ArticlePDF Available

Abstract and Figures

Manufacturers have faced an increasing need for the development of predictive models that predict mechanical failures and the remaining useful life (RUL) of manufacturing systems or components. Classical model-based or physics-based prognostics often require an in-depth physical understanding of the system of interest to develop closed-form mathematical models. However, prior knowledge of system behavior is not always available, especially for complex manufacturing systems and processes. To complement model-based prognostics, data-driven methods have been increasingly applied to machinery prognostics and maintenance management, transforming legacy manufacturing systems into smart manufacturing systems with artificial intelligence. While previous research has demonstrated the effectiveness of data-driven methods, most of these prognostic methods are based on classical machine learning techniques, such as artificial neural networks (ANNs) and support vector regression (SVR). With the rapid advancement in artificial intelligence, various machine learning algorithms have been developed and widely applied in many engineering fields. The objective of this research is to introduce a random forests (RFs)-based prognostic method for tool wear prediction as well as compare the performance of RFs with feed-forward back propagation (FFBP) ANNs and SVR. Specifically, the performance of FFBP ANNs, SVR, and RFs are compared using an experimental data collected from 315 milling tests. Experimental results have shown that RFs can generate more accurate predictions than FFBP ANNs with a single hidden layer and SVR.
Content may be subject to copyright.
Dazhong Wu
Department of Industrial and
Manufacturing Engineering,
National Science Foundation
Center for e-Design,
Pennsylvania State University,
University Park, PA 16802
Connor Jennings
Department of Industrial and
Manufacturing Engineering,
National Science Foundation
Center for e-Design,
Pennsylvania State University,
University Park, PA 16802
Janis Terpenny
Department of Industrial and
Manufacturing Engineering,
National Science Foundation
Center for e-Design,
Pennsylvania State University,
University Park, PA 16802
Robert X. Gao
Department of Mechanical and
Aerospace Engineering,
Case Western Reserve University,
Cleveland, OH 44106
Soundar Kumara
Department of Industrial and
Manufacturing Engineering,
Pennsylvania State University,
University Park, PA 16802
A Comparative Study on
Machine Learning Algorithms
for Smart Manufacturing: Tool
Wear Prediction Using
Random Forests
Manufacturers have faced an increasing need for the development of predictive models
that predict mechanical failures and the remaining useful life (RUL) of manufacturing
systems or components. Classical model-based or physics-based prognostics often
require an in-depth physical understanding of the system of interest to develop closed-
form mathematical models. However, prior knowledge of system behavior is not always
available, especially for complex manufacturing systems and processes. To complement
model-based prognostics, data-driven methods have been increasingly applied to machin-
ery prognostics and maintenance management, transforming legacy manufacturing sys-
tems into smart manufacturing systems with artificial intelligence. While previous
research has demonstrated the effectiveness of data-driven methods, most of these prog-
nostic methods are based on classical machine learning techniques, such as artificial
neural networks (ANNs) and support vector regression (SVR). With the rapid advance-
ment in artificial intelligence, various machine learning algorithms have been developed
and widely applied in many engineering fields. The objective of this research is to intro-
duce a random forests (RFs)-based prognostic method for tool wear prediction as well as
compare the performance of RFs with feed-forward back propagation (FFBP) ANNs and
SVR. Specifically, the performance of FFBP ANNs, SVR, and RFs are compared using an
experimental data collected from 315 milling tests. Experimental results have shown that
RFs can generate more accurate predictions than FFBP ANNs with a single hidden layer
and SVR. [DOI: 10.1115/1.4036350]
Keywords: tool wear prediction, predictive modeling, machine learning, random forests
(RFs), support vector machines (SVMs), artificial neural networks (ANNs), prognostics
and health management (PHM)
1 Introduction
Smart manufacturing aims to integrate big data, advanced ana-
lytics, high-performance computing, and Industrial Internet of
Things (IIoT) into traditional manufacturing systems and proc-
esses to create highly customizable products with higher quality at
lower costs. As opposed to traditional factories, a smart factory
utilizes interoperable information and communications technolo-
gies (ICT), intelligent automation systems, and sensor networks to
monitor machinery conditions, diagnose the root cause of failures,
and predict the remaining useful life (RUL) of mechanical sys-
tems or components. For example, almost all engineering systems
(e.g., aerospace systems, nuclear power plants, and machine tools)
are subject to mechanical failures resulting from deterioration
with usage and age or abnormal operating conditions [13].
Some of the typical failure modes include excessive load, over-
heating, deflection, fracture, fatigue, corrosion, and wear. The
degradation and failures of engineering systems or components
will often incur higher costs and lower productivity due to unex-
pected machine downtime. In order to increase manufacturing
productivity while reducing maintenance costs, it is crucial to
develop and implement an intelligent maintenance strategy that
allows manufacturers to determine the condition of in-service sys-
tems in order to predict when maintenance should be performed.
Conventional maintenance strategies include reactive, preven-
tive, and proactive maintenance [46]. The most basic approach
to maintenance is reactive, also known as run-to-failure mainte-
nance planning. In the reactive maintenance strategy, assets are
deliberately allowed to operate until failures actually occur. The
assets are maintained on an as-needed basis. One of the disadvan-
tages of reactive maintenance is that it is difficult to anticipate the
maintenance resources (e.g., manpower, tools, and replacement
parts) that will be required for repairs. Preventive maintenance is
often referred to as use-based maintenance. In preventive mainte-
nance, maintenance activities are performed after a specified
period of time or amount of use based on the estimated probability
that the systems or components will fail in the specified time inter-
val. Although preventive maintenance allows for more consistent
and predictable maintenance schedules, more maintenance activ-
ities are needed as opposed to reactive maintenance. To improve
Corresponding author.
Manuscript received October 25, 2016; final manuscript received March 13,
2017; published online April 18, 2017. Assoc. Editor: Laine Mears.
Journal of Manufacturing Science and Engineering JULY 2017, Vol. 139 / 071018-1
Copyright V
C2017 by ASME
Downloaded from by The Pennsylvania State University user on 24 February 2020
the efficiency and effectiveness of preventive maintenance, pre-
dictive maintenance is an alternative strategy in which mainte-
nance actions are scheduled based on equipment performance or
conditions instead of time. The objective of proactive mainte-
nance is to determine the condition of in-service equipment and
ultimately to predict the time at which a system or a component
will no longer meet desired functional requirements.
The discipline that predicts health condition and remaining use-
ful life (RUL) based on previous and current operating conditions
is often referred to as prognostics and health management (PHM).
Prognostic approaches fall into two categories: model-based and
data-driven prognostics [712]. Model-based prognostics refer to
approaches based on mathematical models of system behavior
derived from physical laws or probability distribution. For exam-
ple, model-based prognostics include methods based on Wiener
and Gamma processes [13], hidden Markov models (HMMs) [14],
Kalman filters [15,16], and particle filters [1720]. One of the
limitations of model-based prognostics is that an in-depth under-
standing of the underlying physical processes that lead to system
failures is required. Another limitation is that it is assumed that
underlying processes follow certain probability distributions, such
as gamma or normal distributions. While probability density func-
tions enable uncertainty quantification, distributional assumptions
may not hold true in practice.
To complement model-based prognostics, data-driven prognos-
tics refer to approaches that build predictive models using learn-
ing algorithms and large volumes of training data. For example,
classical data-driven prognostics are based on autoregressive
(AR) models, multivariate adaptive regression, fuzzy set theory,
ANNs, and SVR. The unique benefit of data-driven methods is
that an in-depth understanding of system physical behaviors is not
a prerequisite. In addition, data-driven methods do not assume
any underlying probability distributions which may not be practi-
cal for real-world applications. While ANNs and SVR have been
applied in the area of data-driven prognostics, little research has
been conducted to evaluate the performance of other machine
learning algorithms [21]. Because RFs have the potential to han-
dle a large number of input variables without variable selection
and they do not overfit [2224], we investigate the ability of RFs
for the prediction of tool wear using an experimental dataset.
Further, the performance of RFs is compared with that of FFBP
ANNs and SVR using accuracy and training time.
The main contributions of this paper include the followings:
Tool wear in milling operations is predicted using RFs along
with cutting force, vibration, and acoustic emission (AE) sig-
nals. Experimental results have shown that the predictive
model trained by RFs is very accurate. The mean squared
error (MSE) on the test tool wear data is up to 7.67. The
coefficient of determination (R
) on the test tool wear data is
up to 0.992. To the best of our knowledge, the random forest
algorithm is applied to predict tool wear for the first time.
The performances of ANNs, support vector machines
(SVMs), and RFs are compared using an experimental data-
set with respect to the accuracy of regression (e.g., MSE and
) and training time. While the training time for RFs is lon-
ger than that of ANNs and SVMs, the predictive model built
by RFs is the most accurate for the application example.
The remainder of the paper is organized as follows: Section 2
reviews the related literature on data-driven methods for tool wear pre-
diction. Section 3presents the methodology for tool wear prediction
using ANNs, SVMs, and RFs. Section 4presents an experimental
setup and the experimental dataset acquired from different types of
sensors (e.g., cutting force sensor, vibration sensor, acoustic emis-
sion sensor) on a computer numerical control (CNC) milling
machine. Section 5presents experimental results, demonstrates the
effectiveness of the three machine learning algorithms, and com-
pares the performance of each. Section 6provides conclusions that
include a discussion of research contribution and future work.
2 Data-Driven Methods for Tool Wear Prediction
Tool wear is the most commonly observed and unavoidable
phenomenon in manufacturing processes, such as drilling, milling,
and turning [2527]. The rate of tool wear is typically affected by
process parameters (e.g., cutting speed and feed rate), cutting tool
geometry, and properties of workpiece and tool materials. Tay-
lor’s equation for tool life expectancy [28] provides an approxi-
mation of tool wear. However, with the rapid advancement of
sensing technology and increasing number of sensors equipped on
modern CNC machines, it is possible to predict tool wear more
accurately using various measurement data. This section presents
a review of data-driven methods for tool wear prediction.
Schwabacher and Goebel [29] conducted a review of data-
driven methods for prognostics. The most popular data-driven
approaches to prognostics include ANNs, decision trees, and
SVMs in the context of systems health management. ANNs are a
family of computational models based on biological neural net-
works which are used to estimate complex relationships between
inputs and outputs. Bukkapatnam et al. [3032] developed effec-
tive tool wear monitoring techniques using ANNs based on fea-
tures extracted from the principles of nonlinear dynamics.
and Karpat [33] presented a predictive modeling approach for sur-
face roughness and tool wear for hard turning processes using
ANNs. The inputs of the ANN model include workpiece hardness,
cutting speed, feed rate, axial cutting length, and mean values of
three force components. Experimental results have shown that the
model trained by ANNs provides accurate predictions of surface
roughness and tool flank wear. Palanisamy et al. [34] developed a
predictive model for predicting tool flank wear in end milling
operations using feed-forward back propagation (FFBP) ANNs.
Experimental results have shown that the predictive model based
on ANNs can make accurate predictions of tool flank wear using
cutting speeds, feed rates, and depth of cut. Sanjay et al. [35]
developed a model for predicting tool flank wear in drilling using
ANNs. The feed rates, spindle speeds, torques, machining times,
and thrust forces are used to train the ANN model. The experi-
mental results have demonstrated that ANNs can predict tool wear
accurately. Chungchoo and Saini [36] developed an online fuzzy
neural network (FNN) algorithm that estimates the average width
of flank wear and maximum depth of crater wear. A modified
least-square backpropagation neural network was built to estimate
flank and crater wear based on cutting force and acoustic emission
signals. Chen and Chen [37] developed an in-process tool wear
prediction system using ANNs for milling operations. A total of
100 experimental data were used for training the ANN model.
The input variables include feed rate, depth of cut, and average
peak cutting forces. The ANN model can predict tool wear with
an error of 0.037 mm on average. Paul and Varadarajan [38] intro-
duced a multisensor fusion model to predict tool wear in turning
processes using ANNs. A regression model and an ANN were
developed to fuse the cutting force, cutting temperature, and
vibration signals. Experimental results showed that the coefficient
of determination was 0.956 for the regression model trained by
the ANN. Karayel [39] presented a neural network approach
for the prediction of surface roughness in turning operations. A
feed-forward back-propagation multilayer neural network was
developed to train a predictive model using the data collected
from 49 cutting tests. Experimental results showed that the predic-
tive model has an average absolute error of 2.29%.
Cho et al. [40] developed an intelligent tool breakage detection
system with the SVM algorithm by monitoring cutting forces and
power consumption in end milling processes. Linear and polyno-
mial kernel functions were applied in the SVM algorithm. It has
been demonstrated that the predictive model built by SVMs can
recognize process abnormalities in milling. Benkedjouh et al. [41]
presented a method for tool wear assessment and remaining useful
life prediction using SVMs. The features were extracted from
cutting force, vibration, and acoustic emission signals. The experi-
mental results have shown that SVMs can be used to estimate the
071018-2 / Vol. 139, JULY 2017 Transactions of the ASME
Downloaded from by The Pennsylvania State University user on 24 February 2020
wear progression and predict RUL of cutting tools effectively. Shi
and Gindy [42] introduced a predictive modeling method by com-
bining least squares SVMs and principal component analysis
(PCA). PCA was used to extract statistical features from multiple
sensor signals acquired from broaching processes. Experimental
results showed that the predictive model trained by SVMs was
effective to predict tool wear using the features extracted by PCA.
Another data-driven method for prognostics is based on deci-
sion trees. Decision trees are a nonparametric supervised learning
method used for classification and regression. The goal of deci-
sion tree learning is to create a model that predicts the value of a
target variable by learning decision rules inferred from data fea-
tures. A decision tree is a flowchart-like structure in which each
internal node denotes a test on an attribute, each branch represents
the outcome of a test, and each leaf node holds a class label. Jiaa
and Dornfeld [43] proposed a decision tree-based method for the
prediction of tool flank wear in a turning operation using acoustic
emission and cutting force signals. The features characterizing the
AE root-mean-square and cutting force signals were extracted from
both time and frequency domains. The decision tree approach was
demonstrated to be able to make reliable inferences and decisions
on tool wear classification. Elangovan et al. [44] developed a deci-
sion tree-based algorithm for tool wear prediction using vibration
signals. Ten-fold cross-validation was used to evaluate the accuracy
of the predictive model created by the decision tree algorithm. The
maximum classification accuracy was 87.5%. Arisoy and
Ozel [45]
investigated the effects of machining parameters on surface micro-
hardness and microstructure such as grain size and fractions using a
random forests-based predictive modeling method along with
finite element simulations. Predicted microhardness profiles and
grain sizes were used to understand the effects of cutting speed,
tool coating, and edge radius on the surface integrity.
In summary, the related work presented in this section builds
on previous research to explore how the conditions of tool wear
can be monitored as well as how tool wear can be predicted using
predictive modeling. While earlier work focused on prediction of
tool wear using ANNs, SVMs, and decision trees, this paper
explores the potential of a new method, random forests, for tool
wear prediction. Further, the performance of RFs is compared
with that of ANNs and SVMs. Because RFs are an extension of
decision trees, the performance of RFs is not compared with that
of decision trees.
3 Methodology
This section presents the methodology for data-driven prognos-
tics for tool wear prediction using ANNs, SVR, and RFs. The
input of ANNs, SVR, and RFs is the following labeled training
where xi¼ðFX;FY;FZ;VX;VY;VZ;AEÞ,yi2R. The description
of these input data can be found in Table 1.
3.1 Tool Wear Prediction Using ANNs. ANNs are a family
of models inspired by biological neural networks. An ANN is
defined by three types of parameters: (1) the interconnection pat-
tern between different layers of neurons, (2) the learning process
for updating the weights of the interconnections, and (3) the acti-
vation function that converts a neuron’s weighted input to its out-
put activation. Among many types of ANNs, the feed-forward
neural network is the first and the most popular ANN. Back-
propagation is a learning algorithm for training ANNs in conjunc-
tion with an optimization method such as gradient descent.
Figure 1illustrates the architecture of the FFBP ANN with a
single hidden layer. In this research, the ANN has three layers,
including input layer i, hidden layer j, and output layer k. Each
layer consists of one or more neurons or units, represented by
the circles. The flow of information is represented by the lines
between the units. The first layer has input neurons which act as
buffers for distributing the extracted features (i.e., Fi) from the
input data (i.e., xi). The number of the neurons in the input layer
is the same as that of extracted features from input variables.
Each value from the input layer is duplicated and sent to all
neurons in the hidden layer. The hidden layer is used to process
and connect the information from the input layer to the output
layer in a forward direction. Specifically, these values entering a
neuron in the hidden layer are multiplied by weights wij . Initial
weights are randomly selected between 0 and 1. A neuron in the
hidden layer sums up the weighted inputs and generates a single
output. This value is the input of an activation function (sigmoid
function) in the hidden layer fhthat converts the weighted input
to the output of the neuron. Similarly, the outputs of all the neu-
rons in the hidden layer are multiplied by weights wjk . A neural
in the output layer sums up the weighted inputs and generates a
single value. An activation function in the output layer focon-
verts the weighted input to the predicted output ykof the ANN,
which is the predicted flank wear VB. The output layer has only
one neuron because there is only one response variable. The per-
formance of ANNs depends on the topology or architecture of
ANNs (i.e., the number of layers) and the number of neurons in
each layer. However, there are no standard or well-accepted
methods or rules for determining the number of hidden layers
and neurons in each hidden layer. In this research, the single-
hidden-layer ANNs with 2, 4, 8, 16, and 32 neurons in the hid-
den layer are selected. The termination criterion of the training
algorithm is that training stops if the fit criterion (i.e., least
squares) falls below 1.0 10
Table 1 Signal channel and data description
Signal channel Data description
Channel 1 FX: force (N) in Xdimension
Channel 2 FY:force (N) in Ydimension
Channel 3 FZ: force (N) in Zdimension
Channel 4 VX: vibration (g) in Xdimension
Channel 5 VY: vibration (g) in Ydimension
Channel 6 VZ: vibration (g) in Zdimension
Channel 7 AE: acoustic emission (V)
Fig. 1 Tool wear prediction using a feed-forward back-
propagation (FFBP) ANN
Journal of Manufacturing Science and Engineering JULY 2017, Vol. 139 / 071018-3
Downloaded from by The Pennsylvania State University user on 24 February 2020
3.2 Tool Wear Prediction Using SVR. The original SVM
for regression was developed by Vapnik and coworkers [46,47]. A
SVM constructs a hyperplane or set of hyperplanes in a high- or
infinite-dimensional space, which can be used for classification
and regression.
The framework of SVR for linear cases is illustrated in Fig. 2.
Formally, SVR can be formulated as a convex optimization
Minimize 1
Subject to
where x2v;C¼1, e¼0:1, and ni;n
i¼0:001. bcan be com-
puted as follows:
b¼yihx;xiiefor ai0;C
b¼yihx;xiefor a
For nonlinear SVR, the training patterns xican be preprocessed
by a nonlinear kernel function kðx;x0Þ:¼hUðxÞ;UðxÞi0, where
UðxÞis a transformation that maps xto a high-dimensional space.
These kernel functions need to satisfy the Mercer’s theorem.
Many kernels have been developed for various applications. The
most popular kernels include polynomial, Gaussian radial basis
function (RBF), and sigmoid. In many applications, a nonlinear
kernel function provides better accuracy. According to the litera-
ture [32,33], the Gaussian RBF kernel is one of the most effective
kernel functions used in tool wear prediction. In this research, the
Gaussian RBF kernel is used to transform the input dataset
D¼ðxi;yiÞ, where xiis the input vector and yiis the response
variable (i.e., flank wear) into a new dataset in a high-dimensional
space. The new dataset is linearly separable by a hyperplane in a
higher-dimensional Euclidean space as illustrated in Fig. 2. The
slack variables niand n
iare introduced in the instances where the
constraints are infeasible. The slack variables denote the deviation
from predicted values with the error of e¼0:1. The RBF kernel is
kðxi;xjÞ¼exp ðððkxixjk2Þ=2r2ÞÞ, where r2¼0:5. At the
optimal solution, we obtain
iÞUðxÞand fðxÞ¼X
3.3 Tool Wear Prediction Using RFs. The random forest
algorithm, developed by Breiman [22,48], is an ensemble learning
method that constructs a forest of decision trees from bootstrap
samples of a training dataset. Each decision tree produces a
response, given a set of predictor values. In a decision tree, each
internal node represents a test on an attribute, each branch repre-
sents the outcome of the test, and each leaf node represents a class
label for classification or a response for regression. A decision
tree in which the response is continuous is also referred to as a
regression tree. In the context of tool wear prediction, each indi-
vidual decision tree in a random forest is a regression tree because
tool wear describes the gradual failure of cutting tools. A compre-
hensive tutorial on RFs can be found in Refs. [22,48,49]. Some of
the important concepts related to RFs, including bootstrap aggre-
gating or bagging, slipping, and stopping criterion, are introduced
in Secs.
3.3.1 Bootstrap Aggregating or Bagging. Given a training
dataset D¼fðx1;y1Þ;ðx2;y2Þ;;ðxN;yNÞg, bootstrap aggregating
or bagging generates Bnew training datasets Diof size Nby sam-
pling from the original training dataset Dwith replacement. Diis
referred to as a bootstrap sample. By sampling with replacement
or bootstrapping, some observations may be repeated in each Di.
Bagging helps reduce variance and avoid overfitting. The number
of regression trees Bis a parameter specified by users. Typically,
a few hundred to several thousand trees are used in the random
forest algorithm.
3.3.2 Choosing Variables to Split On. For each of the boot-
strap samples, grow an un-pruned regression tree with the follow-
ing procedure: At each node, randomly sample mvariables and
choose the best split among those variables rather than choosing
the best split among all predictors. This process is sometimes
called “feature bagging.” The reason why a random subset of the
predictors or features is selected is because the correlation of the
trees in an ordinary bootstrap sample can be reduced. For regres-
sion, the default m¼p=3.
3.3.3 Splitting Criterion. Suppose that a partition is divided
into Mregions R1,R2,…, Rm. The response is modeled as a con-
stant cmin each region
The splitting criterion at each node is to minimize the sum of
squares. Therefore, the best c
cmis the average of yiin region Rm
Consider a splitting variable jand split point s, and define the
pair of half-planes
R1ðj;sÞ¼fXjXjsgand R2ðj;sÞ¼fXjXjsg(3.6)
The splitting variable jand split point sshould satisfy
For any jand s, the inner minimization is solved by
c1¼aveðyijxiR1ðj;sÞÞ and b
c2¼aveðyijxiR2ðj;sÞÞ (3.8)
Having found the best split, the dataset is partitioned into two
resulting regions and repeat the splitting process on each of the
two regions. This splitting process is repeated until a predefined
stopping criterion is satisfied.
3.3.4 Stopping Criterion. Tree size is a tuning parameter gov-
erning the complexity of a model. The stopping criterion is that
the splitting process proceeds until the number of records in Di
falls below a threshold, and five is used as the threshold.
Fig. 2 Tool wear prediction using SVR
071018-4 / Vol. 139, JULY 2017 Transactions of the ASME
Downloaded from by The Pennsylvania State University user on 24 February 2020
After Bsuch trees fTbgB
1are constructed, a prediction at a new
point xcan be made by averaging the predictions from all the indi-
vidual Bregression trees on x
rf x
ðÞ (3.9)
The random forest algorithm [48,49] for regression is as follows:
(1) Draw a bootstrap sample Zof size Nfrom the training data.
(2) For each bootstrap sample, construct a regression tree by
splitting a node into two children nodes until the stopping
criterion is satisfied.
(3) Output the ensemble of trees fTbgB
(4) Make a prediction at a new point xby aggregating the pre-
dictions of the Btrees.
The framework of predicting flank wear using an RF is illus-
trated in Fig. 3. In this research, a random forest is constructed
using B¼500 regression trees. Given the labeled training dataset
D¼ðxi;yiÞ, a bootstrap sample of size N¼630 is drawn from
the training dataset. For each regression tree, m¼9ðm¼ðp=3Þ;
p¼28Þvariables are selected at random from the 28 variables/
features. The best variable/split-point is selected among the nine
variables. A regression tree progressively splits the training data-
set into two child nodes: left node (with samples <z) and right
node (with samples z). A splitting variable and split point are
selected by solving Eqs. (3.7) and (3.8). The process is applied
recursively on the dataset in each child node. The splitting process
stops if the number of records in a node is less than 5. An
individual regression tree is built by starting at the root node of
the tree, performing a sequence of tests about the predictors, and
organizing the tests in a hierarchical binary tree structure as
shown in Fig. 4. After 500 regression trees are constructed, a pre-
diction at a new point can be made by averaging the predictions
from all the individual binary regression trees on this point.
4 Experimental Setup
The data used in this paper were obtained from Li et al. [50].
Some details of the experiment are presented in this section. The
experimental setup is shown in Fig. 5.
The cutter material and workpiece material used in the experi-
ment are high-speed steel and stainless steel, respectively. The
detailed description of the operating conditions in the dry milling
operation can be found in Table 2. The spindle speed of the cutter
was 10,400 RPM. The feed rate was 1555 mm/min. The Ydepth
of cut (radial) was 0.125 mm. The Zdepth of cut (axial) was
0.2 mm.
315 cutting tests were conducted on a three-axis high-speed
CNC machine (R
oders Tech RFM 760). During each cutting test,
seven signal channels, including cutting force, vibration, and
acoustic emission data, were monitored in real-time. The sampling
rate was 50 kHz/channel. Each cutting test took about 15 s. A sta-
tionary dynamometer, mounted on the table of the CNC machine,
was used to measure cutting forces in three, mutually perpendicu-
lar axes (x,y, and zdimensions). Three piezo accelerometers,
mounted on the workpiece, were used to measure vibration in
three, mutually perpendicular axes (x,y, and zdimensions). An
acoustic emission (AE) sensor, mounted on the workpiece, was
Fig. 3 Tool wear prediction using an RF
Fig. 4 Binary regression tree growing process
Fig. 5 Experimental setup
Journal of Manufacturing Science and Engineering JULY 2017, Vol. 139 / 071018-5
Downloaded from by The Pennsylvania State University user on 24 February 2020
used to monitor a high-frequency oscillation that occurs spontane-
ously within metals due to crack formation or plastic deformation.
Acoustic emission is caused by the release of strain energy as the
microstructure of the material is rearranged. After each cutting
test, the value of tool wear was measured off-line using a micro-
scope (Leica MZ12). The total size of the condition monitoring
data is about 8.67 GB.
5 Results and Discussion
In machine learning, feature extraction is an essential prepro-
cessing step in which raw data collected from various signal chan-
nels are converted into a set of statistical features in a format
supported by machine learning algorithms. The statistical features
are then given as an input to a machine learning algorithm. In this
experiment, the condition monitoring data were collected from (1)
cutting force, (2) vibration, and (3) acoustic emission signal chan-
nels. A set of statistical features (28 features) was extracted from
these signals, including maximum, median, mean, and standard
deviation as listed in Table 3.
Three predictive models were developed using ANNs, SVR,
and RFs, respectively. Two-thirds (2/3) of the input data (i.e.,
three datasets) were selected at random for model development
(training). The remainder (1/3) of the input data was used for
model validation (testing). Figures 68show the predicted against
observed tool wear values with the test dataset using ANNs, SVR,
and RFs, respectively. Figure 9shows the tool wear against time
with RFs.
In addition, the performance of the three algorithms was
evaluated on the test dataset using accuracy and training time.
Accuracy is measured using the R2statistic, also referred to as
the coefficient of determination, and mean squared error (MSE).
In statistics, the coefficient of determination is defined as
R2¼1ðSSE=SSTÞ, where SSE is the sum of the squares of
Table 2 Operating conditions
Parameter Value
Spindle speed 10,400 RPM
Feed rate 1555 mm/min
Ydepth of cut 0.125 mm
Zdepth of cut 0.2 mm
Sampling rate 50 kHz/channel
Material Stainless steel
Table 3 List of extracted features
Cutting force
Max Max Max
Median Median Median
Mean Mean Mean
Standard deviation Standard deviation Standard deviation
Fig. 6 Comparison of observed and predicted tool wear using
an ANN with 16 neurons in the hidden layer (termination crite-
rion: tolerance is equal to 1.0 310
Fig. 7 Comparison of observed and predicted tool wear using
SVR (termination criterion: slack variable or tolerance nis equal
to 0.001)
Fig. 8 Comparison of observed and predicted tool wear using
RFs (termination criterion: minimum number of samples in
each node is equal to 5)
071018-6 / Vol. 139, JULY 2017 Transactions of the ASME
Downloaded from by The Pennsylvania State University user on 24 February 2020
residuals, SST is the total sum of squares. The coefficient of deter-
mination is a measure that indicates the percentage of the response
variable variation that is explained by a regression model. A
higher R-squared indicates that more variability is explained by
the regression model. For example, an R2of 100% indicates that
the regression model explains all the variability of the response
data around its mean. In general, the higher the R-squared, the
better the regression model fits the data. The MSE of an estimator
measures the average of the squares of the errors. The MSE is
defined as MSE ¼ð1=nÞPn
yiyiÞ2, where b
yiis a predicted
value, yiis an observed value, and nis the sample size. The ANN,
SVR, and RF algorithms use between 50% and 90% of the input
data for model development (training) and use the remainder for
model validation (testing). Because the performance of ANNs
depends on the hidden layer configuration, five ANNs with a sin-
gle hidden layer but different number of neurons were tested on
the training dataset. Tables 48list the MSE, R-squared, and train-
ing time for the ANNs with 2, 4, 8, 16, and 32 neurons. With
respect to the performance of the ANN, the training time increases
as the number of neurons increases. However, the increased in
training time are not significant as shown in Fig. 10. In addition,
while the prediction accuracy increases as the number of neurons
increases, the performance is not significantly improved by adding
more than eight neurons in the hidden layer as shown in Figs. 11
and 12. Tables 9and 10 list the MSE, R-squared, and training
time for SVR and RFs. While the training time for RFs is longer
than that of ANNs and SVR, the predictive model built by RFs is
the most accurate as shown in Figs. 1012.
Table 5 Accuracy on the test data and training time for the
FFBP ANN with four neurons in the hidden layer
ANN (number of neurons ¼4)
Training size (%) MSE R
Training time (s)
50 43.428 0.958 0.122
60 51.001 0.951 0.084
70 43.645 0.958 0.093
80 45.661 0.955 0.103
90 45.058 0.958 0.118
Table 6 Accuracy on the test data and training time for the
FFBP ANN with eight neurons in the hidden layer
ANN (number of neurons ¼8)
Training size (%) MSE R
Training time (s)
50 36.810 0.964 0.167
60 34.168 0.968 0.186
70 39.795 0.961 0.202
80 44.175 0.957 0.197
90 46.634 0.954 0.234
Table 7 Accuracy on the test data and training time for the
FFBP ANN with 16 neurons in the hidden layer
ANN (number of neurons ¼16)
Training size (%) MSE R
Training time (s)
50 36.337 0.964 0.394
60 41.420 0.959 0.412
70 40.138 0.960 0.468
80 42.486 0.957 0.506
90 44.056 0.957 0.566
Fig. 9 Tool wear against time (cut) using RFs
Table 4 Accuracy on the test data and training time for the
FFBP ANN with two neurons in the hidden layer
ANN (number of neurons ¼2)
Training size (%) MSE R
Training time (s)
50 49.790 0.951 0.049
60 45.072 0.955 0.054
70 45.626 0.956 0.055
80 47.966 0.953 0.062
90 48.743 0.955 0.056
Table 8 Accuracy on the test data and training time for the
FFBP ANN with 32 neurons in the hidden layer
ANN (number of neurons ¼32)
Training size (%) MSE R
Training time (s)
50 35.305 0.965 1.165
60 38.612 0.963 1.301
70 38.824 0.963 1.498
80 42.469 0.959 1.496
90 48.138 0.953 1.633
Fig. 10 Comparison of training times
Journal of Manufacturing Science and Engineering JULY 2017, Vol. 139 / 071018-7
Downloaded from by The Pennsylvania State University user on 24 February 2020
6 Conclusions and Future Work
In this paper, the prediction of tool wear in milling operations
was conducted using three popular machine learning algorithms,
including ANNs, SVR, and RFs. The performance of these
algorithms was evaluated on the dataset collected from 315 mill-
ing tests. The performance measures include mean squared error,
R-squared, and training time. A set of statistical features was
extracted from cutting forces, vibrations, and acoustic emissions.
The experimental results have shown that while the training time
on the particular dataset using RFs is longer than the FFBP ANNs
with a single hidden layer and SVR, RFs generate more accurate
predictions than the FFBP ANNs with a single hidden layer and
SVR. The main contribution of this paper is twofold: (1) we dem-
onstrated that the predictive model trained by RFs can predict tool
wear in milling processes very accurately for the first time to the
best of our knowledge and (2) we compared the performance of
RFs with that of FFBP ANNs and SVR, as well as observed
that RFs outperform FFBP ANNs and SVR for this particular
application example.
In the future, a comparison of the performance of SVR and RFs
with that of other types of ANNs, such as recurrent neural networks
and dynamic neural networks, will be conducted. In addition, our
future work will focus on designing the parallel implementation of
machine learning algorithms that can be applied to large-scale and
real-time prognosis.
The research reported in this paper is partially supported by
NSF under Grant Nos. IIP-1238335 and DMDII-15-14-01. Any
opinions, findings, and conclusions or recommendations expressed
in this paper are those of the authors and do not necessarily reflect
the views of the National Science Foundation and the Digital Man-
ufacturing and Design Innovation Institute.
[1] Swanson, L., 2001, “Linking Maintenance Strategi es to Performance,” Int. J.
Prod. Econ.,70(3), pp. 237–244.
[2] Valdez-Flores, C., and Feldman, R. M., 1989, “A Survey of Preventive Mainte-
nance Models for Stochastically Deteriorating Single-Unit Systems,” Nav. Res.
Logist.,36(4), pp. 419–446.
[3] Wu, D., Terpenny, J., Zhang, L., Gao, R., and Kurfess, T., 2016, “Fog-Enabled
Architecture for Data-Driven Cyber-Manufacturing Systems,” ASME Paper
No. MSEC2016-8559.
[4] Lee, J., 1995, “Machine Performance Monitoring and Proactive Maintenance in
Computer-Integrated Manufacturing: Review and Perspective,” Int. J. Comput.
Integr. Manuf.,8(5), pp. 370–380.
[5] Bevilacqua, M., and Braglia, M., 2000, “The Analytic Hierarchy Process
Applied to Maintenance Strategy Selection,” Reliab. Eng. Syst. Saf.,70(1),
pp. 71–83.
[6] Suh, J. H., Kumara, S. R., and Mysore, S. P., 1999, “Machiner y Fault Diagnosis
and Prognosis: Application of Advanced Signal Processing Techniques,” CIRP
Ann.-Manuf. Technol.,48(1), pp. 317–320.
[7] Hu, C., Youn, B. D., and Kim, T., 2012, “Semi-Supervised Learning With Co-
Training for Data-Driven Prognostics,” IEEE Conference on Prognostics and
Health Management (PHM), Denver, CO, June 18–21, pp. 1–10.
[8] Schwabacher, M., 2005, “A Survey of Data-Driven Prognostics,” AIAA Paper
No. 2005-7002.
[9] Byrne, G., Dornfeld, D., Inasaki, I., Ketteler, G., K
onig, W., and Teti, R., 1995,
“Tool Condition Monitoring (TCM)—The Status of Research and Industrial
Application,” CIRP Ann.-Manuf. Technol.,44(2), pp. 541–567.
[10] Teti, R., Jemielniak, K., O’Donnell, G., and Dornfeld, D., 2010, “Advanced
Monitoring of Machining Operations,” CIRP Ann.-Manuf. Technol.,59(2),
pp. 717–739.
[11] Gao, R., Wang, L., Teti, R., Dornfe ld, D., Kumara, S., Mori, M., and Helu, M.,
2015, “Cloud-Enabled Prognosis for Manufacturing,” CIRP Ann.-Manuf. Tech-
nol.,64(2), pp. 749–772.
[12] Daigle , M. J., and Goebel, K., 2013, “Model-Based Prognostics With Concur-
rent Damage Progression Processes,” IEEE Trans. Syst. Man Cybernetics:
Syst.,43(3), pp. 535–546.
[13] Si, X.-S., Wang, W., Hu, C.-H., Chen, M.-Y., and Zhou, D.-H., 2013, “A
Wiener-Process-Based Degradation Model With a Recursive Filter Algorithm
for Remaining Useful Life Estimation,” Mech. Syst. Signal Process.,35(1),
pp. 219–237.
[14] Dong, M., and He, D., 2007, “Hidden Semi-Markov Model-Based Methodology
for Multi-Sensor Equipment Health Diagnosis and Prognosis,” Eur. J. Oper.
Res.,178(3), pp. 858–878.
Fig. 11 Comparison of MSEs
Fig. 12 Comparison of R-squared errors
Table 9 Accuracy on the test data and training time for SVR
with radial basis kernel
Training size (%) MSE R
Training time (s)
50 54.993 0.946 0.060
60 49.868 0.952 0.073
70 41.072 0.959 0.088
80 31.958 0.969 0.107
90 23.997 0.975 0.126
Table 10 Accuracy on the test data and training time for RFs
RFs (500 trees)
Training size (%) MSE R
Training time (s)
50 14.170 0.986 1.079
60 11.053 0.989 1.386
70 10.156 0.990 1.700
80 8.633 0.991 2.003
90 7.674 0.992 2.325
071018-8 / Vol. 139, JULY 2017 Transactions of the ASME
Downloaded from by The Pennsylvania State University user on 24 February 2020
[15] Saha, B., Goebel, K., and Christophersen, J., 2009, “Comparison of Prognostic
Algorithms for Estimating Remaining Useful Life of Batteries,” Trans. Inst.
Meas. Control,31(3–4), pp. 293–308.
[16] Niaki, F. A., Michel, M., and Mears, L., 2016, “State of Health Monitoring in
Machining: Extended Kalman Filter for Tool Wear Assessment in Turning of
IN718 Hard-to-Machine Alloy,” J. Manuf. Processes,24(Part 2), pp. 361–369.
[17] Orchard, M. E., and Vachtsevanos, G. J., 2009, “A Particle-Filtering Approach
for On-Line Fault Diagnosis and Failure Prognosis,” Trans. Inst. Meas. Control,
31(3–4), pp. 221–246.
[18] Wang, P., and Gao, R. X., 2015, “Adaptive Resampling-Based Particle Filtering
for Tool Life Prediction,” J. Manuf. Syst.,37(Part 2), pp. 528–534.
[19] Niaki, F. A., Ulutan, D., and Mears, L., 2015, “Stochastic Tool Wear Assess-
ment in Milling Difficult to Machine Alloys,” Int. J. Mechatronics Manuf.
Syst.,8(3–4), pp. 134–159.
[20] Wang, P., and Gao, R. X., 2016, “Stochastic Tool Wear Prediction for Sustain-
able Manufacturing,” Proc. CIRP,48, pp. 236–241.
[21] Sick, B., 2002, “On-Line 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.
[22] Breiman, L., 2001, “Random Forests,” Mach. Learn.,45(1), pp. 5–32.
[23] Biau, G., 2012, “An alysis of a Random Forests Model,” J. Mach. Learn. Res.,
13, pp. 1063–1095.
[24] Verikas, A., Gelzinis, A., and Bacauskiene, M., 2011, “Mining Data With
Random Forests: A Survey and Results of New Tests,” Pattern Recognit.,
44(2), pp. 330–349.
[25] Kamarthi, S., Kumara, S., and Cohen, P., 2000, “Flank Wear Estimation in
Turning Through Wavelet Representation of Acoustic Emission Signals,”
ASME J. Manuf. Sci. Eng.,122(1), pp. 12–19.
[26] Liang, S., and Dornfeld, D., 1989, “Tool Wear Detection Using Time Series
Analysis of Acoustic Emission,” J. Eng. Ind.,111(3), pp. 199–205.
[27] Huang, Y., and Liang, S. Y., 2004, “Modeling of CBN Tool Flank Wear Progression
in Finish Hard Turning,” ASME J. Manuf. Sci. Eng.,126(1), pp. 98–106.
[28] Taylor, F. W., 1907, On the Art of Cutting Metals, ASME, New York.
[29] Schwabacher, M., and Goebel, K., 2007, “A Survey of Artificial Intelligence
for Prognostics,” AAAI Fall Symposium, Arlington, VA, Nov. 9–11, pp.
[30] Bukkapatnam, S. T., Lakhtakia, A., and Kumara, S. R., 1995, “Analysis of Sen-
sor Signals Shows Turning on a Lathe Exhibits Low-Dimensional Chaos,”
Phys. Rev. E,52(3), p. 2375.
[31] Bukkapatnam, S. T., Kumara, S. R., and Lakhtakia, A., 2000, “Fractal Estima-
tion of Flank Wear in Turning,” ASME J. Dyn. Syst. Meas. Control,122(1), pp.
[32] Bukkapatnam, S., Kumara, S., and Lakhtakia, A., 1999, “An alysis of Acoustic
Emission Signals in Machining,” ASME J. Manuf. Sci. Eng.,121(4), pp.
Ozel, T., and Karpat, Y., 2005, “Predictive Modeling of Surface Roughness and
Tool Wear in Hard Turning Using Regression and Neural Networks,” Int. J.
Mach. Tools Manuf.,45(4), pp. 467–479.
[34] Palanisamy, P., Rajendra n, I., and Shanmugasundaram, S., 2008, “Prediction of
Tool Wear Using Regression and ANN Models in End-Milling Operation,” Int.
J. Adv. Manuf. Technol.,37(1–2), pp. 29–41.
[35] Sanjay, C., Neema, M., and Chin, C., 2005, “Modeling of Tool Wear in Drilling
by Statistical Analysis and Artificial Neural Network,” J. Mater. Process. Tech-
nol.,170(3), pp. 494–500.
[36] Chungchoo, C., and Sain i, D., 2002, “On-Line Tool Wear Estimation in CNC
Turning Operations Using Fuzzy Neural Network Model,” Int. J. Mach. Tools
Manuf.,42(1), pp. 29–40.
[37] Chen, J. C., and Chen, J. C., 2005, “An Artificial-Neural-Networks-Based In-
Process Tool Wear Prediction System in Milling Operations,” Int. J. Adv.
Manuf. Technol.,25(5–6), pp. 427–434.
[38] Paul, P. S., and Varada rajan, A., 2012, “A Multi-Sensor Fusion Model Based
on Artificial Neural Network to Predict Tool Wear During Hard Turning,”
Proc. Inst. Mech. Eng., Part B,226(5), pp. 853–860.
[39] Karayel, D., 2009, “Prediction and Control of SurfaceRoughness in CNC Lathe Using
Artificial Neural Network,” J. Mater. Process. Technol.,209(7), pp. 3125–3137.
[40] Cho, S., Asfou r, S., Onar, A., and Kaundinya, N., 2005, “Tool Breakage Detec-
tion Using Support Vector Machine Learning in a Milling Process,” Int. J.
Mach. Tools Manuf.,45(3), pp. 241–249.
[41] Benkedjouh, T., Medjaher, K., Zerhouni, N., and Rechak, S., 2015, “Health
Assessment and Life Prediction of Cutting Tools Based on Support Vector
Regression,” J. Intell. Manuf.,26(2), pp. 213–223.
[42] Shi, D., and Gindy, N. N., 2007, “Tool Wear Predictive Model Based on Least
Squares Support Vector Machines,” Mech. Syst. Signal Process.,21(4), pp.
[43] Jiaa, C. L., and Dornfeld, D. A., 1998, “A Self-Organizing Approach to the Pre-
diction and Detection of Tool Wear,” ISA Trans.,37(4), pp. 239–255.
[44] Elangovan, M., Devasenapati, S. B., Sakthivel, N., and Ramachandran, K.,
2011, “Evaluation of Expert System for Condition Monitoring of a Single Point
Cutting Tool Using Principle Component Analysis and Decision Tree Algo-
rithm,” Expert Syst. Appl.,38(4), pp. 4450–4459.
[45] Arisoy, Y. M., and
Ozel, T., 2015, “Machine Learning Based Predictive Model-
ing of Machining Induced Microhardness and Grain Size in Ti–6Al–4V Alloy,”
Mater. Manuf. Process.,30(4), pp. 425–433.
[46] Cortes, C., and Vapnik, V., 1995, “Support-Vector Networks,” Mach. Learn.,
20(3), pp. 273–297.
[47] Drucker, H., Burges, C. J., Kaufman, L., Smola, A., and Vapnik, V., 1997,
“Support Vector Regression Machines,” Advances in Neural Information Proc-
essing Systems, Vol. 9, pp. 155–161.
[48] Liaw, A., and Wiener, M., 2002, “Classification and Regression by Random
Forest,” R News,2(3), pp. 18–22.
[49] Friedman, J., Hastie, T., and Tibshirani, R., 2001, The Elements of Statistical
Learning, Springer Series in Statistics, Springer, Berlin.
[50] Li, X., Lim, B., Zhou, J., Huang, S., Phua, S., Shaw, K., and Er, M., 2009,
“Fuzzy Neural Network Modelling for Tool Wear Estimation in Dry Milling
Operation,” Annual Conference of the Prognostics and Health Management
Society (PHM), San Diego, CA, Sept. 27–Oct. 1, pp. 1–11.
Journal of Manufacturing Science and Engineering JULY 2017, Vol. 139 / 071018-9
Downloaded from by The Pennsylvania State University user on 24 February 2020
... The other types of models for degradation prediction are data-driven models. These models are mostly based on machine learning (ML) methods, which include support vector regression (SVR) [14][15][16], random forests (RFs) [17][18][19], artificial neural network (ANN) [20][21][22][23][24], etc. For example, by extracting features from the monitoring signals from a set of cutting tool, SVR can be adopted to fit the healthy features into a non-linear model. ...
... The obtained model can be used for estimating and predicting the amount of wear and calculate RUL of the cutting tool [14]. Similarly, the collected signals and the extracted features can also be used via RFs to determine the condition of the cutting tool and its RUL [19]. Compared with SVR, RFs usually need longer running time but show better performance. ...
... This makes direct monitoring difficult to employ in the industry. The indirect monitoring method collects the process signals, such as cutting forces [3,4], current [5,6], vibrations [7][8][9], sound [10,11], and acoustic emission [12,13] to estimate tool wear based on the close relationship between cutting signals and tool condition. With the advancement of sensing technology and artificial intelligence, it is possible to estimate tool wear more accurately and more efficiently using various sensor signals along with machine learning models. ...
... Both time and frequency domain signals were used for model training. Features were normalized using the maximum and minimum values of each feature so each input would be between 0 and 1. Wu et al. [7] compared the performance among Neural Networks (NN), Support Vector Regression (SVR), and Random Forests (RF) with data of milling stainless steels. Time domain signals of cutting forces, vibrations, and acoustic emissions were extracted by statistical methods. ...
Full-text available
Insufficient data is always a challenge for developing an accurate machine learning or deep learning model in manufacturing processes, especially in tool wear monitoring under varied cutting conditions. This paper presents a Random Forest model for predicting tool wear under varied cutting conditions as well as studies extracted signal features. The Random Forest algorithm was chosen as the machine learning model, rather than the novel deep learning model. This was due to the feature importance investigation, which was embedded in the Random Forest algorithm, thereby making it easier to study the physical meanings of signal features. The frequency domain signals were rearranged as features related to spindle speeds and machine tool structure based on domain knowledge. This is the first paper to rearrange the frequency domain signals for observing the physical meanings of selected features. When data normalization was adopted, frequency domain signals related to spindle speeds were excluded from important features. Only spectrum energy related to structure vibration and time domain signals were important features. Data normalization enhanced the weighting of structure vibration features in a machine learning model. This study showed that feature normalization made the machine learning model more adaptable to different cutting conditions. Furthermore, prediction accuracy for cutting condition of spindle speed = 42,000 rpm and feed = 1.5 μm/rev (lowest prediction accuracy among cutting tests in this study) showed an increase from 68.0 to 84.1%. In addition, spindle speed had a more significant effect than feed on classification accuracy in tool wear monitoring based on experimental results. As a result, at least two data sets of the same spindle speed as in tool wear prediction were recommended to be used for model training. When there were at least two data sets in training data with the same spindle speed as in testing data, the study showed prediction accuracies were greater than 75% without data normalization and 81% with data normalization.
... 19,20 Machine learning (ML) algorithms have been advocated to solve complex modeling and optimization problems in numerous engineering fields as numerical computational power has increased. 21 It is a subfield of artificial intelligence (AI) concerned with the creation of models (knowledge) that can efficiently learn from real data. 22−24 Over the last few decades, ML has evolved into a wide field of study, resulting in a variety of different algorithms, hypotheses, methods, implementation areas, etc. 25 However, learning/algorithms have been broadly classified into three categories: ...
Full-text available
Layer-by-layer film (LbL) coatings made of polyelectrolytes are a powerful tool for surface modification, including the applications in the biomedical field, for food packaging, and in many electrochemical systems. However, despite the number of publications related to LbL assembly, predicting LbL coating properties represents quite a challenge, can take a long time, and be very costly. Machine learning (ML) methodologies that are now emerging can accelerate and improve new coating development and potentially revolutionize the field. Recently, we have demonstrated a preliminary ML-based model for coating thickness prediction. In this paper, we compared several ML algorithms for optimizing a methodology for coating thickness prediction, namely, linear regression, Support Vector Regressor, Random Forest Regressor, and Extra Tree Regressor. The current research has shown that learning algorithms are effective in predicting the coating output value, with the Extra Tree Regressor algorithm demonstrating superior predictive performance, when used in combination with optimized hyperparameters and with missing data imputation. The best predictors of the coating thickness were determined, and they can be later used to accurately predict coating thickness, avoiding measurement of multiple parameters. The development of optimized methodologies will ensure different reliable predictive models for coating property/function relations. As a continuation, the methodology can be adapted and used for predicting the outputs connected to antimicrobial, anti-inflammatory, and antiviral properties in order to be able to respond to actual biomedical problems such as antibiotic resistance, implant rejection, or COVID-19 outbreak.
... The XGBoost algorithm is a part of Gradient Boosted Trees, a data-driven model that can identify welding quality during the welding process [24]. The complex nonlinear characteristics are attained using the sensor data in XGBoost models. ...
Full-text available
Smart industries use modern technologies such as machine learning and big data to maintain supply chain management and increase productivity but still the main challenge faced during quality control as this might affect the production rate. Smart industries are completely based on supervised learning that enables better inspection and effectively controls the parameter involved in the production process. Smart industries choose the mechanism that improves production and assures maximum quality. The various kernel function is initially used to select and extract a parameter. Support vector machine (SVM) is a supervised learning approach used in manufacturing industries to evaluate quality control. The SVM model uses the kernel function, namely RBF, along with Neural Networks, in identifying the parameter involved in quality management and undergoes the classification process. SVM consists of C-SVM and V-SVM classifier models involved in the classification process and undergoes training to handle the multiple numbers of consequence aroused during manufacturing. The performance of SVM classifiers and RBF NNs is evaluated. Different kernel functions, such as polynomial, linear, sigmoid, RBF, and over-varying gamma coefficient values, are tested in the experimental evaluation concerned with the comparative analysis of the continuous quality control function of the SVM classifier. Experimental results demonstrate the superiority of the SVM classifier in terms of the estimated computational time (88.1%), F1-measure (89.4%), ROC (65%), and accuracy (94.6%). The goal of the proposed model is to monitor the manufacturing process and control fault occurrence.
... Thus, many case-studies about ML applications in manufacturing fields have emerged [10,11]. For example, the tool wear prediction model can be established by ML containing relationships of complex parameters, which is difficult via model-or physics-based predictive models [12]. Such predictive maintenance in ML improves machine intelligence. ...
Full-text available
Feature recognition and manufacturability analysis from computer-aided design (CAD) models are indispensable technologies for better decision making in manufacturing processes. It is important to transform the knowledge embedded within a CAD model to manufacturing instructions for companies to remain competitive as experienced baby-boomer experts are going to retire. Automatic feature recognition and computer-aided process planning have a long history in research, and recent developments regarding algorithms and computing power are bringing machine learning (ML) capability within reach of manufacturers. Feature recognition using ML has emerged as an alternative to conventional methods. This study reviews ML techniques to recognize objects, features, and construct process plans. It describes the potential for ML in object or feature recognition and offers insight into its implementation in various smart manufacturing applications. The study describes ML methods frequently used in manufacturing, with a brief introduction of underlying principles. After a review of conventional object recognition methods, the study discusses recent studies and outlooks on feature recognition and manufacturability analysis using ML.
... Tool wear estimation utilizing cloud-based parallel machine learning is developed in order to increase cutting tool life during machining operations [75]. A comparative study on machine learning algorithms for smart factories is implemented in order to predict the tool wear during machining operations using random forests [76]. To assess tool wear conditions during milling operations under a variety of cutting circumstances with a high rate of response, sound waves signals utilizing advanced machine learning algorithms are used [77]. ...
Full-text available
Artificial Intelligence (AI) and Machine learning (ML) represents an important evolution in computer science and data processing systems which can be used in order to enhance almost every technology-enabled service, products, and industrial applications. A subfield of artificial intelligence and computer science is named machine learning which focuses on using data and algorithms to simulate learning process of machines and enhance the accuracy of the systems. Machine learning systems can be applied to the cutting forces and cutting tool wear prediction in CNC machine tools in order to increase cutting tool life during machining operations. Optimized machining parameters of CNC machining operations can be obtained by using the advanced machine learning systems in order to increase efficiency during part manufacturing processes. Moreover, surface quality of machined components can be predicted and improved using advanced machine learning systems to improve the quality of machined parts. In order to analyze and minimize power usage during CNC machining operations, machine learning is applied to prediction techniques of energy consumption of CNC machine tools. In this paper, applications of machine learning and artificial intelligence systems in CNC machine tools is reviewed and future research works are also recommended to present an overview of current research on machine learning and artificial intelligence approaches in CNC machining processes. As a result, the research filed can be moved forward by reviewing and analysing recent achievements in published papers to offer innovative concepts and approaches in applications of artificial Intelligence and machine learning in CNC machine tools.
... AI (V) attempts to replicate human intelligence with suitable algorithms, enabling autonomous decision-making, and thus situationally appropriate acting. As a sub-category of AI, ML (V) aims to develop learning data-driven computational algorithms with the goal of linking data, recognizing correlations, drawing conclusions, and optimization [29,[37][38][39]. Big Data (VI) refers to large volumes of heterogeneously structured data being gathered, analyzed, and disturbed at high speeds in order to extract valuable and trustworthy information [40,41]. ...
Full-text available
The advancement of laser ultrasonics has increased rapidly in recent years, providing applications for materials characterization as well as for industrial utilization, as a quality control device. The wide-ranging capabilities for high-temperature in-situ analysis of a variety of microstructural characteristics offers a multitude of possibilities for usage in R&D. To date, this is the only known method that has been successfully deployed for in-situ materials characterization, as well as in the harsh environment of the metalworking industry. Combined with the enablers, introduced by the fourth industrial revolution, and the conjunction of a laser ultrasonic system with a smart production lab, it has great potential to contribute to lower rejection rates, better recyclability, and consequently to a more sustainable production. In this review, the potential for systemic sustainability is explained throughout a part of the value chain, in the context of Industry 4.0. In addition, the integration of the methodology into a miniaturized Smart Production Lab is demonstrated, with the intention of incorporating it as a substantial part of the creation of a digital twin. Such a lab is designed to serve as an interface between laboratory and industry, in order to reveal the possibilities of digital transformation, Industry 4.0, and the application of highly flexible systems such as the laser-ultrasonic system for companies.
The identification of defects plays a key role in the semiconductor industry as it can reduce production risks, minimize the effects of unexpected downtimes and optimize the production process. A literature review protocol is implemented and latest advances are reported in defect detection considering wafer maps towards quality control. In particular, the most recent works are outlined to demonstrate the use of AI-technologies in wafer maps defect detection. The popularity of these technologies is then presented in the form of visualizing graphs. This enables the identification of the most popular and most prominent ML-methods that can be exploited for the purposes of Industry 4.0.
A manufacturing process is defined as the use of one or more physical mechanisms to transform the shape and/or form and/or properties of a material. This chapter discusses AI topics, related to manufacturing processes. Initially, there is a short introduction to the main categories of manufacturing processes, namely, forming, deforming, removing, joining and material properties modification processes. Then, the chapter discusses the role of AI in supporting key activities, at process level, including (i) process monitoring and data processing, (ii) process modeling, optimization and control, (iii) fault diagnosis, tool wear prediction and remaining useful life estimation and (iv) process quality assessment and prediction. For each topic, the scope and the theoretical background are initially provided and then selected cases of AI applications are discussed. At the end of this chapter, both the impact and the limitations of AI at manufacturing process level are discussed.
Full-text available
To provide scientific support for decision-making in critical applications such as maintenance scheduling and inventory management, tool wear monitoring and service life prediction are of significance to achieving sustainable manufacturing. Past research typically assumed time-invariant machining settings in modeling wear progression, hence is limited in accurately tracking varying wear rates. This paper presents a stochastic joint-state-and-parameter model with machining setting as a parameter that affects the state evolution or tool wear propagation. The model is embedded in a particle filter for recursive wear state prediction. Effectiveness of this method is verified through experimental data measured on a CNC milling machine.
Full-text available
An Extended Kalman Filter (EKF) is employed in this work for tracking tool flank wear area in wet-turning of Inconel 718 (IN718) nickel-based alloy in variable feed condition. The tool wear area evolution is modeled with a 3rd order polynomial empirical function and an analytical solution for discrete state space system is derived. The state uncertainty was found to decrease up to a critical range of 200-250μm of average flank wear length, and then increase abruptly with an increase in tool wear. Therefore, the tool wear uncertainty was modeled with failure probability density, i.e. the bathtub function, while a constant uncertainty was considered for the measurement signal (spindle power). To demonstrate the significance of using this method, the root mean square error (RMSE) and the mean absolute error (MAE) were calculated and compared with deterministic method in estimation of the tool wear area. It was shown that the proposed estimation based on stochastic filter EKF increased the accuracy of estimation by maximum of 60%. Results for estimation of the rate of tool wear area indicate additional possible effects or transitions of effects at higher wear conditions.
Full-text available
In the machining industry, maximising profit is intuitively a primary goal; therefore continuously increasing machining process uptime and consequently productivity and efficiency is crucial. Tool wear plays an important factor in both machining uptime and quality, and since tool failure is related to the surface quality and the dimensional accuracy of the end product, it is essential to quantify and predict this phenomenon with the best possible certainty. One of the most common ways of tool wear prediction is through the use of low cost spindle current sensing technology which is used to measure spindle power consumption in CNC machines and relate power increase to tool wear. In this work, two methods of stochastic filtering (i.e. Kalman and particle filter) were used in predicting tool flank wear in machining difficult-to-machine materials through spindle power consumption measurements. Results show a maximum of 15% average error in estimation, which indicates the good potential of using stochastic filtering techniques in estimating tool flank wear. In addition, the particle filter was used for online estimation of a spindle power model parameter with uniform and Gaussian mixture models as the initial probability density functions, and the evolution of this parameter to the true posterior density function over time was investigated.
Full-text available
Advanced manufacturing depends on the timely acquisition, distribution, and utilization of information from machines and processes across spatial boundaries. These activities can improve accuracy and reliability in predicting resource needs and allocation, maintenance scheduling, and remaining service life of equipment. As an emerging infrastructure, cloud computing provides new opportunities to achieve the goals of advanced manufacturing. This paper reviews the historical development of prognosis theories and techniques and projects their future growth enabled by the emerging cloud infrastructure. Techniques for cloud computing are highlighted, as well as the influence of these techniques on the paradigm of cloud-enabled prognosis for manufacturing. Finally, this paper discusses the envisioned architecture and associated challenges of cloud-enabled prognosis for manufacturing.
Conference Paper
Over the past few decades, both small- and medium-sized manufacturers as well as large original equipment manufacturers (OEMs) have been faced with an increasing need for low cost and scalable intelligent manufacturing machines. Capabilities are needed for collecting and processing large volumes of real-time data generated from manufacturing machines and processes as well as for diagnosing the root cause of identified defects, predicting their progression, and forecasting maintenance actions proactively to minimize unexpected machine down times. Although cloud computing enables ubiquitous and instant remote access to scalable information and communication technology (ICT) infrastructures and high volume data storage, it has limitations in latency-sensitive applications such as high performance computing and real-time stream analytics. The emergence of fog computing, Internet of Things (IoT), and cyber-physical systems (CPS) represent radical changes in the way sensing systems, along with ICT infrastructures, collect and analyze large volumes of real-time data streams in geographically distributed environments. Ultimately, such technological approaches enable machines to function as an agent that is capable of intelligent behaviors such as automatic fault and failure detection, self-diagnosis, and preventative maintenance scheduling. The objective of this research is to introduce a fog-enabled architecture that consists of smart sensor networks, communication protocols, parallel machine learning software, and private and public clouds. The fog-enabled architecture will have the potential to enable large-scale, geographically distributed online machine and process monitoring, diagnosis, and prognosis that require low latency and high bandwidth in the context of data-driven cyber-manufacturing systems.
Thesupport-vector network is a new learning machine for two-group classification problems. The machine conceptually implements the following idea: input vectors are non-linearly mapped to a very high-dimension feature space. In this feature space a linear decision surface is constructed. Special properties of the decision surface ensures high generalization ability of the learning machine. The idea behind the support-vector network was previously implemented for the restricted case where the training data can be separated without errors. We here extend this result to non-separable training data.High generalization ability of support-vector networks utilizing polynomial input transformations is demonstrated. We also compare the performance of the support-vector network to various classical learning algorithms that all took part in a benchmark study of Optical Character Recognition.
Tool failure may result in losses in surface finish and dimensional accuracy of a finished part, or possible damage to the work piece and machine. This paper presents a Fuzzy Neural Network (FNN) which is designed and developed for machinery prognostic monitoring. The FNN is basically a multi-layered fuzzy-rule-based neural network which integrates a fuzzy logic inference into a neural network structure. The fuzzy rules help to speed up the learning process of the complex conventional neural network structure and improve the accuracy in prediction and rate of convergence. A case study for prediction of tool life in a dry milling operation is presented to demonstrate the viability of the proposed FNN for tool condition monitoring. A comparison was made in the case study on prediction performances of different models established with the same set of experimental data. It is shown that the FNN is superior to conventional Multi-Regression Models (MRM), Backpropagation Neural Networks (BPNN) and Radial Basis Function Networks (RBFN) in term of prediction accuracy and BPNN in learning speed.