that the homogeneous ensembles outperformed the heterogeneous ensembles.

References

1.
Weller
,
E. J.
,
Schrier
,
H. M.
, and
Weichbrodt
,
B.
,
1969
, “
What Sound Can Be Expected From a Worn Tool?
,”
J. Eng. Ind.
,
91
(
3
), pp.
525
534
.
2.
Goebel
,
K.
,
1996
, “
Management of Uncertainty in Sensor Validation, Sensor Fusion, and Diagnosis of Mechanical Systems Using Soft Computing Techniques
,”
Ph.D. dissertation.
,
University of California
,
Berkeley, VA
.
3.
Li
,
W.
,
Guo
,
Y. B.
,
Barkey
,
M. E.
,
Guo
,
C.
, and
Liu
,
Z. Q.
,
2011
, “
Surface Integrity and Fatigue Strength of Hard Milled Surfaces
,”
International Manufacturing Science and Engineering Conference
,
Corvallis, OR
,
June 13–17
,
ASME Paper No. MSEC2011-50282
, pp.
199
206
.
4.
Denkena
,
B.
,
Tonshoff
,
H. K.
,
Friemuth
,
T.
,
Mueller
,
C.
,
Zenner
,
H.
,
Renner
,
F.
, and
Koehler
,
M.
,
2002
, “
Fatigue Strength of Hard Turned Components
,”
Proceedings of 1st International Conference Manufacturing Engineering
,
Sani, Halkidiki, Greece
,
Oct. 3–4
.
5.
Ghasempoor
,
A.
,
Moore
,
T. N.
, and
Jeswiet
,
J.
,
1998
, “
On-Line Wear Estimation Using Neural Networks
,”
Proc. Inst. Mech. Eng.: J. Eng. Manuf., Part B
,
212
(
2
), pp.
105
112
.
6.
Ambhore
,
N.
,
Kamble
,
D.
,
Chinchanikar
,
S.
, and
Wayal
,
V.
,
2015
, “
Tool Condition Monitoring System: A Review
,”
Mater. Today: Proc.
,
2
(
3–4
), pp.
3419
3428
.
7.
Binsaeid
,
S.
,
Asfour
,
S.
,
Cho
,
S.
, and
Onar
,
A.
,
2009
, “
Machine Ensemble Approach for Simultaneous Detection of Transient and Gradual Abnormalities in End Milling Using Multisensor Fusion
,”
J. Mater. Proc. Technol.
,
209
(
10
), pp.
4728
4738
.
8.
Rangwala
,
S. S.
, and
Dornfeld
,
D. A.
,
1989
, “
Learning and Optimization of Machning Operations Using Computing Abilities of Neural Networks
,”
IEEE Trans. Syst. Man Cybern.
,
19
(
2
), pp.
299
314
.
9.
Scheffer
,
C.
, and
Heyns
,
P. S.
,
2004
, “
An Industrial Tool Wear Monitoring System for Interrupted Turning. Mechanical Systems and Signal Processing
,”
Mech. Syst. Signal Proc.
,
18
(
5
), pp.
1219
1242
.
10.
Dan
,
L.
, and
Mathew
,
J.
,
1990
, “
Tool Wear and Failure Monitoring Techniques for Turning– A Review
,”
Int. J. Mach. Tools Manuf.
,
30
(
4
), pp.
579
598
.
11.
Roth
,
J. T.
,
Djurdjanovic
,
D.
,
Yang
,
X.
,
Mears
,
L.
, and
Kurfess
,
T.
,
2010
, “
Quality and Inspection of Machining Operations: Tool Condition Monitoring
,”
ASME J. Manuf. Sci. Eng.
,
132
(
4
), p.
041015
.
12.
Jemielniak
,
K.
,
1999
, “
Commercial Tool Condition Monitoring Systems
,”
Int. J. Adv. Manuf. Technol.
,
15
(
10
), pp.
711
721
.
13.
Kuntoglu
,
M.
,
Aslan
,
A.
,
Pimenov
,
D. Y.
,
Usca
,
U. A.
,
Salur
,
E.
,
Gupta
,
M. K.
,
Mikolajczyk
,
T.
,
Giasin
,
K.
,
Kaplonek
,
W.
, and
Sharma
,
S.
,
2021
, “
A Review of Indirect Tool Condition Monitoring Systems and Decision-Making Methods in Turning: Critical Analysis and Trends
,”
Sensors
,
21
(
1
), p.
108
.
14.
Ghosh
,
N.
,
Ravi
,
Y. B.
,
Patra
,
A.
,
Mukhopadhyay
,
S.
,
Paul
,
S.
,
Mohanty
,
A. R.
, and
Chattopadhyay
,
A. B.
,
2007
, “
Estimation of Tool Wear During CNC Milling Using Neural Network-Based Sensor Fusion
,”
Mech. Syst. Signal Process.
,
21
(
1
), pp.
466
479
.
15.
Kannatey-Asibu
,
E.
,
Yum
,
J.
, and
Kim
,
T. H.
,
2017
, “
Monitoring Tool Wear Using Classifier Fusion
,”
Mech. Syst. Signal Process.
,
85
, pp.
651
661
.
16.
Wang
,
J.
,
Xie
,
J.
,
Zhao
,
R.
,
Zhang
,
L.
, and
Duan
,
L.
,
2016
, “
Multisensory Fusion Based Virtual Tool Wear Sensing for Ubiquitous Manufacturing
,”
Rob. Comput.-Integr. Manuf.
,
45
(
4
), pp.
47
58
.
17.
Sick
,
B.
,
2002
, “
Online and Indirect Tool Wear Monitoring in Turning With Artificial Neural Networks: A Review of More Than a Decade of Research
,”
Mech. Syst. Signal Process.
,
16
(
4
), pp.
487
546
.
18.
Huang
,
Z.
,
Zhu
,
J.
,
Lei
,
J.
,
Li
,
X.
, and
Tian
,
F.
,
2020
, “
Tool Wear Predicting Based on Multi-Domain Feature Fusion by Deep Convolutional Neural Network in Milling Operations
,”
J. Intell. Manuf.
,
31
(
4
), pp.
953
966
.
19.
Kothuru
,
A.
,
2017
, “
Application of Audible Signals in Tool Condition Monitoring Using Machine Learning Techniques
,”
Master’s thesis
,
Rochester Institute of Technology
,
Rochester, NY
. https://scholarworks.rit.edu/cgi/viewcontent.cgi?article =10890&context =theses
20.
Kothuru
,
A.
,
Nooka
,
S. P.
, and
Liu
,
R.
,
2018
, “
Application of Audible Sound Signals for Tool Wear Monitoring Using Machine Learning Techniques in End Milling
,”
Int. J. Adv. Manuf. Technol.
,
95
(
9–12
), pp.
3797
3808
.
21.
Wang
,
G.
,
Yang
,
Y.
, and
Li
,
Z.
,
2014
, “
Force Sensor Based Tool Condition Monitoring Using a Heterogeneous Ensemble Learning Model
,”
Sensors
,
14
(
11
), pp.
21588
21602
.
22.
Yuan
,
J.
,
Liu
,
L.
,
Yang
,
Z.
, and
Zhang
,
Y.
,
2020
, “
Tool Wear Condition Monitoring by Combining Variational Mode Decomposition and Ensemble Learning
,”
Sensors
,
20
(
21
), p.
6113
.
23.
Riego
,
V.
,
Castejon-Limas
,
M.
,
Sanchez-Gonzalez
,
L.
,
Fernandez-Robles
,
L.
,
Perez
,
H.
,
Diez-Gonzalez
,
J.
, and
Guerrero-Higueras
,
A.-M.
,
2020
, “
Strong Classification System for Wear Identification on Milling Processes Using Computer Vision and Ensemble Learning
,”
Neurocomputing
,
456
(
1
), pp.
678
684
.
24.
Hui
,
Y.
,
Mei
,
X.
,
Jiang
,
G.
,
Tao
,
T.
,
Pei
,
C.
, and
Ma
,
Z.
,
2019
, “
Milling Tool Wear State Recognition by Vibration Signal Using a Stacked Generalization Ensemble Model
,”
Shock Vib.
,
2019
(
3
), pp.
1
16
.
25.
Javed
,
K.
,
Gouriveau
,
R.
,
Li
,
X.
, and
Zerhouni
,
N.
,
2018
, “
Tool Wear Monitoring and Prognostics Challenges: A Comparison of Connectionist Methods Toward an Adaptive Ensemble Model
,”
J. Intell. Manuf.
,
29
(
8
), pp.
1873
1890
.
26.
ISO8688-2
,
1989
,
Tool Life Testing in Milling– Part 2: End Milling
,
The International Organization for Standardization (ISO)
,
Geneva, Switzerland
, pp.
1
26
.
27.
Tobon-Mejia
,
D. A.
,
Medjaher
,
K.
, and
Zerhouni
,
N.
,
2012
, “
CNC Machine Tool’s Wear Diagnostic and Prognostic by Using Dynamic Bayesian Networks
,”
Mech. Syst. Signal Process.
,
28
, pp.
167
182
.
28.
Zhou
,
Y.
,
Sun
,
B.
,
Sun
,
W.
, and
Lei
,
Z.
,
2020
, “
Tool Wear Condition Monitoring Based on a Two-Layer Angle Kernel Extreme Learning Machine Using Sound Sensor for Milling Process
,”
J. Intell. Manuf.
,
33
(
1
), pp.
247
258
29.
Hsieh
,
W.-H.
,
Lu
,
M.-C.
, and
Chiou
,
S.-J.
,
2012
, “
Application of Backpropogation Neural Network for Spindle Vibration-Based Tool Wear Monitoring in Micro-Milling
,”
Int. J. Adv. Manuf. Technol.
,
61
(
1–4
), pp.
53
61
.
30.
Wu
,
Y.
,
Hong
,
G.-S.
, and
Wong
,
W. S.
,
2014
, “
Prognosis of the Probability of Failure in Tool Condition Monitoring Application—A Time Series Based Approach
,”
Int. J. Adv. Manuf. Technol.
,
76
(
1–4
), pp.
513
521
.
31.
Li
,
Z.
,
Liu
,
R.
, and
Wu
,
D.
,
2019
, “
Data-Driven Smart Manufacturing: Tool Wear Monitoring With Audio Signals and Machine Learning
,”
J. Manuf. Process.
,
48
(
4
), pp.
66
76
.
32.
Kothuru
,
A.
,
Nooka
,
S. P.
, and
Liu
,
R.
,
2017
, “
Cutting Process Monitoring System Using Audible Sound Signals and Machine Learning Techniques: An Application to End Milling
,”
International Manufacturing Science and Engineering Conference
,
Los Angeles, CA
,
June 4–8
, ASME Paper No. MSEC2017-3069.
33.
Lei
,
Y.
,
He
,
Z.
,
Ze
,
Y.
, and
Chen
,
X.
,
2008
, “
New Clustering Algorithm-Based Fault Diagnosis Using Compensation Distance Evaluation Technique
,”
Mech. Syst. Signal Process.
,
22
(
2
), pp.
419
435
.
34.
Lee
,
L. C.
,
1986
, “
A Study of Noise Emission for Tool Failure Prediction
,”
Int. J. Mach. Tool. Des. Res.
,
26
(
2
), pp.
205
215
.
35.
Sadat
,
A. B.
, and
Raman
,
S.
,
1987
, “
Detection of Tool Flank Wear Using Acoustic Signature Analysis
,”
Wear
,
115
(
3
), pp.
265
272
.
36.
Schueller
,
A.
,
2021
, “
Ensemble Machine Learning Model Generalizability and Its Application to Indirect Tool Condition Monitoring
,”
Master’s thesis
,
Georgia Institute of Technology
,
Atlanta, GA
.
37.
Shurrab
,
S.
,
Almshnanah
,
A.
, and
Duwairi
,
R. M.
,
2021
, “
Tool Wear Prediction in Computer Numerical Control Milling Operations Via Machine Learning
,”
International Conference on Information and Communication Systems (ICICS)
,
Valencia, Spain
,
May 24–26
.
38.
Castejón-Limas
,
M.
,
Sánchez-González
,
L.
,
Díez-González
,
J.
,
Fernández-Robles
,
L.
,
Riego
,
V.
, and
Pérez
,
H.
,
2019
, “
Texture Descriptors for Automatic Estimation of Workpiece Quality in Milling
,”
Hybrid Artif. Intell. Syst.
,
11
, pp.
734
744
.
39.
Elangovan
,
M.
,
Devasenapati
,
S. B.
,
Sakthivel
,
N. R.
, and
Ramachandran
,
K. L.
,
2011
, “
Evaluation of Expert System for Condition Monitoring of a Single Point Cutting Tool Using Principle Component Analysis and Decision Tree Algorithm
,”
Expert Syst. Appl.
,
38
(
4
), pp.
4450
4459
.
40.
Jegorowa
,
A.
,
Górski
,
J.
,
Kurek
,
J.
, and
Kruk
,
M.
,
2020
, “
Use of Nearest Neighbors (k-NN) Algorithm in Tool Condition Identification in the Case of Drilling in Melamine Faced Particleboard
,”
Maderas: Cienc. Tecnol
,
22
(
2
), pp.
189
196
.
41.
Mannan
,
M. A.
,
Kassim
,
A. A.
, and
Jing
,
M.
,
2000
, “
Application of Image and Sound Analysis Techniques to Monitor the Condition of Cutting Tools
,”
Pattern Recognit. Lett.
,
21
(
11
), pp.
969
979
.
42.
Pedregosa
,
F.
,
Varoquaux
,
G.
,
Gramfort
,
A.
,
Michel
,
V.
,
Thirion
,
B.
,
Grisel
,
O.
,
Blondel
,
M.
, et al
,
2011
, “
Scikit-Learn: Machine Learning in Python
,”
J. Mach. Learn Res.
,
12
(
85
), pp.
2825
2830
.
43.
Wang
,
H.
,
Yang
,
Y.
,
Wang
,
H.
, and
Chen
,
D.
,
2013
, “Soft-Voting ClusteringEnsemble,”
Multiple Classifier Systems. MCS 2013. Lecture Notes in Computer Science
,
Z. H.
Zhou
,
F.
Roli
, and
J.
Kittler
, eds.,
Springer
,
Berlin/Heidelberg
, pp.
307
318
.
44.
Saqlain
,
M.
,
Jargalsaikhan
,
B.
, and
Lee
,
J. Y.
,
2019
, “
A Voting Ensemble Classifier for Wafer Map Defect Patterns Identification in Semiconductor Manufacturing
,”
IEEE Trans. Semicond. Manuf.
,
32
(
2
), pp.
171
182
.
45.
Saeed
,
U.
,
Jan
,
S. U.
,
Lee
,
Y.-D.
, and
Koo
,
I.
,
2021
, “
Fault Diagnosis Based on Extremely Randomized Trees in Wireless Sensor Networks
,”
Reliab. Eng. Syst. Saf.
,
205
(
3
), p.
107284
.
46.
Zhang
,
B.
,
2020
, “
Improved Extremely Randomized Trees Model for Fault Diagnosis of Wind Turbine
,”
Int. J. Sci.
,
7
(
12
), pp.
74
87
.
You do not currently have access to this content.