Tool Wear Condition Monitoring in Milling Process Based on Current Sensors

Abstract

Accurate tool condition monitoring (TCM) is essential for the development of fully automated milling processes. This is typically accomplished using indirect TCM methods that synthesize the information collected from one or more sensors to estimate tool condition based on machine learning approaches. Among the many sensor types available for conducting TCM, motor current sensors offer numerous advantages, in that they are inexpensive, easily installed, and have no effect on the milling process. Accordingly, this study proposes a new TCM method employing a few appropriate current sensor signal features based on the time, frequency, and time–frequency domains of the signals and an advanced monitoring model based on an improved kernel extreme learning machine (KELM). The selected multi-domain features are strongly correlated with tool wear condition and overcome the loss of useful information related to tool condition when employing a single domain. The improved KELM employs a two-layer network structure and an angle kernel function that includes no hyperparameter, which overcome the drawbacks of KELM in terms of the difficulty of learning the features of complex nonlinear data and avoiding the need for preselecting the kernel function and its hyperparameter. The performance of the proposed method is verified by its application to the benchmark NASA milling dataset and separate TCM experiments in comparison with existing TCM methods. The results indicate that the proposed TCM method achieves excellent monitoring performance using only a few key signal features of current sensors.

Full text

This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.2995586, IEEE Access
VOLUME XX, 2017 1
Date of publication xxxx 00, 0000, date of current version xxxx 00, 0000.
Digital Object Identifier 10.1109/ACCESS.2017.Doi Number
Tool Wear Condition Monitoring in Milling
Process Based on Current Sensors
Yuqing Zhou, Weifang Sun
College of mechanical and electrical engineering, Wenzhou University, Wenzhou 325035, China
Corresponding author: Yuqing Zhou(zhouyq@wzu.edu.cn).
This work was supported in part by the National Natural Science Foundation of China under Grant Nos. 51405346 and 71471139, in part by the Zhejiang
Provincial Natural Science Foundation of China under Grant No. LY17E050005, in part by the Wenzhou Major Science and Technology Innovation Project
of China under Grant No. ZD2019042, and in part by the Wenzhou City Public Industrial Science and Technology Project of China under Grant No.
2018G0116.
ABSTRACT Accurate tool condition monitoring (TCM) is essential for the development of fully
automated milling processes. This is typically accomplished using indirect TCM methods that synthesize
the information collected from one or more sensors to estimate tool condition based on machine learning
approaches. Among the many sensor types available for conducting TCM, motor current sensors offer
numerous advantages, in that they are inexpensive, easily installed, and have no effect on the milling
process. Accordingly, this study proposes a new TCM method employing a few appropriate current sensor
signal features based on the time, frequency, and time frequency domains of the signals and an advanced
monitoring model based on an improved kernel extreme learning machine (KELM). The selected multi-
domain features are strongly correlated with tool wear condition and overcome the loss of useful
information related to tool condition when employing a single domain. The improved KELM employs a
two-layer network structure and an angle kernel function that includes no hyperparameter, which overcome
the drawbacks of KELM in terms of the difficulty of learning the features of complex nonlinear data and
avoiding the need for preselecting the kernel function and its hyperparameter. The performance of the
proposed method is verified by its application to the benchmark NASA milling dataset and separate TCM
experiments in comparison with existing TCM methods. The results indicate that the proposed TCM
method achieves excellent monitoring performance using only a few key signal features of current sensors.
INDEX TERMS Tool condition monitoring (TCM), milling process, current sensor, kernel extreme
learning machine (KELM), angle kernel.
I. INTRODUCTION
Milling is a common and efficient machining operation
employed in modern industrial manufacturing for fabricating
various mechanical parts, such as flat surfaces, grooves,
threads, and other complex geometric shapes. Cutting tools
are key components in machine milling operations that are
inevitably subject to wear during milling and therefore
present conditions that vary over their effective lifetimes [1].
However, Konstantinos et al. [2] and Karandikar et al. [3]
have determined that cutting tools are typically used for only
50%–80% of their effective lifetimes owing to excessive tool
wear and breakage (i.e., tool faults). These tool faults are
major causes of unscheduled downtime in milling processes
and typically account for 7%–20% of the total downtime [4].
In addition, tools and tool changes account for 3%–12% of
the total processing cost [5]. As such, tool faults have
negative direct (capital) and indirect (time loss) effects on
milling performance. Therefore, the timeliness of detecting
tool conditions is critical to provide effective information for
implementing scheduled tool replacement decisions without
interrupting normal machine operations [6]. As a result, tool
condition monitoring (TCM) has become an essential task in
industrial milling processes for scheduling operations based
on objective tool condition evaluations [7].
Researchers have investigated TCM in milling processes
for over thirty years based on either direct or indirect
monitoring methods. Direct monitoring methods adopt
optical components for visual inspection and are not suitable
for industrial manufacturing settings due to the expense of
the optical equipment involved and the interference of cutting
fluid and cutting chips [8][9]. Therefore, indirect monitoring
methods have been widely adopted. Indirect TCM methods

This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.2995586, IEEE Access
VOLUME XX, 2017 1
are data-driven methods that synthesize the information
collected from one or more sensors to estimate tool condition
based on machine learning approaches [10].
This study first considers past efforts focused on indirect
TCM methods using various sensors in Section 2 and
discusses their limitations. The problems associated with
these past efforts are addressed by the theoretical framework
and learning algorithm of the TCM method proposed in
Section 3. The prediction performance of the proposed
method is verified in Sections 4 and 5 by its application to
the open-access benchmark NASA milling dataset [11] and
separate TCM experiments in comparison with several
methods. Conclusions are given in Section 6.
II. LITERATURE REVIEW
A. SENSORS
Numerous types of sensors have been employed to obtain
signals for conducting indirect TCM, such as cutting force,
vibration, acoustic emission (AE), and motor current sensors.
(1) Cutting force
The progressive wear of cutting tools during the milling
process increases the roughness of the cutting surface, and
this leads to a corresponding increase in the applied cutting
force. Many studies [1][12][13] have demonstrated that the
cutting force is very sensitive to changes in tool condition
and can therefore accurately estimate the tool state. For
example, Wang et al. determined that the cutting force signal
is the most stable and reliable signal among all commonly
employed sensor signals that are closely related to tool wear
[14]. Huang et al. employed a piezoelectric dynamometer to
monitor the cutting force of an end milling operation [15].
Bulent et al. adopted a rotary dynamometer to capture the
cutting forces in three dimensions and the torque of the drive
moment on a rotating tool [16]. However, cutting force
sensors are difficult to apply in industrial settings because
their physical properties are not appropriate for conducting
TCM when milling medium and large workpieces, such that
milling processes monitored by cutting force sensors are
limited to relatively small physical workpiece sizes [17]. In
addition, Koike et al. established that cutting force
monitoring interferes with the motion control of the spindle
and stage in a milling machine by reducing its rigidity [18].
Moreover, the expense of commercial dynamometers can
unacceptably increase manufacturing costs [19][20].
(2) Vibration
Vibration sensors are widely employed in TCM because
they are inexpensive, easily installed, and provide similar
periodic signal shapes to those of cutting force sensors [21]-
[23]. Besmir et al. established that the level of vibration
generated during the milling process increases with
increasing deterioration in the tool condition[24], and the
feasibility of adopting vibration signals for TCM in milling
processes has been demonstrated by numerous subsequent
studies [25]-[28]. For example, Hsieh et al. demonstrated that
variations in tool conditions during micro-milling processes
can be distinguished according to spindle vibration
acceleration signals when used in conjunction with
appropriate feature extraction and classifiers [29].
Madhusudana et al. adopted a tri-axial integrated
piezoelectric accelerometer on the spindle housing to capture
the spindle vibration acceleration signal during face milling
[30]. Gao et al. achieved good tool condition diagnostic
accuracy by adopting a laser vibrometer to acquire the
vibration displacement of a tool holder [31]. However, the
characteristics of milling processes limit the accuracy of
TCM methods employing vibration sensor signals. First,
vibrations are generated during machine operation even when
the tool is not engaged in cutting, as during an air-cut
operation. In fact, effectively distinguishing air-cut
operations from actual cutting operations remains a
significant challenge in TCM methods employing vibration
sensor signals. Second, vibration signals are difficult to filter
and are therefore prone to providing erroneous data [24].
Finally, the position of sensor installation and cutting-fluid
conditions can affect the vibration signal, which greatly
complicates the training process, and can lead to inaccurate
monitoring results [9].
(3) Acoustic emission
Sensors based on AE are particularly suitable for
conducting TCM in milling processes because the resulting
signals are not mechanically disturbed, have a superior
sensitivity to the those of cutting force and vibration sensor
signals, and propagate at a frequency much greater than the
characteristic frequency caused by cutting, which reduces
interference [32][33]. Hassan et al. demonstrated the
potential of AE signals for detecting the unstable crack
propagation preceding tool chipping/breakage within a time
span on the order of 10 ms [34]. Vetrichelvan et al.
demonstrated that the AE signals obtained from sensors
located on the top surface of the tool holder can effectively
monitor crater wear in the cutting surface [2]. Mathew et al.
experimentally demonstrated with 1-tooth, 2-tooth, and 3-
tooth milling cutters that AE signals exhibit marked
responses to changes in tool condition such as tool breakage
and tool chipping [35]. Ren et al. established that AE signals
captured in micro-milling processes are easily recorded and
provide very rapid responses to changing conditions in the
contact between the tool and workpiece [36]. However,
intermittent cutting during milling processes results in AE
signal spikes when individual teeth enter or exit the
workpiece, which greatly complicates the analysis of AE
signals [32]. In addition, AE sensors are highly sensitive to
environmental noise [37], which increases the difficulty of
extracting valid signal feature information.
(4) Motor current
Because the cutting force increases with increasing tool
wear, the current drawn by the electric motors of a milling
machine undergoes corresponding increases [38]. Motor
current sensors are considered to be more suitable for

This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.2995586, IEEE Access
VOLUME XX, 2017 1
industrial manufacturing settings than cutting force sensors
due to their relatively simple application and lack of
installation effects on machining operations [39][40]. Ghosh
et al. demonstrated that TCM methods based on current
sensor signals provide monitoring results that are fairly
comparable to methods based on cutting force sensor signals
in actual industrial TCM applications [8]. Stavropoulos et al.
demonstrated that motor current signals correlate more
strongly with tool wear than vibration signals [20]. Ammouri
et al. established a TCM index based on the measured current
values of the spindle and drive motors of a milling machine
[38]. Hassan et al. proposed an effective signal processing
technique for applying spindle motor current signals to
describe tool wear conditions under different cutting
parameters in high speed roughing milling operations [41].
However, current sensors are less commonly employed for
TCM in milling processes than the above three types of
sensors. because motor current signals include a considerable
amount of noise, which obstructs the detection of small
fluctuations in the cutting force, and the application of
filtering typically results in the loss of high-frequency
components [18][42]. Teti et al. suggested that the proportion
of spindle power required for material removal is a very
small component of the total power, and that temperature
increases inherent in electrical motors under load influence
power consumption [43]. Specifically, the spindle current
and voltage frequency in high-speed milling processes could
be modified by a pulse-width modulation (PWM) module
when using a 400-Hz 2-pole induction spindle motor to
generate superimposed signals for maintaining a set
rotational speed [44].
The limitations associated with the single-sensor TCM
applications discussed above have generated an increasing
interest in multi-sensor TCM [45][46]. For example, Torabi
et al. applied the signals obtained from dynamometer,
accelerometer, and AE sensors to conduct TCM for a ball
nose milling process [47]. Downey et al. developed a TCM
system based on AE, vibration, and cutting force signals [48].
Jahromi et al. applied the signals derived from cutting force,
accelerometer, and AE sensors for conducting TCM in a
high-speed milling process [49]. Sohyung et al. applied three-
axis dynamometer, three-axis accelerometer, AE, and current
sensors for TCM in an end milling process, and demonstrated
that the diagnosis accuracy was greater than that obtained
using any of the single sensors [49]. Hassan et al. presented a
generalized, nonintrusive multi- signal fusion approach for
real-time tool wear detection by using unprocessed spindle
motor current, voltage, and power signals directly [44].
However, while the use of multiple sensors can enhance the
richness of information indicative of potential tool wear
levels, the production and maintenance costs and the
difficulty of maintenance in industrial machine milling
operations increase when adopting multiple sensors, and the
interference caused by sensors in the milling process
increases with an increasing number of sensors.
B. MONITORING MODEL
The rapid development of artificial intelligence technology in
recent years has led to the use of many AI models to predict
tool-wear conditions based on sensor signal data. These
predominantly include artificial neural networks (ANNs),
hidden Markov models (HMMs), support vector machine
(SVM), and kernel extreme learning machine (KELM). More
recently, deep learning technologies such as convolution
neural networks (CNNs) and recurrent neural networks
(RNNs), with wide applications in image processing and
other fields, have emerged as alternative AI models in TCM
for milling processes.
Many studies have applied ANNs and HMMs to TCM in
milling processes with outstanding results [33][51][52]. Deep
neural networks such as CNNs [53][54] and RNNs [55][56]
have also been applied with considerable success. However,
ANN- and HMM-based TCM models have several
drawbacks [57][58]. First and foremost, they require a large
number of training samples to obtain accurate monitoring
performance, which is time-consuming and costly for
industrial milling operations. Second, they require the
preselection of critical parameters. For example, the number
of hidden layers of an ANN and the number of neurons in
each layer (i.e., the network structure) are critical to the
performance, but the selection of network structure depends
on researcher experience and is not directly related to the
tool-wear process. As such, selecting the optimal network
structure for conducting TCM in milling operations from
among the many possible structures remains an unsolved
issue. In addition, an accurate determination of the tool state
duration distribution in the milling process is critical to the
performance of HMM, although no truly objective means for
determining this distribution presently exists.
In contrast to the above-discussed AI models, SVM and
KELM have generated considerable interest in TCM research
because of their superior performance with small sample
sizes [59]. An SVM applies statistical learning theory to map
input samples in the original space to a high-dimensional
feature space nonlinearly using a kernel function and thereby
constructs a linear algorithm corresponding to the solution in
the original space. A KELM was proposed for use in a single
hidden layer feed-forward neural network (SLFN) with a
kernel function that learns quickly, and its learning accuracy
and speed have been demonstrated to be greater than those of
other models such as SVM, ANN, and HMM in various
applications, including classification, regression, time series
forecasting, and fault diagnosis [60][61]. Moreover, the
KELM tends to achieve not only the smallest training error
but also the smallest norm of the output weights.
Unfortunately, KELM suffers from two drawbacks. First, as
a special case of SLFNs, KELM has a shallow architecture
that fails to completely extract the inherent features in raw
data (particularly microarray data) like deep architectures
[62]. Second, similar to SVM, the selection of the kernel
function, such as a Gaussian kernel, polynomial kernel, or

This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.2995586, IEEE Access
VOLUME XX, 2017 1
sigmoid kernel, and its hyperparameter greatly impact its
performance with respect to the extraction of inherent
features in raw data. However, no theoretical basis exists for
selecting the kernel function objectively, and its hyper-
parameter must be manually preset or tuned by cross-
validation (CV), such as is the case for the kernel width in
radial basis function (RBF) kernels. As a result, it remains
unknown whether KELM can obtain optimal extraction
results in the context of small sample size.
III. PROPOSED METHOD
The purpose of this study is to develop a high performance
TCM method based on KELM with use of current sensors, in
which, the drawbacks of current sensor signal could be
reduced significantly and no need to preselect kernel function
and its hyperparameter in KELM.
A. FRAMEWORK OF THE PROPOSED METHOD
The proposed TCM method employs a few key current
sensor signal features based on the time, frequency, and time-
frequency domains of the signals and an advanced
monitoring model based on an improved KELM to achieve
excellent TCM performance. Here, current sensors are
deemed most appropriate due to their low cost and simple
installation that has no effect on the milling process, while
the selected multi-domain features, which are strongly
correlated with tool wear condition, overcome the drawbacks
associated with the use of current signals described in
Subsection 2.1 and the loss of useful information related to
tool condition when employing a single domain. The
proposed TCM method is schematically illustrated in Figure
1. Its operation comprises three steps: the first step is current
sensor signal acquisition, where the dynamic signals obtained
from current sensors are collected to depict the characteristics
of the milling process. The second step is feature extraction,
where a few key statistical parameters in the time, frequency,
and time-frequency domains of the current sensor signals are
extracted. The last step involves monitoring the tool
condition using an improved KELM. The second and third
steps are discussed in detail in the following subsections.
FIGURE 1. Framework of the proposed TCM method
B. FEATURE EXTRACTION
The three key statistical parameters associated with feature
extraction include the average amplitude (Tavg) of the
spindle motor current in the time domain, the mean of the
power spectrum (Fmps) in the frequency domain, and the
average wavelet energy of the first frequency band (E1)
obtained using the wavelet packet transform (WPT) with
the db2 wavelet basis function in the time-frequency
domain. Here, the WPT conducts a multi-level band
division over the entire signal band, which inherits the
advantages of good time-frequency localization from the
wavelet transform (WT) and further decomposes the high-
frequency band to increase the frequency resolution
[63][64]. As discussed in Section II, the current increases
with increasing cutting force as tool wear becomes
progressively severe. Therefore, changes in the values of
Tavg,Fmps, and E1of the spindle motor current correspond
approximately to changes in tool wear, as can be seen in
Figures 2-4.
In the time domain, the value of Tavg is defined as follows:

n
1i iavg nxT /
(1)
where xiis the amplitude of the i-th current signal sample in a
collection of nsamples in the sample set. As an example, the
relationship between the values of Tavg obtained for the AC
spindle motor current and the tool wear values in the NASA
milling dataset is shown in Figure 2. The results in the figure
indicate that the peaks in tool wear with respect to cut
number are strongly correlated with the peak values of Tavg
with a correlation coefficient R= 0.3779.
FIGURE 2. Relationship between the average current amplitude Tavg of
an AC spindle motor and the tool wear condition of the second tool in
the NASA milling dataset.

This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.2995586, IEEE Access
Author Name: Preparation of Papers for IEEE Access (February 2017)
2 VOLUME XX, 2017
In the frequency domain, the value of Fmps is defined as

n
1i imps nPF /
(2)
where Piis the power spectrum of the signal sample
corresponding to xiobtained by the fast Fourier transform
(FFT). The relationship between the value Fmps obtained for
the AC spindle motor current and the tool wear condition in
the NASA milling dataset is shown in Figure 3. Again, the
results in the figure indicate that the peaks in tool wear with
respect to cut number are strongly correlated with the peak
values of Fmps (R= 0.6203).
FIGURE 3. Relationship between the mean of the power spectrum Fmps
of an AC spindle motor and the tool wear condition of the second tool in
the NASA milling dataset.
In the time-frequency domain, the value of E1is
calculated using the db2 basis function as follows:


 n
1k
2
k
n
1k
2
kdttxtw
n
1
d
n
1
E))()(()( ,, 111
(3)
where d1,kdenotes the wavelet packet coefficients of signal
x(t), and w1,k(t) are the wavelet packets localized at 2kin the
scale of 2. The relationship between the value E1obtained for
the AC spindle motor current and tool wear condition in the
NASA milling dataset is shown in Figure 4. These results
also indicate that the peaks in tool wear with respect to cut
number are strongly correlated with the peak values of E1. (R
= 0.6051).
FIGURE 4. Relationship between the average wavelet energy of the first
frequency band E1 of an AC spindle motor and the tool wear condition of
the second tool in the NASA milling dataset.
C. IMPROVED KERNEL EXTREME LEARNING
MACHINE
The KELM problem can be expressed as minimizing an
objective function [61]:


n
i
i
F
C
1
22
,22
1
min


(4)
ixfyts i
T
ii  ),(..

where β= [β1β2…βL]Tis the vector of output weights
between the Lnodes of the hidden layer and the output node,
||•||Fis the Frobenius norm, εiis the training error of the i-th
training sample, Cis the regularization parameter that
facilitates a tradeoff between the norm of output weights and
training errors, (X,Y) = {(x1,y1), (x2,y2), …, (xn,yn)} is the
training sample set, and f(xi) = [f(xi1)f(xi2) … f(xiL)]Tis the
hidden-layer output vector with respect to xi. Here, f(•) is a
form of feature mapping that maps the input data from the
original dimension space to the L-dimensional hidden-layer
feature space. The optimal value of β(βˆ) that minimizes Eq.
(4) can be efficiently solved as follows:
Y
C
ITT 1
)(
ˆ


(5)
where Φ is the hidden layer output matrix, Iis an identity
matrix, and Yis the dependent value vector in the training
samples. Because the sensor signals in TCM are high-
dimensional, nonlinear, and heterogeneous, the feature
mapping
)(

is unknown. Therefore, we define a kernel
matrix for the extreme learning machine (ELM) using
Mercer’s conditions, as follows:
},{ ij
T


),()()( jijiij xxkxx 

(6)
Then, the prediction score for test point xis determined as
follows.
Y
C
I
xxk
xxk
Y
C
I
xy
T
n
TT
x
1
1
1)(
),(
),(
)()(  













(7)
In this context, which is similar to the context of SVM,
)(

need not be known. Instead, a common kernel
function, such as a Gaussian, linear, or polynomial kernel,
can be used. In addition, the dimensionality Lof the feature
space (number of hidden nodes) need not be explicitly
given.
However, as discussed in Section 2, KELM underperforms
with respect to the extraction of inherent features in raw data.
The discussed drawbacks of KELM are addressed in the
present work by proposing an improved KELM denoted as
two-layer angle KELM (TAKELM), which introduces an
angle kernel function to avoid manual presets or tuning of the
kernel function hyperparameter. The TAKELM architecture
is illustrated in Figure 5. In detail, the input layer in the
training phase consists of the independent variables xiof the
training samples X, and each variable xiincludes 3 × Ns
feature parameters, where Ns denotes the number of applied
current sensors. The two hidden layers consist of the

This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.2995586, IEEE Access
Author Name: Preparation of Papers for IEEE Access (February 2017)
2 VOLUME XX, 2017
optimization of two output weight vectors, where one is the
weight between hidden layer 1 and the hidden input layer
assigned according to Eq. (5) using the angle kernel k0, and
the other is the weight between hidden layer 2 and the output
layer assigned according to Eq. (5) using the angle kernel k1.
The output layer consists of the tool wear values yi
corresponding to xi. In the testing phase, the input layer
consists of one independent variable x` to be predicted in the
testing samples, which includes nine features (i.e., three
features per sensor for three current sensors), and the output
layer is the predicted tool wear values y` assigned according
to Eq. (7).
FIGURE 5. Architecture of the proposed two-layer angle KELM (TAKELM)
Cho and Saul introduced a new kernel function denoted as
the arc-cosine kernel, which mimics the process flow in large,
multilayer neural nets [65]. The angle kernel function
measures the similarity between two vectors through their
angle. Let θdenote the angle between vectors xand y:









yx
yx
1
cos

(8)
A general n-th order kernel function in this family can be
written as follows:
)(
1
),(


n
nn
nJyxyxk 
(9)
where the angular dependences are captured by the functions
Jn(θ). These functions are given by














 




sinsin
1
)(sin)1()( 12
n
nn
n
J
(10)
In general, Jn(θ) takes its maximum value at θ= 0 and
decreases monotonically to zero at θ= π.
The first two expressions of Jn(θ) are given as follows:

)(
0
J
(11)

cos)(sin)(
1J
(12)
However, the angular dependence is more complicated for
n> 1, which could affect the learning speed of TAKELM.
Therefore, the kernel function is truncated at n= 1 in the
present work. We also note the absence of any continuous
tuning parameter in Eqs. (11) and (12), which avoids the
drawback associated with manually presetting or CV tuning
of a hyperparameter. Thus, the k0and k1angle kernels are,
respectively, used as the kernel functions of the first and
second hidden layers in TA-KELM, as shown in Figure 5.
These kernels are given as follows:



),(
0yxk
(13)
)cos)((sin
1
),(
1


 yxyxk
(14)
IV. COMPARATIVE VALIDATION USING BENCHMARK
MILLING DATA
A. DESCRIPTION OF MILLING DATASET
The NASA milling dataset employed for validation testing of
the proposed TCM method was obtained from the Matsuura
machining center (MC-510V) during dry rough milling
processes of cast iron or stainless steel J45 workpieces using
a six-tooth face milling cutter with KC710 carbide inserts
under different cutting parameters. The individual milling
conditions are listed in Table I. The parameter selections
were guided by industrial applicability and recommended
manufacturer settings. Therefore, the cutting speed was set to
200 m/min and the spindle speed was 826 rpm. Two different
depths of cut were selected, that is, 1.5 mm and 0.75 mm,
and two feed rates were considered, that is, 0.0833 mm/tooth
and 0.0417 mm/tooth. The dataset includes sensor signals
obtained from two vibration accelerometers, two AE sensors,
and two CTA 213 current sensors clamped on the cable
connectors for measuring the AC current of the AC spindle
motor and the DC current of the DC spindle motor. Sampling
of the sensor signals was conducted using LabVIEW, and the
signals were directly transmitted to a computer for storage.
Each experimental case was initiated with a new cutting tool,
and the flank wear of each of the six inserts was measured
offline based on optical microscopy imaging after each
surface of the workpiece was completely finished. The flank
wear associated with the insert obtaining the maximum flank
wear value was used as the tool wear value. Here, a
completely milled surface represents a single milling stage,
and the number of milling stages varied depending upon the
milling parameters. Of the total number of 16 cases given in
the dataset, a total of 17 stages, including five stages in the 6-
th case, six stages in the 8-th case, and six stages in the 16-th
case were not considered in this paper due to incomplete
measured tool wear data. This yielded a total of 150 complete
tool wear condition experimental datasets for the 13 cases
listed in Table I. It should be noted that the reduction in the
total sample size from 167 to 150 has little impact on the
proposed algorithm, which is designed for use with small
sample sizes. In addition, the cutting parameters of the 6-th,
8-th, and 16-th cases are the same as those of the 15-th, 14-th,
and 5-th cases, respectively. As a result, the loss of these

This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.2995586, IEEE Access
Author Name: Preparation of Papers for IEEE Access (February 2017)
2 VOLUME XX, 2017
three cases did not reduce the number of milling condition
types in the samples.
TABLE I
Experimental cutting parameters of the NASA milling dataset
Case
Depth of
cut (mm)
Feed rate
(mm/tooth)
Material
Number of
milling stages
1
1.5
0.0833
Cast iron
15
2
0.75
0.0833
Stainless steel J45
14
3
0.75
0.0417
Cast iron
14
4
1.5
0.0417
Cast iron
7
5
1.5
0.0833
Stainless steel J45
6
7
0.75
0.0417
Stainless steel J45
8
9
1.5
0.0833
Cast iron
9
10
1.5
0.0417
Cast iron
10
11
0.75
0.0417
Cast iron
23
12
0.75
0.0833
Cast iron
14
13
0.75
0.0417
Stainless steel J45
15
14
0.75
0.0833
Stainless steel J45
8
15
1.5
0.0417
Stainless steel J45
7
B. ANALYSIS AND RESULTS
The performance of the proposed TCM method was
evaluated for both workpiece materials by dividing the
sample set corresponding to the two materials into training
samples and test samples according to the different cutting
depths and feed rates. As can be seen in Table 1, cast iron
workpieces are employed in 8 cases (1–4, 9–12) and stainless
steel J45 workpieces are employed in 5 cases (5, 7, 13–15).
Therefore, the training set for cast iron was selected from the
2-th, 4-th, 9-th, and 11-th cases while the training set for
stainless steel J45 was selected from the 5-th and 13-th cases,
and the remaining cases (i.e., 1, 3, 10, and 12 for cast iron
and 7, 14, and 15 for stainless steel J45) were used as the
testing set. As such, the training set included data obtained
for 74 milling stages, while the testing set included that for
76 milling stages. In addition, the regularization parameter C
in TAKELM was optimized using a 10-fold CV method.
The ground truth tool wear values and the predicted values
obtained from the proposed TCM method based on
TAKELM are shown in Figure 6. Here, the wear results
obtained for the 7 tools employed in cases 1, 3, 7, 10, 12, 14,
and 15 are listed in sequence. Qualitatively, the tool wear
prediction results are observed to agree well with the ground
truth tool wear data. In addition, TCM methods based on
least squares SVM (LS-SVM) and KELM with current
sensor signals were applied to the NASA milling dataset, and
the Gaussian kernel was selected as the kernel function in
LS-SVM and KELM. The regularization parameter Cand the
hyperparameter hof the Gaussian kernel were optimized
using a 10-fold CV method. The tool wear prediction
performances of the TCM methods based on LS-SVM,
KELM, and TAKELM were evaluated according to several
performance metrics including the mean absolute error
(MAE), root mean square error (RMSE), and correlation
coefficient (R). The results for the three TCM methods are
presented in Table II. A comparison of the results indicates
that the proposed TCM method based on TAKELM provides
superior tool wear prediction from the standpoint of all
performance metrics considered.
TABLE II
SEVERAL PREDICTION PERFORMANCE INDICES OF DIFFERENT TCM
METHODS FOR THE NASA MILLING DATASET.
Method
MAE
RMSE
R
Regulari
zation C
Hyperpara
meter h
LS-SVM
0.0254
0.012
0.9889
18.1756
192.8442
KELM
0.0926
0.013
0.8648
2.0146
739.0018
TAKELM
0.0134
0.003
0.9967
2.1031
——
FIGURE 6. Predicted tool wear values of several methods with the testing set derived from the NASA milling dataset.

This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.2995586, IEEE Access
Author Name: Preparation of Papers for IEEE Access (February 2017)
4 VOLUME XX, 2017
V. EXPERIMENTAL INVESTIGATIONS
A. DESCRIPTION of EXPERIMENT
The experimental setup employed for conducting TCM under
various milling conditions is shown in Figure 7. A three-axis
VDL850A Vertical Machining Center (Dalian Machine Tools
Group, Dalian, China) was used for the experiments. The
cutting tool used in the experiments was an uncoated three-
tooth tungsten steel end milling cutter (Φ 10 mm), and the
workpiece material was #45 steel (carbon content is about
0.45%). Because the motor was a three-phase motor, three
current sensors were clamped on the motor wires to measure
the currents of the three phases of the motor. In addition,
several accelerometers were mounted on the spindle and
table for other research purposes. As shown in Figure 8(a),
the sensor signals were collected during tool-wear testing at a
continuous sampling frequency of 12 kHz using an Avant
MI-7016 data-acquisition instrument (Econ Technologies Co.,
Ltd., Hangzhou, China) and stored on a personal computer.
As shown in Figure 8(b), the wear of each individual flute of
the cutting tool was measured offline using a GP-300C
microscope (Gaopin Precise Instrument Co., Ltd., Suzhou,
China) each time after completely finishing a workpiece
surface. The workpieces were uniformly sized such that a
surface was completely finished after five cuts, that is, three
forward cuts and two backward cuts. It is noteworthy that we
found the influence of the length of rake face wear (KB) on
the surface roughness of the workpiece after milling was
greater than that of flank wear (VB) and the depth of rake
face wear (KT). Therefore, KB was employed as the tool
wear criterion in the experiments, and the tool wear value
after each cutting stage was defined as the maximum KB
value of the three teeth. Figure 9 illustrates the progression of
tool wear after finishing a single workpiece surface 1, 5, and
10 times (i.e., 1, 5, and 10 milling stages). Figure 10 presents
the tool wear value with respect to cutting time. It can be
seen that the tool wear varies greatly under the same feed rate
conditions.
A total of 14 operational conditions were generated with
a random combination of three cutting parameters: spindle
speed (2300, 2400, and 2500 rpm), depth of cut (0.4, 0.5,
and 0.6 mm), and feed rate (0.058, 0.065, and 0.072
mm/tooth). The operational parameters of each
experimental case are listed in Table III. Each experimental
case was initiated with a new tool, and varying numbers of
milling stages were conducted until the degree of measured
tool wear was at least 1.7 mm. Each milling stage consisted
of five cutting passes for finishing a surface (i.e., three
times forward and two times back). Each experimental case
involved 10 milling stages, except for the 7-th case (11
stages) and the 14-th case (7 stages), which represented
data collected for a total of 138 milling TCM samples.
B. ANALYSIS AND RESULTS
The signals obtained from the three current sensors
corresponding to the last cut in each milling stage were
selected to extract nine feature parameters ( i.e., three
feature parameters per sensor for three current sensors).
Considering the sample size of different cutting
parameters, the sample set was divided into training
samples and test samples according to the different cutting
depths and spindle speeds. The training set included cases
in which the spindle speed was 2300 rpm or 2400 rpm and
the cutting depth was 0.4 mm or 0.6 mm, while the testing
set included cases in which the spindle speed was 2500 rpm
and the cutting depth was 0.5 mm. Thus, the 1-st, 2-nd, 4-th,
5-th, 6-th and 8-th cases were selected for the training set
(Table III), and the remaining cases (i.e., 3, 7, and 9-14)
were used as the testing set. Therefore, the sample sizes in
the training and testing set were 60 and 78, respectively. In
addition, the regularization parameter Cin TAKELM was
optimized using a 10-fold CV method.
The ground truth tool wear values and the predicted
values obtained from the proposed TCM method based on
TAKELM for the testing set are shown in Figure 11. We
note here that the prediction results agree particularly well
with the ground truth data. Same as Section IV, the
proposed TAKELM method was compared with LS-SVM
and KELM. The Gaussian kernel was selected as the kernel
function in LS-SVM and KELM. The regularization
parameter and the hyperparameter of the Gaussian kernel
were optimized using a 10-fold CV method. The MAE,
RMSE, and R values obtained for these TCM methods are
listed in Table IV. A comparison of the results in the table
indicates that the proposed TCM method based on
TAKELM provides superior tool wear prediction from the
standpoint of all performance metrics considered. In fact,
the MAE and RMSE values obtained when using the
proposed method are sufficiently small as to represent a
practically negligible prediction error.
TABLE III
Operational conditions in the experiment.
Case
Spindle
speed (rpm)
Depth of
cut (mm)
Feed rate
(mm/tooth)
Number of
milling
stages
1
2300
0.4
0.058
10
2
2300
0.4
0.072
10
3
2300
0.5
0.065
10
4
2300
0.6
0.072
10
5
2300
0.6
0.058
10
6
2400
0.4
0.065
10
7
2400
0.5
0.072
11
8
2400
0.6
0.058
10
9
2500
0.4
0.072
10
10
2500
0.4
0.058
10
11
2500
0.5
0.058
10
12
2500
0.6
0.065
10
13
2500
0.6
0.072
10
14
2500
0.6
0.058
7

This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.2995586, IEEE Access
Author Name: Preparation of Papers for IEEE Access (February 2017)
6 VOLUME XX, 2017
FIGURE 7. Experimental setup
(a) Data-acquisition instrumentation (b) Optical microscopy tool imaging
FIGURE 8. Measurement instrumentation employed in the milling experiments
(a) First milling stage (b) Fifth milling stage (c) Tenth milling stage
FIGURE 9. Tool images indicative of different tool-wear values

This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.2995586, IEEE Access
Author Name: Preparation of Papers for IEEE Access (February 2017)
6 VOLUME XX, 2017
FIGURE 10. Tool wear with respect to cutting time in the milling experiments.
FIGURE 11. Predicted tool wear values of several methods with the testing set derived from the milling experiments.
TABLE IV
SEVERAL PREDICTION PERFORMANCE INDICES OF DIFFERENT TCM
METHODS FOR THE MILLING EXPERIMENTS.
Method
MAE
RMSE
R
Regulariz
ation C
Hyperpara
meter h
LS-SVM
0.2223
0.2775
0.9144
2.4105
44.7099
KELM
0.0912
0.1444
0.9655
347.4767
11.6987
TAKELM
0.0232
0.0328
0.9982
2.0328
——
VI. CONCLUSION
This study proposed a TCM method employing a few key
current sensor signal features based on the time, frequency,
and time-frequency domains of the signals and an advanced
monitoring model based on an improved KELM to achieve
excellent TCM performance for monitoring milling processes.
Current sensors were deemed to be most appropriate due to
their low cost and simple installation that has no effect on the

This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.2995586, IEEE Access
Author Name: Preparation of Papers for IEEE Access (February 2017)
VOLUME XX, 2017 9
milling process, while the selected multi-domain features,
which are strongly correlated with tool wear condition,
overcome the loss of useful information related to tool
condition when employing a single domain. The proposed
TAKELM employs an angle kernel function that includes no
hyperparameter. This approach overcomes the drawbacks of
KELM in terms of learning the features of complex nonlinear
data and avoiding the need for preselecting the kernel
function and its hyperparameter. The prediction performance
of the proposed method was verified by its application to the
open-access benchmark NASA milling dataset and separate
TCM experiments in comparison with TCM methods based
on the LS-SVM and KELM. The results demonstrate that the
proposed method outperforms the methods based on KELM
and LS-SVM and obtains prediction results with very small
errors. As such, the proposed TCM method achieves
excellent monitoring performance using only a few key
signal features of current sensors.
It must be noted that the NASA dataset and the separate
TCM experiments were both limited to cases involving low
spindle speeds (i.e., 826 and 2300-2500 rpm, respectively),
and only gradual changes in tool condition were observed.
Therefore, further investigation must be conducted for
verifying the effectiveness of the proposed TAKELM
method in high-speed milling and for monitoring other tool
conditions (e.g., chipping and breakage).
REFERENCES
[1] Javed, K.; Gouriveau, R.; Li, X.; Zerhouni, N. Tool wear monitoring
and prognostics challenges: A comparison of connectionist methods
toward an adaptive ensemble model. J. Intell. Manuf. 29(8)(2018), pp.
1873-1890.
[2] Konstantinos, S.; Athanasios, K. Reliability assessment of cutting tool
life based on surrogate approximation methods. Int. J. Adv. Manuf.
Technol., 71(2014), pp. 1197-1208.
[3] Karandikar, J.; Mcleay, T.; Turner, S.; Schmitz, T. Tool wear
monitoring using naïve bayes classifiers. Int. J. Adv. Manuf. Technol.,
77(2015), pp. 1613-1626.
[4] Vetrichelvan, G.; Sundaram, S.; Kumaran, S.S.; Velmurugan, P. An
investigation of tool wear using acoustic emission and genetic
algorithm. J. Vib. Control, 21(2014), pp. 3061-3066.
[5] Liu, C.; Wang, G.F.; Li, Z.M. Incremental learning for online tool
condition monitoring using ellipsoid artmap network model. Appl.
Soft Comput., 35(2015), pp. 186-198.
[6] Aliustaoglu, C.; Ertunc, H.M.; Ocak, H. Tool wear condition
monitoring using a sensor fusion model based on fuzzy inference
system. Mech. Syst. Signal Process., 23(2009), pp. 539-546.
[7] Gao, R.; Wang, L.; Teti, R.; Dornfeld, D.; Kumara, S.; Mori, M.; Helu,
M. Cloud-enabled prognosis for manufacturing. CIRP Ann., 64(2015),
pp. 749-772.
[8] Ghosh, N.; Ravi, Y.B.; Patra, A.; Mukhopadhyay, S.; Paul, S.;
Mohanty, A.R.; Chattopadhyay, A.B. Estimation of tool wear during
CNC milling using neural network-based sensor fusion. Mech. Syst.
Signal Process. 21(2007), pp. 466-479.
[9] Drouillet, C.; Karandikar, J.; Nath, C.; Journeaux, A.C.; Mansori,
M.E.; Kurfess, T. Tool life predictions in milling using spindle power
with the neural network technique. J. Manuf. Process., 22(2016), pp.
161-168.
[10]Chryssolouris, G.; Domroese, M.; Beaulieu, P. Sensor Synthesis for
Control of Manufacturing Processes. J. Eng. Ind. ASME, 114(1992),
pp. 158-174.
[11]Agogino, A.; Goebel, K. Mill Data Set [EB/OL]. http://ti.arc.nasa.gov/
project/prognostic- data- repository.
[12]Nouri, M.; Fussell, B.; Ziniti, B.; Linder, E. Real-time tool wear
monitoring in milling using a cutting condition independent method.
Int J Mach Tool Manuf, 89(2015), pp. 1-13.
[13]Zhang, H.; Zhao, J.; Wang, F.; Li, A. Cutting forces and tool failure
in high-speed milling of titanium alloy tc21 with coated carbide tools.
J Eng Manuf, 229(1) (2015), pp. 20-27.
[14]Wang, M.; Wang, J. CHMM for tool condition monitoring and
remaining useful life prediction. Int J Adv Manuf Technol, 59(5-8)
(2012), pp.463-471.
[15]Huang, P.; Ma, C.; Kuo, C. A PNN self-learning tool breakage
detection system in end milling operations. App Soft Comput, 37
(2015), pp. 114-124.
[16]Kaya, B.; Oysu, C.; Ertunc, H. Force-torque based on-line tool wear
estimation system for CNC milling of inconel 718 using neural
networks. Adv Eng Softw, 42(3)(2011), pp. 76-84.
[17]Prickett, P.; Johns, C. An overview of approaches to end milling tool
monitoring. Int J Mach Tool Manuf, 39(1) (1999), pp. 105-122.
[18]Koike, R.; Ohnishi, K. Aoyama, T. A sensorless approach for tool
fracture detection in milling by integrating multi-axial servo
information. CIRP Annals - Manuf Technol 65(1)(2016), pp. 385-388.
[19]Ghani, J.; Rizal, M.; Nuawi, M.; Ghazali, M.; Haron, C. Monitoring
online cutting tool wear using low-cost technique and user-friendly
GUI. Wear, 271(9-10)(2011), pp. 2619-2624.
[20]Stavropoulos, P.; Papacharalampopoulos, A.; Vasiliadis, E.; Chryss-
olouris, G. Tool wear predictability estimation in milling based on
multi-sensorial data. Int J Adv Manuf Technol, 82(1-4)(2016), pp.
509-521.
[21]Sevilla, P.; Robles, J.; Jauregui, J.; Jimenez, D. FPGA-based
reconfigurable system for tool condition monitoring in high-speed
machining process. Measurement, 64(2015), pp. 81-88.
[22]Sevilla, P.; Robles, J.; Muñiz, J.; Lee, F. Tool failure detection method
for high-speed milling using vibration signal and reconfigurable
bandpass digital filtering. Int J Adv Manuf Technol, 81(5-8)(2015), pp.
1-8.
[23]Sevilla, P.; Jauregui, J.; Herrera, G.; Robles, J. Efficient method for
detecting tool failures in high-speed machining process. J Eng Manuf,
227(4)(2013), pp. 473-482.
[24]Cuka, B.; Kim, D. Fuzzy logic based tool condition monitoring for
end-milling. Robot Comp Integ Manuf, 47(10)(2017), pp. 22-36.
[25]Wang, G.; Yang, Y.; Zhang, Y.; Xie, Q. Vibration sensor based tool
condition monitoring using ν, support vector machine and locality
preserving projection. Sens Actu Physical, 209(2014), pp. 24-32.
[26]Zhou, Y.Q.; Liu, X,F.; Li, F.P.; Sun, B.T.; Xue W. An online damage
identification approach for numerical control machine tools based on
data fusion using vibration signals. J Vib Cont, 21(15)(2015), pp.
2925-2936.
[27]Cao, X.C.; Chen, B.Q.; Yao, B.; He, W.P. Combining translation-
invariant wavelet frames and convolutional neural network for
intelligent tool wear state identification. Comput in Indus, 106(2019),
pp. 71-84.
[28]Zhang C, Yao X, Zhang J, Jin H (2016) Tool condition monitoring
and remaining useful life prognostic based on a wireless sensor in dry
milling operations. Sensors 16 795: 1-20
[29]Hsieh, W.; Lu, M.; Chiou, S. Application of backpropagation neural
network for spindle vibration-based tool wear monitoring in micro-
milling. Int J Adv Manuf Technol, 61(1-4)(2012), pp. 53-61.
[30]Madhusudana, C.; Kumar, H.; Narendranath, S. Condition monitoring
of face milling tool using k-star algorithm and histogram features of
vibration signal. Int J Eng Sci Technol, 19(3)(2016), pp. 1543-1551.
[31]Gao, C.; Xue, W.; Ren, Y.; Zhou, Y.Q. Numerical control machine
tool fault diagnosis using hybrid stationary subspace analysis and least
squares support vector machine with a single sensor. Applied Sci, 7(4)
346(2017), pp. 1-12.
[32]Yen, C.; Lu, M.; Chen, J. Applying the self-organization feature map
(som) algorithm to ae-based tool wear monitoring in micro-cutting.
Mech Syst Signal Pr 34(1-2) (2013), pp. 353-366.
[33]Pechenin, V.; Khaimovich, A.; Kondratiev, A.; Bolotov, M. Method
of controlling cutting tool wear based on signal analysis of acoustic
emission for milling. Procedia Eng, 176(2017), pp. 246-252.

This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/.
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2020.2995586, IEEE Access
Author Name: Preparation of Papers for IEEE Access (February 2017)
VOLUME XX, 2017 9
[34]Hassan, M.; Sadek A.; Attia, M.H.; Thomson V. Intelligent machining:
real-time tool condition monitoring and intelligent adaptive control
systems. J Machi Eng, 18(1) (2018), pp. 5-18.
[35]Mathew, M.; Pai, P.; Rocha, L. An effective sensor for tool wear
monitoring in face milling: acoustic emission. Sadhana, 33(3)(2008),
pp. 227-233.
[36]Ren, Q.; Balazinski, M.; Baron, L.; Jemielniak, K.; Botez, R.; Achiche,
S. Type-2 fuzzy tool condition monitoring system based on acoustic
emission in micromilling. Info Sci, 255(1)(2014), pp. 121-134.
[37]Zhu, K.P.; Vogel, B. Sparse representation and its applications in
micro-milling condition monitoring: noise separation and tool
condition monitoring. Int J Adv Manuf Technol, 70(1-4)(2014), pp.
185-199.
[38]Ammouri, A.; Hamade, R. Current rise criterion: a process-
independent method for tool-condition monitoring and prognostics. Int
J Adv Manuf Technol, 72(1-4)(2014), pp. 509-519.
[39]Ritou, M.; Garnier, S.; Furet, B.; Hascoet, J. Angular approach
combined to mechanical model for tool breakage detection by eddy
current sensors. Mech Syst Signal Pr, 44(1-2)(2014), pp. 211-220.
[40]Sevilla, P.; Herrera, G.; Robles, J.; Jáuregui, J. Tool breakage
detection in cnc high-speed milling based in feed-motor current
signals. Int J Adv Manuf Technol, 53(9-12)(2011), pp. 1141-1148.
[41]Hassan, M.; Sadek A.; Attia, M.H.; Thomson V. A novel generalized
approach for real-time tool condition monitoring. J of Manuf Sci Eng,
140(2) (2018), 021010.
[42]Rizal, M.; Ghani, J.; Nuawi, M.; Che, H. A review of sensor system
and application in milling process for tool condition monitoring. Rese
J Applied Sci Eng Technol, 7(10)(2014), pp. 2083-2097.
[43]Teti, R.; Jemielniak, K.; Donnell, G.O.; Dornfeld, D. Advanced
monitoring of machining operations. CIRP Annals- Manuf Technol,
59(2010), pp. 717-739.
[44]Hassan, M.; Sadek A.; Attia, M.H. A Generalized Multisensor Real-
Time Tool Condition – Monitoring Approach Using Deep Recurrent
Neural Network. Smart Sustain Manuf Syst, 3(2) (2019), pp. 41-52.
[45]Wang, P.; Gao, R. Stochastic tool wear prediction for sustainable
manufacturing. Procedia CIRP, 48(2016), pp. 236-241.
[46]Harris, K.; Triantafyllopoulos, K.; Stillman, E.; Mcleay, T. A
multivariate control chart for autocorrelated tool wear processes. Qual
Reliab Eng Int, 32(6)(2016), pp. 2093-2106.
[47]Torabi, A.J.; Meng, J.E.; Xiang, L. Application of clustering methods
for online tool condition monitoring and fault diagnosis in high-speed
milling processes. IEEE Systems Journal, 10(2)(2016), pp. 721-732.
[48]Downey, J.; Sullivan, D.; Nejmen, M. Real time monitoring of the cnc
process in a production environment- the data collection and analysis
phase. Procedia CIRP, 41(2016), pp. 920-926.
[49]Jahromi, A.; Meng, J.; Li, X. Sequential fuzzy clustering based
dynamic fuzzy neural network for fault diagnosis and prognosis.
Neurocomputing, 196(2016), pp. 31-41.
[50]Cho, S.; Binsaeid, S.; Asfour, S. Design of multisensor fusion-based
tool condition monitoring system in end milling. Int J Adv Manuf
Technol, 46(5-8)(2010), pp. 681-694.
[51]Zhu, K.P.; Wong Y.San.; Hong G.S. Multi-category micro-milling
tool wear monitoring with continuous hidden Markov models. Mech.
Syst. Signal Process, 23(2009), pp. 547-560.
[52]Yu, J.; Liang, S.; Tang, D.; Liu, H. A weighted hidden markov model
approach for continuous-state tool wear monitoring and tool life
prediction. Int J Adv Manuf Technol, 91(1-4)(2016), pp. 201-111.
[53] Kothuru, A.; Nooka, S.P.; Liu, R. Application of deep visualization in
CNN-based tool condition monitoring for end milling. Procedia
Manufacturing, 34(2019), pp. 995-1004.
[54]Wu, X.F.; Liu, Y.H.; Bi, S.Z. Intelligent Recognition of Tool Wear
Type Based on Convolutional Neural Networks[J]. Comput Integ
Manuf Syst, 25(8)(2019), pp. 1-16. (in China)
[55] Liu, S.H.; Zhang, R.J.; Zhang, S.L.; Ma C.; Zhang H.G. Prediction of
remaining Life of Cutting Tool Based on DNN. Journal of Harbin
Univer Sci Tech, 24(3)(2019), pp. 1-8.
[56]Zhao, R.; Wang, D.; Yan, R. Machine Health Monitoring Using Local
Feature-Based Gated Recurrent Unit Networks. IEEE Transactions on
Indus Electro, 65(2)(2018), pp. 1539-1548.
[57]Salimiasl, A.; Özdemir, A. Analyzing the performance of artificial
neural network (ANN)-, fuzzy logic (FL)-, and least square (LS)-
based models for online tool condition monitoring. Int J Adv Manuf
Technol, 87(1-4) (2016), pp. 1-14.
[58]Zhou, Y.Q, Xue, W. Review of tool condition monitoring methods in
milling processes. Int. J. Adv. Manuf. Technol. 96(2018), pp. 2509-
2523.
[59]Shawe, T.; Sun, S. A review of optimization methodologies in support
vector machines. Neurocompu 74(17)(2011), pp. 3609-3618.
[60]Huang, G.B. What are Extreme Learning Machines? Filling the Gap
Between Frank Rosenblatt’s Dream and John von Neumann’s Puzzle.
Cognit. Comput. 7(2015), pp. 263-278.
[61]Huang, G.; Huang, G.B.; Song, S.J.; You K.Y. Trends in extreme
learning machines: A review. Neural Networks, 61(2015), pp. 32-48.
[62]Gang, Song.; Qun, Dai. A novel double deep ELMs ensemble system
for time series forecasting. Knowl Based Syst, 134 (2017), pp. 31-49.
[63]Wang, J.; Xie, J.; Zhao, R.; Zhang, L.; Duan, L. Multisensory fusion
based virtual tool wear sensing for ubiquitous manufacturing. Robot.
Comput. Integr. Manuf. 45(2017), pp. 47-58.
[64]Cao, X.C.; Zeng, N.Y.; Chen, B.Q. Sparsity enhanced topological
fractal decomposition for smart machinery fault diagnosis. IEEE
Access, 6(2018), pp. 51886-51897.
[65]Cho, Y.; Saul, L.K. Kernel Methods for Deep Learning, Advances in
Neural Information Processing Systems, Conference on Neural
Information Processing Systems 2009, Vancouver, British Columbia,
Canada, (2009), pp. 342-350.