metals

Article
A Comparative Study on the Effect of Welding
Parameters of Austenitic Stainless Steels Using
Artificial Neural Network and Taguchi Approaches
with ANOVA Analysis
Halil Ibrahim Kurt 1, * ID , Murat Oduncuoglu 1 , Necip Fazil Yilmaz 2 , Engin Ergul 3
and Ramazan Asmatulu 4
1 Department of Mechanical and Metal Technologies, Technical Sciences, Gaziantep University,
Gaziantep 27310, Turkey; murat@gantep.edu.tr
2 Department of Mechanical Engineering, Engineering Faculty, Gaziantep University,
Gaziantep 27310, Turkey; nfyilmaz@gantep.edu.tr
3 Izmir Vocational School, Dokuz Eylul University, Izmir 35380, Turkey; engin.ergul@deu.edu.tr
4 Department of Mechanical Engineering, Wichita State University, 1845 Fairmount, Wichita, KS 67260, USA;
ramazan.asmatulu@wichita.edu
* Correspondence: hikurt@gantep.edu.tr or hiakurt@gmail.com; Tel.: +90-342-317-1746




Received: 27 March 2018; Accepted: 4 May 2018; Published: 8 May 2018


Abstract: In order to investigate the structure of welds, austenitic stainless steel (SS) studs with a
diameter of 6 mm were welded to austenitic SS plates with a thickness of 5 mm using an arc stud
welding (ASW) method. The effects of the welding current, welding time, and tip volume of the stud
on the microstructure and ultimate tensile strength (UTS) of the welded samples were investigated
in detail. The formation of δ-ferrites was detected in the weld zone because of the higher heat
generated during the welding process. Higher welding current and time adversely affected the stud
and significantly reduced the UTS of the samples. The UTS of the joints was also estimated using
artificial neural network (ANN) and Taguchi approaches. The mathematical formulations for these
two approaches were given in explicit form. Experimental results showed that the neural network
results are more consistent with experimental results than those of the Taguchi method. Overall, it can
be concluded that in order to achieve good welding joints and high strength values, ASW parameters
should be investigated properly to determine the optimum conditions for each metal.

Keywords: stud welding; mechanical properties; ANN; Taguchi; ANOVA

1. Introduction
Welding is a major fabrication method and widely used to join materials through a fusion
process. Metallic materials are mainly considered in welding due to their excellent features and
properties [1–3]. Numerous metallic materials can be joined using various welding techniques,
including friction stir welding, friction stir spot welding, ultrasonic welding, gas tungsten arc welding,
laser welding, gas metal arc welding, and arc stud welding (ASW). All of these methods have different
advantages and disadvantages in terms of cost, appropriateness, labor, training, efficiency, time,
temperature, and simplicity [4–9]. The process parameters of welding are a crucial factor affecting the
welding quality.
The effects of friction stir welding parameters on the microstructure and mechanical properties
of AISI 316L austenitic stainless steel (SS) joints were investigated by Kumar et al. who used
different tool rotational speeds. The authors suggested that a higher tool rotational speed results in

Metals 2018, 8, 326; doi:10.3390/met8050326 www.mdpi.com/journal/metals

Metals 2018, 8, 326 2 of 13

plasticization of the material, and a lower tool rotational speed induces low plastic flow of the material.
The optimum properties were obtained at a tool rotational speed of 600 rev/min [10]. The influence
of welding parameters, such as welding current, base metal geometry, and welding time, on the
weld characteristics in the electric ASW process was discussed. It was reported that a higher welding
current considerably increased the hardness and penetration depth of welding zones in the metal
substrates [11]. Chi et al. used a new sensor to measure the effects of stud plunge depth and reported
that the proposed sensor had a precise stud plunge depth, which is a very important parameter in
the ASW process [12]. The welding current, welding time, and tip volume of the stud are the most
important factors affecting joint quality and strength. The high tip volume stud increases the formation
of flash, and a high welding current deforms the stud. Sufficient melting does not occur if a low welding
current and welding time are selected. In order to obtain quality, high-strength, and sound joints,
these parameters can be appropriately selected. It is well known that welding parameters significantly
affect the heat input, which affects the joint strength. The interactions and effects on heat input of these
factors should be considered in detail. The weldability of 2024-T3 aluminum alloy studs to an extruded
AZ80-F magnesium plate 3 mm thick was investigated using the ASW method The authors noted that
the optimal discharge voltage for the study was 300 V. Grain refinements of 1 µm thick were observed
near the joint interface of the AZ80-F magnesium and the Mg17 Al12 and Al3 Mg2 intermetallics [13].
The influences of keyhole gas tungsten arc welding parameters on the fusion zone profile of AISI 316L
stainless steel were analyzed. It was reported that the increase in welding current caused a rise of
weld depth and width. However, at a lower welding current, a completely penetrating keyhole could
not be obtained in the weld pool [14]. Ye et al. demonstrated the effects of welding parameters on the
mechanical properties, weld appearance, and interface of dissimilar aluminum/steel double-sided
butt welding-brazing. They determined that the optimum parameters are 13 V for the metal inert
gas (MIG) voltage, 70 A for tungsten inert gas (TIG) current, 13.5 for the MIG/TIG ratio, and 2 cm/s
for welding speed [15]. A high MIG voltage causes the formation of intermetallic compound with a
thicker layer, and the layer turns out to be thinner with a higher welding speed. Indeed, the joining of
dissimilar metals is recognized as a challenging process because of the major differences in physical,
chemical, mechanical, and metallurgical properties of the materials.
Recently, the ASW process has been extensively utilized for sheet metals in various industries,
such as automotive, ship, aircraft, electric, electronic, and construction. Different types of ASW methods
(e.g., capacitor discharge stud welding, short-cycle drawn ASW, and drawn ASW with shielding) are
used to weld metallic sheet materials, depending on the type of production, the amount of applied load,
and the type of materials and properties. The characteristics of ASW are influenced by stud diameter,
welding current, welding time, and tip volume of the stud. In other words, several parameters are
influential in achieving optimal mechanical properties and defect-free high-quality joints. To the best
of our knowledge, a comprehensive study related to 316 austenite stainless steel studs welded to
304 stainless steel plates by the arc stud welding method has not been carried out in the literature.
Therefore, this current study investigated in detail the weldability of AISI 316 SS studs to 304 SS plates
using the ASW process as well as influences of the welding current, welding time, and tip volume of
the stud on the microstructure and tensile behaviors of the joints. Also, a detailed statistical study was
executed using an artificial neural network (ANN) approach and a Taguchi approach with analysis of
variance (ANOVA) analysis.

2. Materials and Methods

In this study, austenitic stainless steel studs with a diameter of 6 mm and length of 45 mm, and 304
austenitic stainless steel plates with a thickness of 5 mm and width of 50 mm were purchased locally
and used without further treatment or modification.
A Soyer-BMK-16i type ASW machine (Heinz Soyer Bolzenschwei&technik GmbH, Munich,
Germany) was used in this study. Argon gas with a constant flow rate of 5 liters per minute was chosen
as a shield gas to protect the weld zone from oxidation and tarnishing.
Metals 2018, 8, 326 3 of 13

Tables 1 and 2 provide the compositions and mechanical properties of the stud and base metal
materials, respectively, utilized in this study. The welding operation was carried out using different
welding currents and times. Table 3 provides the maximum and minimum values of the welding
parameters employed.

Table 1. Composition (wt %) of stud and base metal utilized in this study.

Materials C Si Mn P S Cr Ni Mo Fe
Plate (304 SS) 0.08 1 2 0.045 0.03 18–20 8–10.5 - Balance
Stud (316 SS) 0.08 1 2 0.045 0.03 16–18 10–14 2–3 Balance

Table 2. Mechanical properties of stud and base metal utilized in this study [16].

Materials UTS (MPa) El. (%) Hardness (HV)

Plate (304) 515 - 55 275
Stud (316) 515 - 55 275

Table 3. Maximum and minimum values of welding parameters utilized in this study.

Level Welding Current (amps) Welding Time (s) Lift (mm) Plunge (mm)
Min 400 0.10
3 2
Max 550 0.15

Lift and plunge values were adjusted as 3 and 2 mm in all tests, respectively. The tip volume of
the stud (TVS) (V: mm3 ) was calculated using Equation (1):
   2 
180 − 2d 
 
1  h
V= π sin ·     ·h (1)
3 2 cos 180−2d 2

where h is plunge, and d is the tip angle of the stud.

Lift is the distance between the stud tip and the surface of the workpiece when the stud is pulled
away by the solenoid coil in the stud gun. Plunge is the length of the stud metal that appears at the end
of the gas shroud ring. Plunge and tip angle significantly affect the tip volume of stud, but lift does not
affect it. The increasing plunge value (h) increases the tip volume of the stud. However, the increasing
tip angle (d) value decreases the tip volume of the stud. In other words, if the “d” value reaches zero,
then the maximum value of the tip volume of the stud is obtained. Following the welding process,
the prepared specimens were sectioned by cutting them from the middle of the stud metal using a
wire electrical discharge machine (EDM) (Carmar accuracy Co., Ltd., Taichung, Taiwan), and then
they were ground and polished for surface microstructural studies. After the grinding and polishing
process, the specimens were also etched using a modified Keller’s reagent (10 mL HNO3 , 1.5 mL HCl,
1.0 mL HF, and 87.5 mL distilled water) in order to obtain clear images. An optical microscope (Nikon
MA 100, Nikon, Tokyo, Japan) was used to examine the microstructures. In order to evaluate the
weld quality, tensile tests were conducted on the samples using a universal tensile test machine and
performed according to the ISO 14555 standard. Three tensile tests were carried out, and the average
of results was reported.
Metals 2018, 8, 326 4 of 13

3. Results

3.1. Macro-Micro Structures of Welds

Figure 1 shows macroscopic views of some welded specimens at different welding parameters.
Visual inspection with the naked eye did not reveal many macroscopic defects and other flaws on
the prepared weld samples. Because of the high welding current, the welding zone of the sample
(Figure
Metals 1f)8,isx FOR
2018, higher than
PEER the other samples, as is clearly shown by excessive fusion of the stud. 4 of 13
REVIEW
Metals 2018, 8, x FOR PEER REVIEW 4 of 13

Figure
Figure 1.
1.Macroscopic
Macroscopicviewsviewsof of
welded
weldedspecimens with
specimens varying
with parameters:
varying parameters:(a) 400-0.15-3-2-10°; (b)
(a) 400-0.15-3-2-10 ◦;
Figure 1. Macroscopic views of welded specimens with varying parameters: (a) 400-0.15-3-2-10°; (b)
400-0.15-3-2-20°; (c)
◦ 400-0.10-3-2-20°; (d)
◦ 500-0.10-3-2-0°; (e)
◦ 500-0.10-3-2-30°;◦ and (f) 550-0.10-3-2-30°.
◦
(b) 400-0.15-3-2-20 ; (c) 400-0.10-3-2-20 ; (d) 500-0.10-3-2-0 ; (e) 500-0.10-3-2-30 ; and (f) 550-0.10-3-2-30 .
400-0.15-3-2-20°; (c) 400-0.10-3-2-20°; (d) 500-0.10-3-2-0°; (e) 500-0.10-3-2-30°; and (f) 550-0.10-3-2-30°.
Figure 2 exhibits the cross-sectional image and microstructure of the specimen 400-0.15-3-2
Figure
Figure22exhibits
exhibitsthethe
cross-sectional image
cross-sectional and and
image microstructure of theof
microstructure specimen 400-0.15-3-2
the specimen shown
400-0.15-3-2
shown previously in Figure 1b.
previously in Figure
shown previously in1b.
Figure 1b.

Figure 2. Specimen 400-0.15-3-2: (a) cross-section image and (b) microstructure.

Figure 2.
Figure 2. Specimen
Specimen 400-0.15-3-2:
400-0.15-3-2: (a)
(a) cross-section
cross-section image
image and
and (b)
(b) microstructure.
microstructure.
The cross-sectional image and the microstructure shown in Figure 2 belong to the specimen with
The cross-sectional image and the microstructure shown in Figure 2 belong to the specimen with
the maximum tensile strength.
The cross-sectional image and Noticeable defects were
the microstructure not observed
shown in Figureon the cross-section
2 belong images
to the specimen of
with
the maximum tensile strength. Noticeable defects were not observed on the cross-section images of
this sample (Figure
the maximum 2a).strength.
tensile In this welding experiment,
Noticeable defectsthree
weredistinct regionson
not observed weretheclearly observed:
cross-section base
images
this sample (Figure 2a). In this welding experiment, three distinct regions were clearly observed: base
metal, heat-affected zone (HAZ), and welding zone, also known as the weld metal
of this sample (Figure 2a). In this welding experiment, three distinct regions were clearly observed: and fusion zone,
metal, heat-affected zone (HAZ), and welding zone, also known as the weld metal and fusion zone,
as
baseindicated in Figure 2b. zone
metal, heat-affected The width
(HAZ),of and
the HAZ is relatively
welding zone, alsonarrow
known compared
as the weldto zones
metalof thefusion
and other
as indicated in Figure 2b. The width of the HAZ is relatively narrow compared to zones of the other
welding processes in
zone, as indicated conducted
Figure 2b.on thewidth
The specimens. A dendritic
of the HAZ structure
is relatively narrowwascompared
also detected along
to zones of the
the
welding processes conducted on the specimens. A dendritic structure was also detected along the
HAZ towards the center of the weld, which may indicate some structural changes
other welding processes conducted on the specimens. A dendritic structure was also detected along on the surface.
HAZ towards the center of the weld, which may indicate some structural changes on the surface.
the HAZ towards the center of the weld, which may indicate some structural changes on the surface.
3.2. Mechanical Properties
3.2. Mechanical Properties
3.2. Mechanical Properties
3.2.1. Neural Network Approach
3.2.1. Neural
3.2.1. Neural Network
Network Approach
Approach
In the neural network approach, tensile test results were divided into two groups of data sets:
In the
In the neural
neural network approach,
approach, tensile
tensile test
test results
results were
were divided
divided into
into two
two groups
groups ofof data
data sets:
sets:
training (75%) and network
testing (25%). The input variables included welding current (WC; amps), welding
training
training (75%)
(75%) and
and testing (25%). The input variables included welding current (WC; amps), welding
time (WT; s), and tiptesting
volume (25%).
of theThe input
stud variables
(TVS; mm3), soincluded
the finalwelding current (WC;
output variable is the amps),
ultimatewelding
tensile
time (WT; s), and tip volume of the stud (TVS; mm3), so the final output variable is the ultimate tensile
strength (UTS) of the prepared samples. All parameters were normalized in the range of 0 to 1.0 using
strength (UTS) of the prepared samples. All parameters were normalized in the range of 0 to 1.0 using
Equation (2):
Equation (2):
vr − vmin
θnormalized = vr − vmin (2)
θnormalized = max − vmin
v (2)
vmax − vmin
Metals 2018, 8, 326 5 of 13

time (WT; s), and tip volume of the stud (TVS; mm3 ), so the final output variable is the ultimate tensile
strength (UTS) of the prepared samples. All parameters were normalized in the range of 0 to 1.0 using
Equation (2):
vr − vmin
θnormalized = (2)
vmax − vmin
Metals
where 2018,
vr 8,isx FOR
the PEER REVIEWand
variables, 5 ofthe
vmax and vmin are the maximum and minimum values in 13
model, respectively.
performance. Explanations about the layers, R, MAE, MAPE, and MSE have been provided in detail
MetalsVarious
2018, 8, x neuron
FOR PEERnumbers
REVIEW (1–7) were used to fix the model architecture, when error-evaluation 5 of 13
in other were
criteria studies [17–19].
utilized Figures
from 3 and square
the mean 4 provide the(MSE),
error influences
mean of absolute
neuron numbers for training
error (MAE), and
and mean
test sets,
absolute respectively.
percentage error (MAPE).
performance. Explanations about theThe correlation
layers, R, MAE,coefficient
MAPE, and (R)MSE
was have
used been
to calculate
providedtheinmodel
detail
performance.
in other studies Explanations about the
[17–19]. Figures layers,
3 and R, MAE,
4 provide theMAPE, and of
influences MSE have been
neuron provided
numbers in detailand
for training in
other studies
test sets, [17–19]. Figures 3 and 4 provide the influences of neuron numbers for training and test
respectively.
MSE Correlation MAE
sets, respectively.
1
0.9 MSE Correlation MAE
0.81
0.7
0.9
0.6
0.8
Impact Impact

0.5
0.7
0.4
0.6
0.3
0.5
0.2
0.4
0.1
0.3
0
0.2
0.1 1 2 3 4 5 6 7
0 Neuron numbers
1 2 3 4 5 6 7
Neuronnumbers
Figure 3. Influence of neuron numbersfor training set.
Figure 3. Influence of neuron numbers for training set.
Figure 3. Influence of neuron numbers for training set.
MSE Correlation MAE

1
MSE Correlation MAE
0.9
0.81
0.7
0.9
0.6
0.8
Impact Impact

0.5
0.7
0.4
0.6
0.3
0.5
0.2
0.4
0.1
0.3
0
0.2
1 2 3 4 5 6 7
0.1
0 Neuron numbers
1 Figure 4.2 Influence3of neuron4numbers for
5 test set. 6 7
Neuron numbers
Figure 4. Influence of neuron numbers for test set.

For the training set, the minimum MSE and MAE values are 0.0274 and 0.1098, respectively,
Figure 4. Influence of neuron numbers for test set.
while the maximum correlation value is 0.8323. For the test set, the minimum MSE and MAE values
are 0.0007 and 0.019, respectively, whereas the maximum correlation value is 0.9992. Equation (3)
For the training set, the minimum MSE and MAE values are 0.0274 and 0.1098, respectively,
shows the explicit formulation of ultimate tensile strength for the welds as a function of welding
while the maximum correlation value is 0.8323. For the test set, the minimum MSE and MAE values
parameters. This equation was procured using a macro value in MATLAB program. It could be
Metals 2018, 8, 326 6 of 13

For the training set, the minimum MSE and MAE values are 0.0274 and 0.1098, respectively,
while the maximum correlation value is 0.8323. For the test set, the minimum MSE and MAE values are
0.0007 and 0.019, respectively, whereas the maximum correlation value is 0.9992. Equation (3) shows
the explicit formulation of ultimate tensile strength for the welds as a function of welding parameters.
This equation was procured using a macro value in MATLAB program. It could be written down that
the proposed
Metals
Metals 2018, 8,
2018, 8, x explicit
x FOR
FOR PEERformulation
PEER REVIEW
REVIEW is forced for the given ranges of the experiments. 66 of
of 13
13

 
1
UTS = 543.28 × 1 + 246.46 (3)
UTS =
UTS = 543.28 × 1(( + e1−-w
543.28 × w ) + 246.46
) + 246.46 (3)
(3)
1 +
1+e e-w

where w
where w
where is
w is the
is theu1
the u1+ u2
u1 ++ u2 + u3
u2 ++ u3 u1, u2, and u3
u3 ++ 1.0144, in which u1, u2, and
+ 1.0144, in which u3 are
are the
are the empirical
the empirical values
empirical values given
values given below:
given below:
below:
u1
u1===(((1.0/(1.0
u1 (((1.0/(1.0 +++ exp(
(((1.0/(1.0 −1.0 ×
exp(−1.0
exp(−1.0 ×× (((x)
(((x) ××(14.0987))
(((x) × (14.0987)) +
(14.0987)) ++ ((y)
((y) ××(−10.1375))
((y) × (−10.1375))+
(−10.1375)) ++((z)
((z) ××(−22.6694))
((z)× (−22.6694))
(−22.6694)) ++ + (10.7274)))))×
(10.7274)))))
(10.7274))))) ×
× (25.5146)))
(25.5146)))
(25.5146)))
u2===(((1.0/(1.0
u2
u2 (((1.0/(1.0+++exp(
(((1.0/(1.0 −1.0 ××× (((x)
exp(−1.0
exp(−1.0 (((x)××× ((−1.5550))
(((x) −1.5550)) +++ ((y)
(−1.5550)) ((y)××× ((−7.7413))
((y) −7.7413)) +++ ((z)
(−7.7413)) ((z)××× ((−11.2698))
((z) −11.2698)) +++ (2.0932)))))
(−11.2698)) (2.0932)))))×××
(2.0932)))))
−19.3582)))
(−19.3582)))
((−19.3582)))
u3 ===(((1.0/(1.0
u3
u3 (((1.0/(1.0 +++exp(
(((1.0/(1.0 exp(−1.0
−1.0 ××× (((x)
exp(−1.0 (((x) ××× (2.1121))
(((x) (2.1121)) +++((y)
(2.1121)) ((y)×××(6.3599))
((y) (6.3599))+ ++((z)
(6.3599)) ((z)
× ××(−(−7.9340))
((z) (−7.9340)) +(−(−0.2742)))))
7.9340)) + + (−0.2742)))))
0.2742))))) ×××
(−13.6633)))
−13.6633)))
((−13.6633)))
wherex,x,
where
where x,y,y,
y,and
andzzzare
and arenormalized
are normalizedinput
normalized inputdata
input dataof
data ofthe
of thewelding
the weldingcurrent,
welding current,welding
current, weldingtime,
welding time,and
time, andtip
and tipvolume
tip volume of
volume of
of
thestud.
the
the stud.
stud.
Figures5–7
Figures
Figures 5–7illustrate
5–7 illustratethe
illustrate theeffects
the effectsofof
effects ofvarious
variouswelding
various welding
welding parameters
parameters on
onon
parameters the
thethe ultimate
ultimate tensile
tensile
ultimate strength
strength
tensile of
strength
of
the the welded
welded
of the welded joints.
joints.
joints.

Figure 5.
Figure
Figure 5. Variation
5. Variationof
Variation ofultimate
of ultimatetensile
ultimate tensilestrength
tensile strengthwith
strength withwelding
with weldingcurrent.
welding current.
current.

Figure6.6.
Figure
Figure 6. Effect
Effect of
Effect of welding
of weldingtime
welding timeon
time onultimate
on ultimatetensile
ultimate tensilestrength.
tensile strength.
strength.
Metals 2018, 8, 326 7 of 13
Metals 2018, 8, x FOR PEER REVIEW 7 of 13
Metals 2018, 8, x FOR PEER REVIEW 7 of 13

Figure 7.
Figure 7. Interaction
Interaction of
of ultimate
ultimate tensile
tensile strength
strength by
by tip
tip volume
volume of
of stud.
stud.
Figure 7. Interaction of ultimate tensile strength by tip volume of stud.
It was observed that the optimum experimental results of welding time, welding current, and
It
It was
was observed
observedthatthatthe
theoptimum
optimumexperimental
experimentalresults
resultsofof
welding
weldingtime, welding
time, welding current, andand
current, tip
tip volume of the stud in all cases were found for 0.13 s, 400 amps, and 2.79 mm3 3, respectively. It can
volume of the
tip volume stud
of the in all
stud cases
in all were
cases found
were found forfor
0.13 s, s,400
0.13 400amps,
amps,and
and2.79
2.79mm
mm3, ,respectively.
respectively. It
It can
can
also be seen that the rise of both welding current and welding time together deteriorates the tensile
also be seen that the rise of both welding current and welding time together deteriorates
also be seen that the rise of both welding current and welding time together deteriorates the tensile the tensile
results of the welds. UTS values of some samples were very high, and fracture in some of the prepared
results
results of
of the
the welds. UTS values
welds. UTS values of
of some
some samples
samples were
were very
very high,
high, and
and fracture
fracture in
in some
some ofof the
the prepared
prepared
specimens occurred at the stud, as shown in Figure 8a. Fracture in other specimens also took place at
specimens occurred at the stud, as shown in Figure 8a. Fracture in other specimens
specimens occurred at the stud, as shown in Figure 8a. Fracture in other specimens also took place also took place at
at
the weld zone (Figure 8b).
the weld zone (Figure
the weld zone (Figure 8b). 8b).

Figure 8. Fractured samples after tensile tests.

Figure 8. Fractured samples after tensile tests.
Figure 8. Fractured samples after tensile tests.
3.2.2. Taguchi Approach
3.2.2. Taguchi Approach
3.2.2. Taguchi Approach
The aims of this experimental design were to determine the effects of processing parameters on
The aims of this experimental design were to determine the effects of processing parameters on
the output
The aims products,
of this identify whichdesign
experimental of the selected
were to parameters
determine the haseffects
the greatest effect onparameters
of processing the output
the output products, identify which of the selected parameters has the greatest effect on the output
performance,
on the outputand define the
products, best possible
identify which of ranges of those parameters
the selected parameters in hasorder to obtaineffect
the greatest high-quality
on the
performance, and define the best possible ranges of those parameters in order to obtain high-quality
products.
output ANOVA is aand
performance, statistical
definetool
the that
bestispossible
used to determine
ranges of the differences
those parameters or similarities
in order tobetween
obtain
products. ANOVA is a statistical tool that is used to determine the differences or similarities between
groups of dataproducts.
high-quality [20]. Minitab
ANOVAsoftware
is aand the Taguchi
statistical tool method, which
that is used toare efficient tools
determine for the design
the differences or
groups of data [20]. Minitab software and the Taguchi method, which are efficient tools for the design
of high-quality
similarities product
between groupsmanufacturing systems,software
of data [20]. Minitab were usedandfor
thethe optimum
Taguchi design
method, of experiments
which are efficient
of high-quality product manufacturing systems, were used for the optimum design of experiments
[21]. for
tools ThetheTaguchi
design approach provides
of high-quality an orthogonal
product manufacturing array L9, which
systems, were was
usedselected based ondesign
for the optimum three
[21]. The Taguchi approach provides an orthogonal array L9, which was selected based on three
different
of welding
experiments [21].parameters.
The Taguchi This approach
approach recommends
provides analyzing
an orthogonal arraythe
L9,data
whichusing
wasthe mean based
selected effect
different welding parameters. This approach recommends analyzing the data using the mean effect
or signal-to-noise
on (S/N) ratio,
three different welding a logarithmic
parameters. This function
approachofrecommends
the desired result, which
analyzing theserves as an the
data using objective
mean
or signal-to-noise (S/N) ratio, a logarithmic function of the desired result, which serves as an objective
function
effect for the optimization
or signal-to-noise (S/N)ofratio,
the process parameters.
a logarithmic Thisoftechnique
function the desiredalso helpswhich
result, with data
servesanalysis
as an
function for the optimization of the process parameters. This technique also helps with data analysis
and prediction
objective functionof optimum levels during
for the optimization theprocess
of the joining parameters.
process [22].This technique also helps with data
and prediction of optimum levels during the joining process [22].
Theand
analysis S/Nprediction
ratio is the ratio of the
of optimum “signal”,
levels duringrepresenting the desirable
the joining process [22]. value, and the “noise”,
The S/N ratio is the ratio of the “signal”, representing the desirable value, and the “noise”,
representing the undesirable value. The signal-to-noise ratio
The S/N ratio is the ratio of the “signal”, representing the desirable is widely usedvalue,
to measure
and thethe“noise”,
quality
representing the undesirable value. The signal-to-noise ratio is widely used to measure the quality
performance the
representing andundesirable
significance value.
of the welding process. Theratio
The signal-to-noise S/N is
ratios were
widely calculated
used according
to measure to the
the quality
performance and significance of the welding process. The S/N ratios were calculated according to the
selected values of the formula for each experimental run. Figures 9 and 10 show
performance and significance of the welding process. The S/N ratios were calculated according to the main plots of the
selected values of the formula for each experimental run. Figures 9 and 10 show the main plots of the
S/N ratios
selected for tensile
values of the strength.
formula for each experimental run. Figures 9 and 10 show the main plots of the
S/N ratios for tensile strength.
S/N ratios for tensile strength.
Metals 2018, 8, 326 8 of 13
Metals 2018, 8, x FOR PEER REVIEW 8 of 13
Metals 2018, 8, x FOR PEER REVIEW 8 of 13

Metals 2018, 8, x FOR PEER REVIEW Main Effects Plot for Means 8 of 13
Data Means
Main Effects Plot for Means
WC (amps) Data Means WT (sec)
800
Main Effects
WC (amps) Plot for Means WT (sec)
750
800 Data Means
700
750
WC (amps) WT (sec)

(MPa)
800
650
700

(MPa)
750
600
650

of Means
700
600 400 500 550 0.10 0.13 0.15
(MPa)
of Means
650
400 TVS 500
(mm3) 550 0.10 0.13 0.15
800
600
Mean
Means

TVS (mm3)
750
800
400 500 550 0.10 0.13 0.15
Mean

700
750
TVS (mm3)
Mean of

800
650
700
750
600
650
700
600 0.260 1.109 56.548
650
0.260 1.109 56.548
600
Figure 9. Main effect plot for means of tensile strength.
Figure0.2609. Main effect plot
1.109 56.548for means of tensile strength.
Figure 9. Main effect plot for means of tensile strength.

Figure 9. Main effect plot for means of tensile strength.

Figure 10. Main effect plot for signal-to-noise (S/N) ratios of tensile strength.
Figure 10. Main effect plot for signal-to-noise (S/N) ratios of tensile strength.
Figure 10. Main effect plot for signal-to-noise (S/N) ratios of tensile strength.
The optimum level setting of welding factors is the level showing the maximum value of S/N
Figure 10. Main effect plot for signal-to-noise (S/N) ratios of tensile strength.
ratio.The optimum
Figure level setting
11 provides of welding
an interaction factors
plot for is the level
the ultimate showing
tensile the maximum value of S/N
strength.
The
ratio.optimum level setting
Figure 11 provides of welding
an interaction plotfactors
for the is the level
ultimate showing
tensile strength.the maximum value of S/N
The optimum level setting of welding factors is the level showing the maximum value of S/N
ratio.ratio.
Figure 11 provides an interaction plot for the ultimate tensile strength.
Figure 11 provides an interaction plot for the ultimate tensile strength.

Figure 11. Interaction plot for ultimate tensile strength.

Figure 11. Interaction plot for ultimate tensile strength.

Figure 11. Interaction plot for ultimate tensile strength.

Figure 11. Interaction plot for ultimate tensile strength.
Metals 2018, 8, 326 9 of 13

Increasing the welding time results in decreasing the strength, so the enhancement in welding
current raises the mean effect and S/N ratio for the tensile strengths of the specimens. The mean
effect and S/N ratio for tensile strength improve with the tip volume of the stud and then decrease
considerably. Test results provided in Figures 9–11 are valid under the given conditions. The explicit
formulation of the UTS as a function of welding parameters is given in Equation (4):

UTS (MPa) = 292 + 1.31 WC (amps) − 1315 WT (s) − 3.15 TVS (mm 3 ) (4)

Based on the equation and calculations, the correlation coefficient and mean absolute percentage
error values of the Taguchi approach are 0.5690 and 21.6911, respectively. The significance level
(p-values) of the constant, welding current, welding time, and tip volume of the stud are 0.402, 0.051,
0.437, and 0.049, respectively. The p-value of the regression model is 0.66. Test results confirm that the
error percentage is high while the learning rate is relatively low with the Taguchi method. From the
Taguchi approach, it can be concluded that the optimum level setting of the welding current, welding
time, and tip volume of the stud are 550 amps, 0.10 s, and 1.109 mm3 , correspondingly.

4. Discussion
The arc stud welding method was successfully applied to stainless steel. From the macro visual
inspection of the weld joints, it was found that welding without any macro-defects was obtained by
selecting the appropriate parameters. The primary aim of using argon shielding gas was to protect the
weld pool from the influences of the atmosphere, such as oxidation and nitrogen absorption, and also
to stabilize the arc welding process. However, oxidation could still be seen around the welding metals,
possibly because of the oxygen leakage from the atmosphere into the weld pool. In the ASW method,
various welding parameters, such as welding current, welding time, lift, and plunge were widely
applied. These parameters generally affect the quality of the welded materials and joint structures.
The high welding current and welding time can deform the stud and decrease the joint efficiency of
the welds substantially (Figure 1f). The solidification of δ-ferrite begins from the heat-affected zone
and increases towards the welding zone area. The welding operation in an ASW process takes place in
milliseconds; thus, solidification of the weld pool is very fast, and the width of the HAZ is quite narrow.
The amount and distribution of δ-ferrite, which mainly depends on chemical composition
and cooling rate, significantly affect the properties and performance of austenitic stainless steels.
The volume fraction of δ-ferrite can alter the microstructure of samples by changing the chemical
composition of steel. It is well known that Cr, Si, Ti, and Mo are predominantly δ-ferrite stabilizing
elements. The δ-ferrite has a body-centered cubic (BCC) crystalline structure and slows the grain
growth with changing the strength of the steel. The interphase boundaries act as strong barriers to
the dislocation motions [23,24]. The welding zone also exhibits a primarily ferrite mode during the
solidification process, which could be mainly due to the higher heat input in the welding zone areas.
It is also known that austenitic SS has austenite with its primary phase at room temperature and
that the δ-ferrite in welding zone of austenitic SS forms some dendrites prior to solidification of the
austenite at the peritectic temperature of around 1450 ◦ C [25].
The network architecture, learning rate, and initial weight mainly affect the performance of the
welding process. The hidden layers and neuron numbers are also important factors affecting the
welding process and performance. In order to determine the network architecture and the optimal
parameters, there have not been well-defined methods to date; thus, this study addresses some of
these major concerns. Currently the trial-and-error approach has been the only approach for this aim.
The optimal results were obtained with three neurons in one hidden layer. It can be concluded that the
optimal model is a 3-3-1 architecture. The model learning ability is quite reliable according to the MSE
and MAE results in the training set. The performance, effectiveness, and generalization ability of the
system were evaluated using the test setups to calculate the expected ability in the next.
Metals 2018, 8, 326 10 of 13

MetalsIt2018,
is also clear
8, x FOR thatREVIEW
PEER the correlation coefficient has a very high value and shows good reliability 10 of 13
ratios. The equation could be used for fixing the influences of welding parameters on the strengths of
results)
the weldisjoints.
aboutMAPE 3.03%,(forand the maximum
average percentage error should
error value)not exceedset
of testing 6%.(forIt was determinedresults)
un-normalized that the is
ultimate
about tensile
3.03%, and strength
the maximum of theerror
welds could
should notbe calculated
exceed 6%. It waswithdetermined
96.97% accuracy. The maximum
that the ultimate tensile
strength of
strength value was obtained
the welds could betocalculated
be about 789.74 MPa. From
with 96.97% the tensile
accuracy. test results,
The maximum it wasvalue
strength seen wasthat
some specimens had very good joint performance, while other samples
obtained to be about 789.74 MPa. From the tensile test results, it was seen that some specimens had demonstrated weak or
insufficient
very good joint joint performance.
performance, Thisother
while may samples
be due todemonstrated
local variations of the
weak properties,joint
or insufficient grainperformance.
coarsening,
improper welding parameters, and surface oxidations. The change in
This may be due to local variations of the properties, grain coarsening, improper welding parameters, any welding parameter
drastically
and surfaceaffects the other
oxidations. parameters
The change in any and properties,
welding as well.
parameter To produce
drastically high-quality
affects joints, the
the other parameters
optimum
and welding
properties, parameters
as well. To produce should be properly
high-quality selected
joints, and evaluated
the optimum weldingfor each set should
parameters of test
specimens. Results show that the considered weld parameters are highly
be properly selected and evaluated for each set of test specimens. Results show that the considered significant factors affecting
the ultimate
weld parameters tensilearestrength of arc studfactors
highly significant joints. affecting
A high welding current
the ultimate and strength
tensile welding of timearcincrease the
stud joints.
heat
A and
high in turn current
welding deform and the stud gradually.
welding Also, any
time increase thechange
heat and in the cross-sectional
in turn deform thearea studofgradually.
the stud,
whichany
Also, haschange
an important effect on the weld
in the cross-sectional areaquality, affects
of the stud, the arc
which hascurrent density effect
an important and heat intensity
on the weld
distribution.
quality, affectsThus,
the arcparameters duringand
current density the heat
welding procedure
intensity must beThus,
distribution. selected properlyduring
parameters to obtainthe
maximum strength values [26,27].
welding procedure must be selected properly to obtain maximum strength values [26,27].
Fisher introduced
Fisher introduced the the design
design ofof experiments,
experiments, which
which is is considered
considered aa powerful
powerful technique
technique for for this
this
type of
type of analysis
analysis [28].
[28]. The
The technique
technique is is widely
widely used
used for
for the
the experimental
experimental layout
layout to to determine
determine the the level
level
of changes in the processing parameters on the output performance.
of changes in the processing parameters on the output performance. The UTS could be estimated The UTS could be estimated
with 78.31%
with 78.31% accuracy
accuracy using
using the the Taguchi
Taguchi method.
method. Welding
Welding current
current andand tip
tip volume
volume of of the
the stud
stud have
have
lower p-values. Welding time with 0.437 p-values among the other
lower p-values. Welding time with 0.437 p-values among the other parameters has a high p-value,parameters has a high p-value,
which indicates
which indicates thatthat this
this isis not
not an
an important
important parameter.
parameter. In In previous
previous studies,
studies, promising
promising results
results were
were
achieved totofind
achieved find
the the method
method of optimization
of optimization and modeling,
and control control modeling,
and estimationand of estimation of the
the experimental
experimental and theoretical results [29,30]. A comparison of the neural
and theoretical results [29,30]. A comparison of the neural network and Taguchi approaches are shown network and Taguchi
approaches
in Figure 12.are shown in Figure 12.

Figure 12. Comparison of neural network and Taguchi approaches.

Figure 12. Comparison of neural network and Taguchi approaches.

A comparison of the artificial neural network and Taguchi approaches follows:

A comparison of the artificial neural network and Taguchi approaches follows:
• The
The methods
methods are are extensively
extensively used
used to
to optimize
optimize engineering
engineeringprocesses.
processes.
• The
The Taguchi
Taguchimethod
methodhashas aa significant
significant advantage
advantageinin the
the design
design of
of experiments,
experiments, which
which can
can also
also be
be
applied
applied to
to aavariety
varietyofofquantitative
quantitativetests;
tests;by
byusing
usingthis
thismethod,
method,time
timeand
andcost
costcan
canbebe
saved
savedand
anda
much
a muchhigher
higher number
number of of
assays
assayscan
canbebereduced.
reduced.
 ANOVA in the Taguchi approach can be used for analysis and is an alternative and efficient
approach for fast, low-cost assay optimization. The Taguchi method incorporates one primary
experiment to study the main effects of each factor, modeling some of the important interactions.
 The ANN model is popular in predicting the field that is used to solve the problem by rebuilding
any function with arbitrary precision and has good adaptive and self-learning ability.
Metals 2018, 8, 326 11 of 13

• ANOVA in the Taguchi approach can be used for analysis and is an alternative and efficient
approach for fast, low-cost assay optimization. The Taguchi method incorporates one primary
experiment to study the main effects of each factor, modeling some of the important interactions.
• The ANN model is popular in predicting the field that is used to solve the problem by rebuilding
any function with arbitrary precision and has good adaptive and self-learning ability.
• The average relative uncertainty values of ANN and Taguchi approaches are 3.86% and 56.37,
respectively. The ANN has rapid overlearning, more accuracy (~3%), and precision (±24 MPa);
however, the Taguchi method has more low accuracy (~21%) and precision (±389 MPa) in
predicting the ultimate tensile strength of the welds.
• A high p-value (0.066) of regression in the Taguchi method indicates that the equation used here
has a low accuracy for estimating the ultimate tensile strength of welds.
• It was observed that the average percentage error value decreased and the correlation coefficient
value was significantly improved with the neural network approach compared to the Taguchi
approach. In other words, results of the neural network approach are in better agreement with
the test results, which may be attributed to the high learning rate of the ANN method.

In order to decrease experimental error and increase experimental reproducibility, all experimental
steps were performed under the same conditions, and the materials used (commercial 304 and 316 SS)
have the same properties. Three tensile tests for each sample were carried out, and the average of
the results was reported. The proposed models are valid for the given ranges and conditions for a
stud diameter of 6 mm. The optimal parameters of welding are a key issue to obtain the maximum
tensile strength. The maximization of the quality and joint strength of welding is frequently related
to optimization of the welding process parameters. In this paper, two model-based approaches for
welding strength were presented. The artificial neural network and Taguchi methodologies were used
to develop the appropriate welding current, welding time, and tip volume of the stud models based
on real experimental measurement data. The well-known ANN and Taguchi modeling processes
were selected for this case study. These models estimate the ultimate tensile strength as a function
of welding current, welding time, and tip volume of the stud. The comparative study shows that
optimization and control of the UTS using the ANN model provide better error-based performance
than the Taguchi model.
Overall, the present study provides the following major findings based on the experimental test
and model results:

• Increasing the welding current and time raises the local heat, which can probably cause some
deformations on the stud, which in turn diminishes the ultimate tensile strength values.
• The grain growth in the weld zone through external heat energy can cause a reduction in strength.
• Decreasing the cross-sectional area of the stud with a high welding current and time enhances the
heat intensity distribution and deteriorates the mechanical properties of the welded joints.
• A higher welding current or higher welding time can increase the chance of defect formations in
the weld areas, which can also significantly affect the mechanical properties and quality of the
welded metal.
• A high learning rate and high correlation coefficient indicate the effectiveness of the neural
network model, which may be used for the mechanical predictions of welded materials in
many industries.

5. Conclusions
Austenitic stainless steel materials were successfully welded using the arc stud welding method
and tested for tensile properties.

• Test results showed that a dendritic structure was formed during welding, which mainly contained
a δ-ferrite and austenitic structure.
Metals 2018, 8, 326 12 of 13

Improper welding parameters significantly deteriorate the ultimate tensile strength of the welds.
• Tensile test results were statistically studied using artificial neural network and Taguchi
approaches. Neural network results were in good agreement with the test results, and the
formulation has a high reliability with low error rates. The UTS of the joints using the ANN
and Taguchi methods were estimated with an accuracy of 96.97% and 78.31%, respectively.
More studies may be needed to obtain closer matching in the future. Hence, it was concluded
that the neural network model was fairly successful and has analytical virtue for specifying the
ultimate tensile strength of welds under different welding processing cases.
• Welding parameters such as welding current, time, and tip volume of the stud are the most
significant parameters in the ASW process. Thus, these parameters should be properly adjusted
to maximize the mechanical properties of the welds because any change in any of the parameters
can significantly affect all other parameters as well. For example, if a high level of welding current
or welding time is selected during welding, then this leads to more fusion/melting and forms
necking at the joined region due to grain coarsening effects and other structural changes.

Author Contributions: H.I.K., M.O., and N.F.Y. designed the tests, performed the tests, analyzed the data,
and wrote the paper. E.E. contributed the theoretical section. N.F.Y. directed the research, and R.A. contributed to
the results discussion.
Funding: This research received no external funding.
Acknowledgments: The authors declare that they did not receive any funds for covering the costs to publish in
open access.
Conflicts of Interest: The authors declare no conflict of interest.

References
1. Cabibbo, M.; Forcellese, A.; Simoncini, M.; Pieralisi, M.; Ciccarelli, D. Effect of welding motion and
pre-/post-annealing of friction stir welded AA5754 joints. Mater. Des. 2016, 93, 146–159. [CrossRef]
2. Wahba, M.; Mizutani, M.; Katayama, S. Single pass hybrid laser-arc welding of 25 mm thick square groove
butt joints. Mater. Des. 2016, 97, 1–6. [CrossRef]
3. Trzepiecinski, T.; Malinowski, T.; Pieja, T. Experimental and numerical analysis of industrial warm forming
of stainless steel sheet. J. Manuf. Process. 2017, 30, 532–540. [CrossRef]
4. Zhao, D.; Zhao, K.; Ren, D.; Guo, X. Ultrasonic welding of magnesium–titanium dissimilar metals: A study
on influences of welding parameters on mechanical property by experimentation and artificial neural
network. J. Manuf. Sci. Eng. 2017, 139, 031019. [CrossRef]
5. Huang, L.; Wu, D.; Hua, X.; Liu, S.; Jiang, Z.; Li, F.; Wang, H.; Shi, S. Effect of the welding direction on the
microstructural characterization in fiber laser-GMAW hybrid welding of 5083 aluminum alloy. J. Manuf. Process.
2018, 31, 514–522. [CrossRef]
6. Habibi, M.; Hashemi, R.; Fallah Tafti, M.; Assempour, A. Experimental investigation of mechanical properties,
formability and forming limit diagrams for tailor-welded blanks produced by friction stir welding. J. Manuf. Process.
2018, 31, 310–323. [CrossRef]
7. Yang, J.; Yu, Z.; Li, Y.; Zhang, H.; Zhou, N. Laser welding/brazing of 5182 aluminium alloy to ZEK100
magnesium alloy using a nickel interlayer. Sci. Technol. Weld. Join. 2018, 1–8. [CrossRef]
8. Kumar, V.; Hussain, M.; Raza, M.S.; Das, A.K.; Singh, N.K. Fiber laser welding of thin nickel sheets in air and
water medium. Arabian J. Sci. Eng. 2017, 42, 1765–1773. [CrossRef]
9. Krasnowski, K. Experimental study of FSW t-joints of EN-AW 6082-T6 and their behaviour under static
loads. Arabian J. Sci. Eng. 2014, 39, 9083–9092. [CrossRef]
10. Kumar, S.S.; Murugan, N.; Ramachandran, K.K. Microstructure and mechanical properties of friction stir
welded AISI 316l austenitic stainless steel joints. J. Mater. Process. Technol. 2018, 254, 79–90. [CrossRef]
11. Samardžić, I.; Kladarić, I.; Klarić, Š. The influence of welding parameters on weld characteristics in electric
arc stud welding. Metalurgija 2009, 48, 181–185.
12. Chi, Q.; Zhang, J.; Zhang, Y. Study on the autocontrol of stud plunge depth in stepping arc stud welding.
J. Appl. Sci. 2006, 6, 362–365.
Metals 2018, 8, 326 13 of 13

13. Harada, Y.; Sada, Y.; Kumai, S. Dissimilar joining of AA2024 aluminum studs and AZ80 magnesium plates
by high-speed solid-state welding. J. Mater. Process. Technol. 2014, 214, 477–484. [CrossRef]
14. Feng, Y.; Luo, Z.; Liu, Z.; Li, Y.; Luo, Y.; Huang, Y. Keyhole gas tungsten arc welding of AISI 316l stainless
steel. Mater. Des. 2015, 85, 24–31. [CrossRef]
15. Ye, Z.; Huang, J.; Cheng, Z.; Gao, W.; Zhang, Y.; Chen, S.; Yang, J. Combined effects of mig and tig arcs on weld
appearance and interface properties in al/steel double-sided butt welding-brazing. J. Mater. Process. Technol.
2017, 250, 25–34. [CrossRef]
16. Shackelford, J.F.; Alexander, W. CRC Materials Science and Engineering Handbook, 3rd ed.; Taylor & Francis:
Abingdon, UK, 2001.
17. Kurt, H.I. Influence of hybrid ratio and friction stir processing parameters on ultimate tensile strength of
5083 aluminum matrix hybrid composites. Compos. Part B Eng. 2016, 93, 26–34. [CrossRef]
18. Kurt, H.I.; Oduncuoglu, M. Formulation of the effect of different alloying elements on the tensile strength of
the in situ Al-Mg2 Si composites. Metals 2015, 5, 371–382. [CrossRef]
19. Kurt, H.I.; Oduncuoglu, M.; Asmatulu, R. Wear behavior of aluminum matrix hybrid composites fabricated
through friction stir welding process. J. Iron Steel Res. Int. 2016, 23, 1119–1126. [CrossRef]
20. Rama, R.S.; Padmanabhan, G. Application of Taguchi methods and ANOVA in optimization of process
parameters for metal removal rate in electrochemical machining of AL/5% SIC composites. Int. J. Eng. Res. Appl.
2012, 2, 192–197.
21. Roy, R.K. A Primer on the Taguchi Method; Society of Manufacturing Engineers: Dearborn, MI, USA, 2010.
22. Pandey, A.; Khan, M.; Moeed, K. Optimization of resistance spot welding parameters using Taguchi method.
Int. J. Eng. Sci. Technol. 2013, 5, 234–241.
23. Padilha, A.F.; Rios, P. Decomposition of austenite in austenitic stainless steels. ISIJ Int. 2002, 42, 325–327.
[CrossRef]
24. Janovec, J.; Sustarsic, B.; Medved, J.; Jenko, M. Phases in austenitic stainless steels. Mater. Technol. 2003, 37,
307–312.
25. Lai, J.; Haigh, J. Delta-Ferrite Transformations in a Type 316 Weld Metal; Central Electricity Research Labs.:
Leatherhead, UK, 1978.
26. Radisavljevic, I.; Zivkovic, A.; Radovic, N.; Grabulov, V. Influence of FSW parameters on formation quality
and mechanical properties of AL 2024-T351 butt welded joints. Trans. Nonferrous Met. Soc. China 2013, 23,
3525–3539. [CrossRef]
27. Dorbane, A.; Ayoub, G.; Mansoor, B.; Hamade, R.F.; Kridli, G.; Shabadi, R.; Imad, A. Microstructural
observations and tensile fracture behavior of FSW twin roll cast AZ31 mg sheets. Mater. Sci. Eng. A 2016, 649,
190–200. [CrossRef]
28. Fisher, R.A. The Design of Experiments, 5th ed.; Macmillan Pub Co.: Oxford, UK, 1949.
29. Al-Abdullah, K.I.A.-L.; Abdi, H.; Lim, C.P.; Yassin, W.A. Force and temperature modelling of bone milling
using artificial neural networks. Measurement 2018, 116, 25–37. [CrossRef]
30. Gajate, A.; Haber, R.; del Toro, R.; Vega, P.; Bustillo, A. Tool wear monitoring using neuro-fuzzy techniques:
A comparative study in a turning process. J. Intell. Manuf. 2012, 23, 869–882. [CrossRef]

© 2018 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access
article distributed under the terms and conditions of the Creative Commons Attribution
(CC BY) license (http://creativecommons.org/licenses/by/4.0/).