machines

Article
Adaptive Neuro-Fuzzy Inference System-Based Predictive
Modeling of Mechanical Properties in Additive Manufacturing
Vasileios D. Sagias 1 , Paraskevi Zacharia 2, * , Athanasios Tempeloudis 1 and Constantinos Stergiou 1

1 Department of Mechanical Engineering, University of West Attica, 12241 Egaleo, Greece;

sagias@[Link] (V.D.S.); thanas_temp@[Link] (A.T.); stergiou@[Link] (C.S.)
2 Department of Industrial Design and Production Engineering, University of West Attica, 12241 Egaleo, Greece
* Correspondence: [Link]@[Link]

Abstract: Predicting the mechanical properties of Additive Manufacturing (AM) parts is a complex
task due to the intricate nature of the manufacturing processes. This study presents a novel application
of the Adaptive Neuro-Fuzzy Inference System (ANFIS) to predict the mechanical properties of
PLA specimens produced using Fused Filament Fabrication (FFF). The ANFIS model integrates the
strengths of neural networks and fuzzy logic to establish a mapping between the inputs and the output
mechanical properties, specifically maximum stress, strain, and Young’s modulus. Experimental data
were collected from three-point bending tests conducted on FFF samples fabricated from PLA material
with different manufacturing parameters, such as infill pattern, infill, layer thickness, printing speed,
extruder and bed temperature, printing orientation (along each axis and twist angle), and raster
angle. These data were used to train, check, and validate the ANFIS model. The results reveal that
the proposed predictive model can effectively predict the mechanical properties of FFF-printed PLA
samples, demonstrating its potential for broader applications across various AM technologies and
materials, ultimately enhancing the efficiency and effectiveness of the AM fabrication process.

Keywords: adaptive neuro-fuzzy inference system (ANFIS); additive manufacturing (AM); 3D

printing; mechanical properties’ prediction; three-point bending; FFF technology; PLA

Citation: Sagias, V.D.; Zacharia, P.;

Tempeloudis, A.; Stergiou, C.
Adaptive Neuro-Fuzzy Inference
1. Introduction
System-Based Predictive Modeling of Within the context of the fourth industrial revolution, several science sections merge
Mechanical Properties in Additive with each other in order to lead industry to new horizons. Fuzzy modeling, a tool which
Manufacturing. Machines 2024, 12, 523. can impressively represent nonlinear relations between the parameters of a system [1],
[Link] along with adaptive Artificial Neural Network (ANN) results in the Adaptive Neuro-Fuzzy
machines12080523 Inference System (ANFIS). ANFIS can establish input–output systems based on both “if–
Academic Editor: Gianni Campatelli then” rules and specified input–output data pairs [2]. This combination takes advantage of
both tools in a single framework.
Received: 29 June 2024 Additive Manufacturing is a rapidly expanding technology, applied to a wide range
Revised: 25 July 2024
of industrial sectors, transforming design files to functional products as well as parts and
Accepted: 29 July 2024
assemblies. The main advantages of AM are the freedom of design, sustainability in energy
Published: 31 July 2024
and materials, the ability for complex structures to be manufactured, and the affordability
in fast prototyping. However, AM still faces low productivity and uncertainty of the
parts, regarding their mechanical properties. The main reason is the multifactorial process
Copyright: © 2024 by the authors.
parameters that influence the manufacturing procedure.
Licensee MDPI, Basel, Switzerland. Several studies have been made to propose new methods and materials in AM, offering
This article is an open access article solutions and further development on the AM, as it is one of the four manufacturing pillars.
distributed under the terms and In 1986, Charles Hull presented a new technology in which successive layers of materials
conditions of the Creative Commons are formed on top of each other creating three-dimensional parts. This new process was
Attribution (CC BY) license (https:// named stereolithography (SLA). Since then, new methods are being developed, and novel
[Link]/licenses/by/ materials are being applied, allowing new applications and industry fields to continuously
4.0/). merge with AM.

Machines 2024, 12, 523. [Link] [Link]

Machines 2024, 12, 523 2 of 19

ASTM classifies Additive Manufacturing into seven major categories [3]: Material
Extrusion, Powder Bed Fusion, Sheet Lamination, Binder Jetting, Material Jetting, VAT
Photopolymerization, and Direct Energy Deposition. Among these, Material Extrusion is
the most widely used AM process. In this method, the material is selectively dispensed
through a heated nozzle following a layer-by-layer path to create a physical model.
The large variety of materials, used in AM, can be categorized [4] into four groups:
Metals and Alloys, Polymers and Composites, Ceramics, and finally Concrete, most of
which can be used in Material Extrusion processes.
New Additive Manufacturing (AM) technologies are continually being developed,
and the variety of materials utilized in these processes is expanding rapidly. Moreover, AM,
also known as 3D printing, is experiencing rapidly growth due to its facilitation capabilities,
having a key role in industries, such as aerospace, oil and gas, automotive, energy, medical,
tool and die, and other consumer goods [5]. As Artificial Intelligence (AI) tools can be
applied to control the factors that affect the mechanical properties of the materials [6,7],
this study will explore the convergence of AM and ANFIS. The aim is to develop a tool
that can predict the mechanical properties of specimens, taking into consideration most
of the manufacturing parameters of AM processes, thereby enhancing the efficiency of
AM applications.
Although Additive Manufacturing is gaining popularity, due to its reduced product
cycle time and the lack of need for expensive tools, the commercialization of this technology
is still limited because of several shortcomings. One significant issue is the difficulty in
determining the strength of the parts, which arises from the anisotropic and heterogeneous
microstructure of the fabricated parts. The most critical material characteristics are the
mechanical properties, as they determine the product’s ability to meet the designed require-
ments. These properties, which include stress, strain, and Young’s modulus, depend on
various parameters, such as the applied AM method, material, infill pattern and percentage,
layer thickness, the existence of wall and its thickness, temperature, building orientation,
curing conditions, and many more.
Previous studies [8–20] in the field have usually focused on a limited number of the
most significant parameters, within the strict boundaries of the conducted experiments,
using several experimental, numerical, and statistic methods.
This research is triggered by the need to develop a unified tool for predicting the
mechanical properties of AM parts, adaptable to AM technology and material, while
accounting for the various process parameters that impact the final product. The mechanical
properties to be approached are maximum stress, strain, and Young’s modulus.
With the rapid evolution of AM technologies and the range expansion of used ma-
terials, the application of AM structures is continuously widening. Therefore, Artificial
Intelligence (AI) can be employed to control the factors that affect the mechanical properties
of the materials [4].
This study examines the synergy between Additive Manufacturing (AM) and Artificial
Intelligence (AI) to develop an AI tool aimed at enhancing the understanding and efficient
use of materials in AM. This tool will be used to predict the mechanical properties of the
specimens, considering the majority of setting parameters during the AM process, thereby
benefiting research and practical applications.

2. The Adaptive Neuro-Fuzzy Inference System (ANFIS)

The modeling of processes and system identification using input–output data has
attracted many research efforts. The main components of soft computing, such as fuzzy
logic and neural networks, have shown great ability in solving complex nonlinear system
identification and control problems. The Adaptive Neuro-Fuzzy Inference System (ANFIS)
model [2] is a hybrid predictive model that combines the learning capabilities of Artificial
Neural Networks (ANNs) with the reasoning capabilities of fuzzy logic. ANFIS uses input–
output sets and a series of if–then fuzzy rules to incorporate the human-like reasoning
style of fuzzy inference systems (FISs). The ANFIS model is especially effective in a
Machines 2024, 12, x FOR PEER REVIEW 3 of 19

Machines 2024, 12, 523 3 of 19

uses input–output sets and a series of if–then fuzzy rules to incorporate the human-like
reasoning style of fuzzy inference systems (FISs). The ANFIS model is especially effective
invariety
a variety of engineering
of engineering applications
applications [21–26],
[21–26], whenwhen
data data are inconsistent
are inconsistent or nonlinear,
or nonlinear, where
where conventional methods fail or are too complicated
conventional methods fail or are too complicated to employ. to employ.
AAtypical
typicalANFIS
ANFIS structure consists of
structure consists of five
fivelayers,
layers,wherein
whereineacheachlayer
layerisisconstructed
constructedby
byseveral nodes. The outputs of the previous layer are used as input nodes forthe
several nodes. The outputs of the previous layer are used as input nodes for thecurrent
current
layer.
[Link]
Consideringa afirst-order
first-orderSugeno
Sugenofuzzy
fuzzymodel
modelwith
withtwo
twoinputs
inputsxxandandyyand andone
one
output
outputf,f,aatypical
typicalrule
ruleset
setwith
withtwotwofuzzy
fuzzyif–then
if–thenrules
rulescan
canbebeexpressed
expressedas asfollows:
follows:
•• Rule
Rule1:1:ifif(x(xisisAA1)1 )and
and(y(yisisBB
1), ),
then (f1 = p1x + q1y + r1).
1 then (f1 = p1 x + q1 y + r1 ).
•• Rule
Rule2:2:ifif(x(xisisAA2)2 )and
and(y(yisisBB
2), ),
then (f2 = p2x + q2y + r2).
2 then (f2 = p2 x + q2 y + r2 ).
Where
Wherex,x,yyareare inputs,
inputs,AAi,i ,BBi iare
aremembership
membershipfunctions
functionsand
andppi,i ,qqi,i ,rri iare
areconsequent
consequent
parameters,
parameters,andandi iisisthe
thenode
nodenumber.
[Link] Thecorresponding
correspondingequivalent
equivalentANFIS ANFISarchitecture
architecture
isisshown
shownininFigure
[Link] Theentire
entiresystemsystemarchitecture
architectureconsists
consistsofoffive
fivelayers,
layers,namely,
namely,thethe
fuzzy layer (Layer 1), product layer (Layer 2), normalized layer (Layer
fuzzy layer (Layer 1), product layer (Layer 2), normalized layer (Layer 3), consequence 3), consequence
layer
layer(Layer
(Layer4),
4),and
andtotal
totaloutput
outputlayerlayer(Layer
(Layer5).
5).The
Thenumber
numberofofnodes
nodesininother otherlayers
layers(layer
(layer
2–4)
2–4)relates
relatesto
tothe
thenumber
numberof offuzzy
fuzzyrules rules(R).
(R).

ANFISarchitecture.
[Link]
Figure architecture.

The basic idea behind using neuro-adaptive learning techniques is that it is very simple
The basic idea behind using neuro-adaptive learning techniques is that it is very sim-
and allows implementation of multi-input–single-output first-order Sugeno-type FIS. This
ple and allows implementation of multi-input–single-output first-order Sugeno-type FIS.
technique provides a method for the fuzzy modeling procedure to learn information about
This technique provides a method for the fuzzy modeling procedure to learn information
a dataset, in order to compute the membership function parameters that best allow the
about a dataset, in order to compute the membership function parameters that best allow
associated fuzzy inference system to track the given input/output data. This learning
the associated fuzzy inference system to track the given input/output data. This learning
approach takes place prior to the operation of the control system. The ANFIS methodology
approach takes place prior to the operation of the control system. The ANFIS methodol-
can be decomposed into four steps:
ogy can be decomposed into four steps:
Step 1: A set of input–output data, to be used as training data, is obtained from the
Stepprocess.
sewing 1: A setAnother
of input–output
optional data, to can
dataset be used
be usedas training data,
as test data is obtained
after [Link] the
sewing process. Another optional dataset can be used as test data after
Step 2: The initial Sugeno-type FIS structure, regarding antecedent membership training.
Step 2:number
functions, The initial
of Sugeno-type FIS structure,
rules, and consequence regardingisantecedent
parameters, created. membership func-
tions, Step
number of rules, and consequence parameters, is created.
3: The learning process is carried out using the training data to adjust the
Step 3: The
membership learning process
functions, is the
to create carried out usingrules,
interference the training
and todata to adjust
determine thethe member-
consequent
ship functions,
parameters. to create the interference rules, and to determine the consequent parameters.
Step
Step4:4:The
Themodel
modelis is validated
validated using the testing
using the testing data,
data,which
whichhave havenot
notbeen
beenused
usedduring
dur-
ing
thethe training.
training. TheThe objective
objective of this
of this validation
validation is validate
is to to validateits its generalization
generalization capability.
capability.

[Link]
ExperimentalResults
Resultsand
andValidation
Validation
Through
Througha aliterature
literaturereview
review andandexperiments
experiments[9],[9],
many factors
many that that
factors influence the me-
influence the
chanical properties
mechanical of the
properties of AM specimens
the AM specimens were gathered.
were [Link] the useuse
By the of Taguchi methodol-
of Taguchi method-
ology
ogy and
and sensitivity
sensitivity analysis,
analysis, these
these factors
factors were
were classifiedaccording
classified accordingtototheir
theirimpact
impactononthe
the
mechanicalproperties
mechanical propertiesofofthe
thespecimens.
[Link]
factorsand
andtheir
theirvalues
valueswere
wereselected
selectedas
as
an input to the ANFIS model. Bending, tension, and torsion experiments
an input to the ANFIS model. Bending, tension, and torsion experiments were conducted were conducted
onvarious
on variousmaterials
materialswith
withthe
theuseuseofofmany
manyAM AMtechnologies,
technologies,suchsuchasasSLA,
SLA,FFF,
FFF,SLS,
SLS,etc.
etc.
All experiments were conducted according to ASTM standards such as ASTM D638, D695,
D7791, D790, and D5279 [27–32].
Machines 2024, 12, 523 4 of 19

3.1. Gathering Experimental Data

The challenge was to produce a tool capable of predicting the mechanical properties
(stress, strain, and Young’s modulus) of as many AM technologies and materials as possible.
Thus, a model with twenty-one inputs and three outputs was created. A total of twenty-one
parameters are presented, namely, (1) AM Technology, (2) Testing Method, (3) Material,
(4) Infill Pattern, (5) Infill Percentage, (6) Layer Thickness, (7) Wall Thickness, (8) Speed,
(9) Extruder Temperature, (10) Laser Power Ratio, (11) Bed Temperature, (12) Position on
Printer Bed, (13) Incline against Printer Bed, (14) Twist around Axis of Centre of Gravity,
(15) Raster Angle, (16) Layers for Alternating Raster Angle, (17) Percentage of First Material,
(18) Curing Time, (19) Curing Power, (20) Layer Composition, and (21) Cross-Section. All
selected inputs are presented in Table 1, along with their values and the code given to each
value for use within the model.
All AM processes and materials presented in this study were used in the AM Labora-
tory Mechanical Engineering Department, University of West Attica.

Table 1. All initial parameters/model inputs of ANFIS generic model.

Input/Factor Number of Levels Levels Level Code

FFF/FDM 1
SLA 2
Input 1 */AM Technology 4 discrete values
SLS 3
DED 4
Bending 1
Input 2 */Testing Method 3 discrete values Tensile 2
Torsion 3
ABS + PLA 1
PLA 2
ABS 3
Resin Pro CR 4
Input 3 */Material 8 discrete values
ABS + 5
PETG 6
SUS316L 7
Ti 8
Rectilinear 1
Triangle 2
Honeycomb 3
Input 4 */Infill Pattern 6 discrete values
Spiral 4
Cross 5
Diamond 6
Continuous Lower Level 0%
Input 5 */Infill Percentage As input
(Range values) Higher Level 100%
Continuous Lower Level
Input 6 */Layer Thickness As input
(Range values) Higher Level
Continuous Lower Level
Input 7 */Wall Thickness As input
(Range values) Higher Level
Continuous Lower Level
Input 8/Speed As input
(Range values) Higher Level
Continuous Lower Level
Input 9/Extruder Temperature As input
(Range values) Higher Level
Continuous Lower Level 0%
Input 10/Laser Power Ratio As input
(Range values) Higher Level 100%
Continuous Lower Level 0 ◦ C
Input 11/Bed Temperature As input
(Range values) Higher Level 100 ◦ C
Machines 2024, 12, 523 5 of 19

Table 1. Cont.

Input/Factor Number of Levels Levels Level Code

X 1
X + 30◦ 2
Input 12 */Position on X + 45◦ 3
6
Printer Platform X + 60◦ 4
X + 90◦ 5
Y 6
On table 1
On table +30◦ 2
Input 13 */Inclination against On table +45◦ 3
6
Printer Platform On table +60◦ 4
On table +90◦ 5
Vertical 6
Input 14 */Twist Angle around On table 1
2
Center of Gravity axis On table +90◦ 2
0◦ 1
90◦ 2
0◦ /90◦ 3
Input 15 */Raster Angle 7 90◦ /0◦ 4
30 /0◦ /−30◦
◦ 5
45◦ /−45◦ 6
0◦ /120◦ /240◦ 7
Per 1 layer 1
Per block—2 layers 2
Per block—3 layers 3
Input 16/Layers for Altering
7 Per block—4 layers 4
Raster Angle (Block)
Per block—5 layers 5
Per block—6 layers 6
Per block—7 layers 7
Input 17/Percentage of Continuous Lower Level 0%
As input
First Material (Range values) Higher Level 100%
Continuous Lower Level
Input 18/Curing Time As input
(Range values) Higher Level
0 0
UT1 1
Input 19/Curing Power 4 discrete values
UT2 2
UT3 3
Sandwich 1
Input 20/Layer Composition 2
Wave 2
Rectangle 1
Input 21/Cross-Section 3 discrete values Dogbone 2
Circle 3
* Mandatory input.

3.2. The ANFIS Generic Model

Such predictive models require a high quantity of input data to produce accurate
outputs. During the development of the methodology and tool creation, there was a
sufficient amount of data on the FFF technology, bending test method, and PLA material.
Thus, all predictions were based on such data, which are presented in Table 2. Some of the
specimens used for the bending test are visually presented in Figure 2. Figure 3 illustrates
the bending test (a) conducted according to ASTM D790 [29] and the specimen after the
test (b).
Machines 2024, 12, 523 6 of 19

Table 2. Three-point bending experimental data—printing parameters.

Layer Bed
Infill Speed Temperature Position Twist Inclination
S/N Infill (%) Thickness Temperature
Pattern (mm/s) (◦ C) on Bed Angle (◦ ) (◦ )
(mm) (◦ C)
1 2 50 0.07 50 200 60 1 1 5
2 2 75 0.07 50 200 60 3 1 5
3 3 100 0.18 50 200 60 5 1 7
4 2 75 0.18 50 200 60 5 1 5
5 2 100 0.18 50 200 60 1 1 5
6 3 50 0.18 50 200 60 3 1 7
7 2 100 0.3 50 200 60 3 1 5
8 2 50 0.3 50 200 60 5 1 5
9 3 75 0.3 50 200 60 1 1 7
10 1 60 0.18 25 215 55 1 1 6
11 3 60 0.18 38 215 55 5 1 7
12 2 60 0.18 50 215 55 1 5 5
13 3 60 0,18 25 230 55 1 5 7
14 2 60 0.18 38 230 55 1 1 5
15 1 60 0.18 50 230 55 5 1 6
16 2 60 0.18 25 245 55 5 1 5
17 1 60 0.18 38 245 55 1 5 6
18 3 60 0.18 50 245 55 1 1 7
19 1 15 0.18 25 215 55 1 1 6
20 3 15 0.18 38 215 55 5 1 7
21 2 15 0.18 50 215 55 1 5 5
22 3 15 0.18 25 230 55 1 5 7
23 2 15 0.18 38 230 55 1 1 5
24 1 15 0.18 50 230 55 5 1 6
25 2 15 0.18 25 245 55 5 1 5
26 1 15 0.18 37.5 245 55 1 5 6
27 3 15 0.18 50 245 55 1 1 7
28 1 15 0.18 25 180 25 1 1 6
29 3 15 0.18 38 180 25 5 1 7
30 2 15 0.18 50 180 25 1 5 5
31 3 15 0.18 25 195 25 1 5 7
32 2 15 0.18 37.5 195 25 1 1 5
33 1 15 0.18 50 195 25 5 1 6
34 2 15 0.18 25 210 25 5 1 5
35 1 15 0.18 38 210 25 1 5 6
36 3 15 0.18 50 210 25 1 1 7
37 1 60 0.18 25 180 60 1 1 6
38 3 60 0.18 37.5 180 60 5 1 7
39 2 60 0.18 50 180 60 1 5 5
40 3 60 0.18 25 195 60 1 5 7
41 2 60 0.18 37.5 195 60 1 1 5
42 1 60 0.18 50 195 60 5 1 6
43 2 60 0.18 25 210 60 5 1 5
44 1 60 0.18 37.5 210 60 1 5 6
45 3 60 0.18 50 210 60 1 1 7

Each experiment was repeated five times, according to the ASTM standard. In Table 3,
the three-point bending results are presented as average values along with their standard
deviations. Stress and strain (Figure 4) produced by the experimental data and the Young’s
modulus were calculated based on Equation (1):

P L3
w0 = (1)
48 E I
where w0 is the deflection (mm), P is the concentrated load (N) applied on the center of
the beam, L is the distance between the two supports of the beam (mm), I is the second
moment of area (mm4 ), and E is the Young’s modulus. The calculation of the I is based on
Equation (2).
a3 b
I= (2)
12
 Machines 2024, 12, x FOR PEER REVIEW 7 of 19
Machines 2024, 12, x FOR PEER REVIEW 7 of 19
Machines 2024, 12, 523 7 of 19
40 3 60 0.18 25 195 60 1 5 7
4041 32 6060 0.18
0.18 25
37.5 195
195 6060 11 51 75
4142 21 6060 0.18
where a is37.5
0.18 50 beam’s195
the depth
195 (mm), and6060b the beam’s
15 width (mm).
11 All bending
56 specimens
4243 12 6060 0.18
0.18 50 195
were square25sections (210
□8 mm). Thus,60 60 5
by knowing the 1
5 beam dimensions,
1 6experimentally
5
4344 21 6060 0.18
0.18 25 210
37.5central deflection
measuring the 210 60
and the 5
60 applied force, 1
1 it is possible 56 the Young’s
5 to calculate
4445 13 6060 0.18
0.18
modulus E.37.5
50 210
210 6060 11 51 67
45 3 60 0.18 50 210 60 1 1 7

Figure 2. One group of specimens used for bending.

Figure 2. One group of specimens used for bending.
Figure 2. One group of specimens used for bending.

(a) (b)
(a) (b)
Figure 3. Bending test on PLA material manufactured by FFF: (a) bending test and (b) bending spec-
Figure 3. 3.
Bending
imen after
Figure test. test on
Bending PLA
test onmaterial manufactured
PLA material by FFF: (a)by
manufactured bending
FFF: test and (b) bending
(a) bending spec-
test and (b) bending
imen after test.
specimen after test.
Each experiment was repeated five times, according to the ASTM standard. In Table
Each
3, the experiment
three-point was repeated
bending results five
are times, according
presented to the
as average ASTM
values standard.
along In Table
with their stand-
Table 3. Three-point bending experimental data—results.
3,ard
thedeviations.
three-pointStress
bendingandresults
strainare presented
(Figure as average
4) produced by values along with data
the experimental their and
stand-
the
ard deviations.
Young’s Stress
modulus and
were strain
calculated
Stress (Figure
based 4)
on
Stress produced
Equation by
(1): the
Strain experimental data
Strain and the
Young’s
Young’sS/N modulus were calculated based
Average on Equation (1):
Standard Average Standard Modulus
(MPa) Deviation 𝑃𝐿 (%) Deviation (GPa)
𝑤 𝑃48𝐿 𝐸 𝐼 (1)
1 14.00 𝑤
1.10 48 𝐸 𝐼 5.80 0.62 (1) 6.03
2 12.00 0.67 7.00 0.52 4.29
3 13.00 0.66 5.00 0.71 6.50
4 13.00 0.60 8.50 0.72 3.82
5 8.50 0.41 5.00 0.45 4.25
6 18.00 0.62 6.00 0.77 7.50
7 8.50 0.34 5.00 0.24 4.25
8 8.00 0.78 2.50 0.49 8.00
9 6.00 0.73 4.50 0.58 3.33
Machines 2024, 12, 523 8 of 19

Table 3. Cont.

Stress Stress Strain Strain Young’s

S/N Average Standard Average Standard Modulus
(MPa) Deviation (%) Deviation (GPa)
10 3.20 0.45 2.50 0.42 3.20
11 4.00 0.41 3.40 0.64 3.02
12 1.00 0.35 0.82 0.68 3.20
13 2.00 0.35 1.50 0.49 3.59
14 3.00 0.42 2.45 0.74 3.38
15 4.00 0.42 3.00 0.66 3.76
16 2.00 0.57 1.50 0.62 3.85
17 1.50 0.24 1.00 0.42 4.43
18 4.00 0.44 3.45 0.32 3.51
19 3.75 0.70 2.50 0.64 4.64
20 4.00 0.55 2.50 0.47 5.06
21 2.50 0.47 1.60 0.56 5.05
22 2.00 0.23 1.20 0.38 5.51
23 4.00 0.40 2.60 0.44 5.20
24 3.00 0.51 1.95 0.59 5.31
25 4.00 0.48 2.50 0.57 5.64
26 1.50 0.33 1.05 0.47 5.14
27 4.00 0.53 2.55 0.54 5.77
28 4.08 0.75 4.78 0.49 2.14
29 5.09 0.62 4.51 0.77 2.82
30 4.03 0.80 1.86 0.83 5.41
Machines 2024, 12, x FOR PEER REVIEW 8 of 19
31 4.27 0.52 1.85 0.42 5.77
32 4.53 0.79 4.44 0.55 2.55
33 4.45 0.67 4.33 0.65 2.57
34 3.96 1.04 4.28 0.98 2.32
where w0 is the deflection (mm), P is the concentrated load (N) applied on the center of
35 3.13 0.75 1.90 0.53
the beam, L is the distance between the two supports of the beam (mm), I is the second 4.12
36 5.29 0.54 4.70 0.62 2.81
moment of area (mm ), and E is the Young’s modulus. The calculation of the I is based on
4
37 2.73 0.83 5.18 0.92 0.74
Equation (2).
38 2.64 0.76 3.75 0.81 0.99
39 2.66 0.48 𝑎 𝑏 2.77 0.39 1.35
40 1.69 0.52𝐼 2.80 0.64 (2)
0.85
41 3.03 0.62 12 4.63 0.52 0.92
42 2.98 0.62 4.80 0.58
where a is the beam’s depth (mm), and b the beam’s width (mm). All bending specimens 0.87
43 3.36 0.83 3.82 0.78
were square sections (□8 mm). Thus, by knowing the beam dimensions, experimentally 1.24
44 1.98 0.40 2.53 0.37 1.10
measuring the central deflection and the applied force, it is possible to calculate the
45 3.01 0.70 4.90 0.69 0.86
Young’s modulus E.

Stress–strain
[Link]–strain
Figure curve
curve of experiment
of experiment 37 (indicative).
37 (indicative).

Table 3. Three-point bending experimental data—results.

Strain
Stress Average Stress Standard Strain Standard Young’s Modulus
S/N Average
(MPa) Deviation Deviation (GPa)
(%)
 Machines 2024, 12, 523 9 of 19

Considering that ANFIS models have a single output, three separate models were
developed, each corresponding to one of the outputs.
Machines 2024, 12, x FOR PEER REVIEW The fuzzy inference system (FIS) is generated following the Subtractive Clustering 10 of 19
method [33], as suggested for systems with more than six input parameters. The training
process for the ANFIS model involved preparing the experimental data by randomly
splitting the data into training and validation sets. Figure 5 shows the scattering of the
data (Figure
output values.8)Specifically,
showed low theperformance. Theis RMSE
training dataset of as
depicted thecircles,
modelandequals to 9.17, 20%
the checking
within the range of the outputs, caused probably by the high number of the
dataset is depicted as pluses. For the generation of the initial model for ANFIS training, examined
factors compared
Subtractive to is
Clustering the low number
applied. of the
Subtractive entries. method
Clustering Regarding thethe
groups RMSE forclusters
data in strain and
based on modulus,
Young’s the given range of influence.
the values The system
for the index locates
error were the center of each
correspondingly highcluster
(51% and 41%
defines
within its
theeffect
range according to that
of the data [Link], respectively).
for each

[Link]
Figure Datafor
for2121input
input variables.
variables.

The model structure, combining fuzzy logic and neural networks, was trained using
a hybrid learning algorithm that adjusts membership function parameters through least-
squares and backpropagation gradient descent methods. Training continued for a specified
number of epochs until the error converged to a relatively low value. The training error
is calculated as the difference between the predicted output of the ANFIS model and the
actual experimental value for each data point in the training set. The error calculation was
performed using the Root Mean Square Error (RMSE) for both training and validation sets,
providing a measure of the model’s performance and generalization capability. Figure 6
illustrates this process, showing the reduction in RMSE over successive epochs, indicating
the model’s successful training and validation. Figure 6 shows the checking error as dots on
top and the training error as asterisks on the bottom. The FIS test against the training data
(Figure 7) revealed a well-trained system, but the test against the checking data (Figure 8)
showed low performance. The RMSE of the model equals to 9.17, 20% within the range
of the outputs, caused probably by the high number of the examined factors compared to
the low number of the entries. Regarding the RMSE for strain and Young’s modulus, the
Machines 2024, 12, 523 10 of 19

values for the index error were correspondingly high (51% and 41% within the range of the
data [Link]
Figure Dataone, respectively).
for 21 input variables.

Machines 2024, 12, x FOR PEER REVIEW 11 of 19

[Link]
Figure Trainingprocess
processofof
thethe ANFIS.
ANFIS.

[Link]
Figure Testingerror
erroragainst
against training
training data
data (maximum
(maximum stress).
stress).
Machines 2024, 12, 523 11 of 19
Figure 7. Testing error against training data (maximum stress).

[Link]
Figure Erroragainst
against checking
checking data
data (maximum
(maximum stress).
stress).

3.3.
[Link]
TheANFIS
ANFISBending
BendingModel
Model
Based on the analysis of the generic ANFIS model, a reduced focus on bending and
Based on the analysis of the generic ANFIS model, a reduced focus on bending and
PLA material was produced. This decision was motivated by the relatively higher number
PLA material was produced. This decision was motivated by the relatively higher number
of experimental available data of these two inputs (PLA and bending).
of experimental available data of these two inputs (PLA and bending).
The proposed bending model was based on the experimental data of FFF technology,
bending test method, and PLA material. Thus, nine inputs were used, i.e., (1) Infill Pattern,
(2) Infill Percentage, (3) Layer Thickness, (4) Speed, (5) Extruder Temperature, (6) Bed
Temperature, (7) Position on Printer Bed, (8) Incline against Printer Bed, and (9) Raster
Angle, as presented in Table 4.

Table 4. Datasheet of the ANFIS bending model.

Layer Bed
Speed Temperature Position on Twist angle Inclination
Infill Pattern Infill (%) Thickness Temperature
(mm/s) (◦ C) Bed (◦ ) (◦ )
(mm) (◦ C)
2 50 0.1 50 200 60 1 1 5
2 75 0.1 50 200 60 3 1 5
3 100 0.1 50 200 60 5 1 7
2 75 0.2 50 200 60 5 1 5
2 100 0.2 50 200 60 1 1 5
3 50 0.2 50 200 60 3 1 7
2 100 0.3 50 200 60 3 1 5
2 50 0.3 50 200 60 5 1 5
3 75 0.3 50 200 60 1 1 7

A further examination of the data revealed three areas where the responses vary from
low to quite accurate. Taking this into account, a higher level of investigation on the settings
of the FIS is conducted. Figure 9 illustrates the five processing layers and the connections
between them within the structure of the ANFIS model. The dataset is divided into training
(circles) and checking datasets (pluses), as depicted in Figure 10. Figure 11 shows that the
 A further examination of the data revealed three areas where the responses vary from
low to quite accurate. Taking this into account, a higher level of investigation on the set-
tings of the FIS is conducted. Figure 9 illustrates the five processing layers and the con-
Machines 2024, 12, 523 nections between them within the structure of the ANFIS model. The dataset 12 is ofdivided
19
into training (circles) and checking datasets (pluses), as depicted in Figure 10. Figure 11
shows that the system achieves the best convergence since the first epoch due to limited
system
inputs,achieves
with thethe best convergence
checking since as
error depicted thedots
firston
epoch
top due
and to
thelimited inputs,
training errorwith the
as asterisks
checking error depicted as dots on top and the training error as asterisks on the bottom.
on the bottom.

Machines 2024, 12, x FOR PEER REVIEW 13 of 19

[Link]
Figure ANFISmodel
modelstructure.
structure.

Figure10.
Figure [Link]
Datafor
for9 9input
input variables.
variables.
 Machines 2024, 12, 523 13 of 19
Figure 10. Data for 9 input variables.

Figure11.
Figure [Link]
Trainingprocess
processof of
thethe ANFIS.
ANFIS.

For
Foraabetter
betterunderstanding
understanding of of
Sugeno-type
Sugeno-type fuzzy rules,
fuzzy a pictorial
rules, viewview
a pictorial of fuzzy rulesrules
of fuzzy
isispresented in Figure 12. Figure 13 illustrates the surface plots that represent the mapping
presented in Figure 12. Figure 13 illustrates the surface plots that represent the mapping
from
fromthetheinputs
inputstotothe
theoutputs. Each
outputs. Each surface
surfaceplot indicates
plot the the
indicates correlation between
correlation two two
between
inputs
inputsand
and the
the output
output (maximum
(maximumstress)
stress)expressed
expressedby bydifferent
differentcolors.
colors. Warmer
Warmer colors
colors like
like yellow indicate higher activation levels, while cooler colors like blue indicate lower
yellow indicate higher activation levels, while cooler colors like blue indicate lower acti-
activation levels. Finally, Figure 14 represents the experimental and predicted values for
vation levels. Finally, Figure 14 represents the experimental and predicted values 14
Machines 2024, 12, x FOR PEER REVIEW forofthe
19
the maximum stress against the checking data. The maximum stress is equal to 1.17, which
maximum stress against the checking data. The maximum stress is equal to 1.17, which is
is compared to the range of the checking outputs equal to 9.75%.
compared to the range of the checking outputs equal to 9.75%.

Figure12.
Figure [Link]
Fuzzyrule
ruleactivation.
activation.
Machines 2024, 12, 523 14 of 19
Figure 12. Fuzzy rule activation.

(a) (b)

(c) (d)
Figure
[Link]
Surfaceplots against
plots maximum
against maximum stress between
stress (a) (a)
between Infill Pattern
Infill andand
Pattern InfillInfill
Percentage, (b)
Percentage,
Infill
Machines 2024, 12, x FOR PEER REVIEW Pattern and Layer Thickness, (c) Infill Percentage and Layer Thickness, and (d)
(b) Infill Pattern and Layer Thickness, (c) Infill Percentage and Layer Thickness, and (d) Infill Percentage
15 Infill
of 19
and Extruder Temperature.
Percentage and Extruder Temperature.

Figure14.
Figure [Link]
Comparisonbetween
between experimental
experimental and
and predicted
predicted values
values against
against checking
checking data data (maxi-
(maximum
mum stress).
stress).

Similarly, two ANFIS models are developed for the strain and the Young’s modulus
based on the same experiments. For both models, the training error equals to zero. Figures
15 and 16 depict the experimental and predicted values for the two cases, respectively.
Regarding the Young’s modulus, it equals to 3049 MPa, which reflects 40% of the data
Machines 2024, 12, 523
Figure 14. Comparison between experimental and predicted values against checking data15 of 19
(maxi-
mum stress).

Similarly,
Similarly, two
two ANFIS models
models are
are developed
developedfor forthe
thestrain
strainand
andthe
the Young’s
Young’s modu-
modulus
lus based
based on same
on the the same experiments.
experiments. Formodels,
For both both models, the training
the training error to
error equals equals
zero. to zero.
Figures
Figures 15 and 16 depict the experimental and predicted values for the two cases,
15 and 16 depict the experimental and predicted values for the two cases, respectively. respec-
tively. Regarding
Regarding the Young’s
the Young’s modulus,
modulus, it equals
it equals to 3049to MPa,
3049 MPa,
whichwhich reflects
reflects 40% of40%theofdata
the
data range. However, the strain equals to 2.21, reduced by 20% within the
range. However, the strain equals to 2.21, reduced by 20% within the data range. data range.

Machines 2024, 12, x FOR PEER REVIEW

Figure 15.
Figure 15. Comparison
Comparison between
between experimental
experimental and
and predicted
predicted values
values against
against checking
checking data 16 of 19
data (Young’s
(Young’s
modulus).
modulus).

Figure16.
Figure 16. Comparison
Comparison between
between experimental
experimentaland
andpredicted
predictedvalues
valuesagainst
againstchecking
checkingdata
data(strain).
(strain).

4.
4. Analysis
Analysis of
of Model
Model Performance
Performance
The
TheANFIS
ANFIS generic
generic model,
model, developed
developed for
for 21
21 inputs,
inputs, showed
showed inadequate
inadequate performance,
performance,
as
as expected, in achieving satisfactory results for the analyzed properties of the specimens.
expected, in achieving satisfactory results for the analyzed properties of the specimens.
Although
Although the
the training
training process
process showed
showed excellent
excellent recognition
recognition of
of the
the correlations
correlations of
of the
the 3D
3D
printing parameters with the output values, the test against the checking data
printing parameters with the output values, the test against the checking data proved that proved
that
the the entries
entries in the
in the dataset
dataset areare few
few totosupport
supportthethemethod.
method. The
The resultant
resultant RMSE
RMSE against
against
checking data is 20%, 41%, and 51% within the range of data for maximum stress, Young’s
modulus, and strain, respectively.
The ANFIS bending model, consisting of nine inputs, exhibited improved RMSE for
maximum stress and strain, equal to 9.75% and 20%, respectively. The fact that the index
for the Young’s modulus was 40% seems to be illusory. It could be evidence that the quan-
Machines 2024, 12, 523 16 of 19

checking data is 20%, 41%, and 51% within the range of data for maximum stress, Young’s
modulus, and strain, respectively.
The ANFIS bending model, consisting of nine inputs, exhibited improved RMSE for
maximum stress and strain, equal to 9.75% and 20%, respectively. The fact that the index for
the Young’s modulus was 40% seems to be illusory. It could be evidence that the quantity
of the available data was not adequate.
The observed difference in the modeling accuracy of stresses compared to Young’s
modulus and strain can be explained by several factors. Firstly, stresses, particularly
maximum stress, are more directly influenced by key input parameters such as infill density,
layer height, and printing speed, which directly affect the load-bearing capacity and stress
distribution within the material. In contrast, Young’s modulus and strain percentage are
more sensitive to microstructural variations and intrinsic material properties, which may
not be as effectively captured by the input parameters used. Additionally, the experimental
measurement of maximum stress is typically more straightforward and less prone to error
compared to Young’s modulus and strain, which can be influenced by small experimental
errors and noise. The variability in the experimental data for Young’s modulus and strain
can be higher due to the complex interactions between material properties and the printing
process, introducing noise into the training data and making it more challenging for
the model to learn accurate patterns. Lastly, the ANFIS model might be more adept at
capturing the relatively simpler relationship between input parameters and maximum
stress, whereas the relationships for Young’s modulus and strain might be more complex,
leading to potential overfitting or underfitting issues. These considerations underscore the
importance of refining input parameters and model structures to improve predictions for
Young’s modulus and strain percentage.
As a concluding remark, the performance increases when using 9 input parameters
compared to 21 input parameters. This is explained by the fact that two distinct models
are developed in this study: one with 21 inputs designed to be more general, and another
with 9 inputs specifically focused on bending. The general model with 21 inputs aims to
capture a wide range of physical effects and is therefore applicable to a broader spectrum
of AM technologies and materials. However, the data available for this model are less
comprehensive, which can limit its performance. In contrast, the bending model with nine
inputs is customized for specific parameters that directly influence the bending behavior of
the samples. The data used for the bending model are more extensive, allowing for a more
precise training process.
While it is true that reducing the number of input parameters may exclude certain
physical effects, the selected parameters in the bending model are those most critical to
capturing the mechanical behavior under bending conditions. This approach strikes a
balance between model simplicity and accuracy, demonstrating that a focused, well-trained
model can outperform a more general one with fewer but more relevant input parameters.

5. Conclusions
The main focus of this research aimed at establishing a novel, flexible method for
predicting the mechanical properties of Additively Manufactured parts through Artificial
Neural Networks and fuzzy logic. Two ANFIS models were developed, i.e., a generic model
that requires additional experimental data from various AM technologies, materials, and
mechanical tests, and a focused model specifically designed for predicting the mechanical
properties of PLA specimens produced using FFF in bending tests.
In line with the objective of optimizing the AM fabrication process, the majority of
the relevant studies typically focus and examine a limited number of parameters within
the strict boundaries of the experiments. The innovative aspect of this research is the
development of a predictive model capable of adapting to any AM technology and material,
while considering the various process parameters that affect the maximum stress and strain
and Young’s modulus of the final product.
Machines 2024, 12, 523 17 of 19

The study highlights the performance improvement achieved by using 9 input pa-
rameters compared to 21 input parameters. This is due to the development of two distinct
models: one with 21 inputs designed to be more general, and another with 9 inputs specifi-
cally focused on bending. The general model with 21 inputs aims to capture a wide range of
physical effects and is therefore applicable to a broader spectrum of AM technologies and
materials. However, the data available for this model are less comprehensive, which can
limit its performance. In contrast, the bending model with nine inputs is customized for spe-
cific parameters that directly influence the bending behavior of the samples. The data used
for the bending model are more extensive, allowing for a more precise training process.
Comparing the experimental results with the numerically modeled mechanical pa-
rameters, we observe a good correlation in certain aspects while identifying areas that
require further refinement. The numerically predicted maximum stress and strain showed
reasonable agreement with the experimental values, with RMSE values within 20% and
9.75%, respectively, suggesting that the model is fairly accurate for these parameters. How-
ever, the prediction for Young’s modulus exhibited a higher RMSE of approximately 40%,
primarily due to one outlier with a significant deviation. This indicates that, while the
model captures the general trend, the accuracy for Young’s modulus can be improved with
additional data and potential refinement of the model.
The results of the developed systems revealed the potential of the method to provide
successful predictions, highlighting the necessity for more input data. This would enable an
accurate initial estimation of the applied AM process (including AM technologies, materials,
structure settings, and process parameters), thereby avoiding the waste of crucial resources.
Despite the potential of this novel approach, it is clear that further experiments are
necessary to enhance the model. Future experiments will enrich the dataset with results
from different AM technologies, materials, and experimental studies. Given ANFIS’s
proven capability to identify nonlinear relationships in the field of mechanical properties, it
can be applied to other areas of research. For example, examining the surface quality of
AM parts using ANFIS, while integrating the knowledge gained from this study, would be
particularly interesting.
In conclusion, the developed ANFIS model shows great promise for predicting the
mechanical properties of FFF-printed PLA specimens with high accuracy. The findings
highlight the importance of optimizing input parameters to enhance model performance,
providing a valuable tool for researchers and practitioners in the field of additive manufac-
turing. Future research will further validate the model with diverse datasets and investigate
ways to include additional relevant parameters without sacrificing model simplicity and
performance along with continuous addition of experimental data on all available AM
technologies, materials, and types of experimental tests in mechanics.

Author Contributions: Conceptualization, V.D.S. and P.Z.; methodology, V.D.S., P.Z. and A.T.;
validation, V.D.S., P.Z. and A.T.; formal analysis, A.T., P.Z. and V.D.S.; investigation, A.T., V.D.S. and
P.Z.; resources, P.Z, V.D.S. and A.T.; data curation, V.D.S. and A.T.; writing—original draft preparation,
A.T., V.D.S. and P.Z.; writing—review and editing, V.D.S., P.Z., A.T. and C.S.; visualization, A.T.;
supervision, C.S. All authors have read and agreed to the published version of the manuscript.
Funding: This research received no external funding.
Data Availability Statement: Data are contained within the article.
Conflicts of Interest: The authors declare no conflicts of interest.

References
1. Takagi, T.; Sugeno, M. Fuzzy identification of systems and its applications to modeling and control. IEEE Trans. Syst. Man Cybern.
1985, SMC-15, 116–132. [CrossRef]
2. Jang, J.-S. ANFIS: Adaptive-network-based fuzzy inference system. IEEE Trans. Syst. Man Cybern. 1993, 23, 665–685. [CrossRef]
3. ASTM F2792-12; Standard Terminology for Additive Manufacturing Technologies. ASTM International: West Conshohocken, PA,
USA, 2012; Volume 1, p. 1.
Machines 2024, 12, 523 18 of 19

4. Ngo, T.D.; Kashani, A.; Imbalzano, G.; Nguyen, K.T.; Hui, D. Additive manufacturing (3D printing): A review of materials,
methods, applications and challenges. Compos. Part B Eng. 2018, 143, 172–196. [CrossRef]
5. Callı, M.; Albak, E.I.; Ozturk, F. Prediction and Optimization of the Design and Process Parameters of a Hybrid DED Product
Using Artificial Intelligence. Appl. Sci. 2022, 12, 5027. [CrossRef]
6. Ali, M.H.; Batai, S.; Sarbassov, D. 3D printing: A critical review of current development and future prospects. Rapid Prototyp. J.
2019, 25, 1108–1126. [CrossRef]
7. Divjak, A.; Modrić, D.; Kovačić, I.; Cviljušac, V. Anisotropic Mechanical Properties of Materials in Stereolithographic Additive
Manufacturing. Tech. Gaz. 2020, 27, 1748–1753.
8. Khorasani, A.; Gibson, I.; Awan, U.S.; Ghaderi, A. The effect of SLM process parameters on density, hardness, tensile strength and
surface quality of Ti-6Al-4V. Addit. Manuf. 2019, 25, 176–186. [CrossRef]
9. Ramesh, M.; Panneerselvam, K. Mechanical investigation and optimization of parameter selection for Nylon material processed
by FDM. Mater. Today Proc. 2021, 46, 9303–9307. [CrossRef]
10. Abouelmajd, M.; Bahlaoui, A.; Arroub, I.; Zemzami, M.; Hmina, N.; Lagache, M.; Belhouideg, S. Experimental analysis and
optimization of mechanical properties of FDM-processed polylactic acid using Taguchi design of experiment. Int. J. Simul.
Multidiscip. Des. Optim. 2021, 12, 30. [CrossRef]
11. Sagias, V.D.; Giannakopoulos, K.I.; Stergiou, C. Mechanical properties of 3D printed polymer specimens. Procedia Struct. Integr.
2018, 10, 85–90. [CrossRef]
12. Polyzos, E.; Katalagarianakis, A.; Polyzos, D.; Van Hemelrijck, D.; Pyl, L. A multi-scale analytical methodology for the prediction
of mechanical properties of 3D-printed materials with continuous fibres. Addit. Manuf. 2020, 36, 101394. [CrossRef]
13. Kumar Mishra, P.; Senthil, P. Prediction of in-plane stiffness of multi-material 3D printed laminate parts fabricated by FDM
process using CLT and its mechanical behaviour under tensile load. Mater. Today Commun. 2020, 23, 100955. [CrossRef]
14. Yadav, D.; Chhabra, D.; Gupta, R.K.; Phogat, A.; Ahlawat, A. Modeling and analysis of significant process parameters of FDM 3D
printer using ANFIS. Mater. Today Proc. 2020, 21, 1592–1604. [CrossRef]
15. Mehrpouya, M.; Gisario, A.; Rahimzadeh, A.; Nematollahi, M.; Baghbaderani, K.S.; Elahinia, M. A prediction model for finding
the optimal laser parameters in additive manufacturing of NiTi shape memory alloy. Int. J. Adv. Manuf. Technol. 2019, 105,
4691–4699. [CrossRef]
16. Mohamed, O.A.; Xu, W. Comment about lack of sufficient data on “A prediction model for finding the optimal laser parameters in
additive manufacturing of NiTi shape memory alloy” by Mehrpouya et al. [The International Journal of Advanced Manufacturing
Technology 105.11 (2019): 4691–4699.]. Prog. Addit. Manuf. 2021, 7, 435–442.
17. Dhar, A.R.; Gupta, D.; Roy, S.S. Development of a bi- directional multi- input- multioutput predictive model for the fused
deposition modelling process using co-active adaptive neurofuzzy inference system, IOP Conference Series. Mater. Sci. Eng. 2021,
1136, 12007. [CrossRef]
18. Abate, K.M.; Nazir, A.; Jeng, J.-Y. Design, optimization, and selective laser melting of vin tiles cellular structure-based hip implant.
Int. J. Adv. Manuf. Technol. 2021, 112, 2037–2050. [CrossRef]
19. Hu, Z.; Mahadevan, S. Uncertainty quantification in prediction of material properties during additive manufacturing. Scr. Mater.
2019, 135, 135–140. [CrossRef]
20. Dev, S.; Srivastava, R. Experimental investigation and optimization of FDM process parameters for material and mechanical
strength. Mater. Today Proc. 2017, 26, 1995–1999. [CrossRef]
21. Zacharia, P.T. An Adaptive Neuro-fuzzy Inference System for Robot Handling Fabrics with Curved Edges towards Sewing. J.
Intell. Robot Syst. 2010, 58, 193–209. [CrossRef]
22. Azad, A.; Karami, H.; Farzin, S.; Saeedian, A.; Kashi, H.; Sayyahi, F. Prediction of Water Quality Parameters Using ANFIS
Optimized by Intelligence Algorithms (Case Study: Gorganrood River). KSCE J. Civ. Eng. 2018, 22, 2206–2213. [CrossRef]
23. Vakhshouri, B.; Nejadi, S. Prediction of compressive strength of self-compacting concrete by ANFIS models. Neurocomputing 2018,
280, 13–22. [CrossRef]
24. Ly, H.-B.; Pham, B.T.; Dao, D.V.; Le, V.M.; Le, L.M.; Le, T.-T. Improvement of ANFIS Model for Prediction of Compressive Strength
of Manufactured Sand Concrete. Appl. Sci. 2019, 9, 3841. [CrossRef]
25. El-Hasnony, I.M.; Barakat, S.I.; Mostafa, R.R. Optimized ANFIS Model Using Hybrid Metaheuristic Algorithms for Parkinson’s
Disease Prediction in IoT Environment. IEEE Access 2020, 8, 119252–119270. [CrossRef]
26. Saleh, M.; Anwar, S.; Al-Ahmari, A.M.; AlFaify, A.Y. Prediction of Mechanical Properties for Carbon fiber/PLA Composite Lattice
Structures Using Mathematical and ANFIS Models. Polymers 2023, 15, 1720. [CrossRef]
27. ASTM D638-14; Standard Test Method for Tensile Properties of Plastics. ASTM International: West Conshohocken, PA, USA, 2014;
Volume 1, p. 1.
28. ASTM D695-15; Standard Test Method for Compressive Properties of Rigid Plastics. ASTM International: West Conshohocken,
PA, USA, 2015; Volume 1, p. 1.
29. ASTM D790-17; Standard Test Methods for Flexural Properties of Unreinforced and Reinforced Plastics and Electrical Insulating
Materials. ASTM International: West Conshohocken, PA, USA, 2017; Volume 1, p. 1.
30. ASTM D3039; Standard Test Method for Tensile Properties of Polymer Matrix Composite Materials. ASTM International: West
Conshohocken, PA, USA, 2014; Volume 1, p. 1.
Machines 2024, 12, 523 19 of 19

31. ASTM D5279-21; Standard Test Method for Plastics: Dynamic Mechanical Properties: In Torsion. ASTM International: West
Conshohocken, PA, USA, 2021; Volume 1, p. 1.
32. ASTM D7791-17; Standard Test Method for Uniaxial Fatigue Properties of Plastics. ASTM International: West Conshohocken, PA,
USA, 2017; Volume 1, p. 1.
33. Srisaeng, P.; Baxter, G. Predicting Australia’s Domestic Airline Passenger Demand using an Anfis Approach. Transp. Telecommun.
2022, 23, 151–159. [CrossRef]

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual
author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to
people or property resulting from any ideas, methods, instructions or products referred to in the content.