Open Access is an initiative that aims to make scientific research freely available to all. To date our community has made over 100 million downloads. It’s based on principles of collaboration, unobstructed discovery, and, most importantly, scientific progression. As PhD students, we found it difficult to access the research we needed, so we decided to create a new Open Access publisher that levels the playing field for scientists across the world. How? By making research easy to access, and puts the academic needs of the researchers before the business interests of publishers.
We are a community of more than 103,000 authors and editors from 3,291 institutions spanning 160 countries, including Nobel Prize winners and some of the world’s most-cited researchers. Publishing on IntechOpen allows authors to earn citations and find new collaborators, meaning more people see your work not only from your own field of study, but from other related fields too.
To purchase hard copies of this book, please contact the representative in India:
CBS Publishers & Distributors Pvt. Ltd.
www.cbspd.com
|
customercare@cbspd.com
Attempt has been made to investigate the experimental process and surface roughness (SR) optimization of cold working (high carbon and high chromium) hard die steel (D2) during wire electrical discharge machining processes (WEDM). It is very difficult to determine optimal cutting parameters for improving cutting performance has been reported. Wire electrical discharge machining process relies heavily on the operators’ technologies and experience because of their numerous and diverse range as using complicated cuts can made through difficult to machine electrically conductive components, WEDM process was developed to generate precise cutting on complicate, hard and difficult to machine materials. Tan-sigmoid and purlin transfer functional with bias based four layered back propagation artificial neural network (BPANN) approach have been used to investigate the effect of six independent parameters namely gap voltage (Vg), flush rate (Fr), Pulse on time (Ton), pulse off time (Toff), wire feed (Wf) and wire tension (Wt) over CLA value of surface roughness (Ra) along with corresponding material removal rate (MRR). A fractional factorial design of experiment of three level were employed to conduct 80 rows of experiment on (D2) steel with chrome coated copper alloy wire electrode. The predicted response, CLA values of SR and corresponding MRR were observed by the approach of BPANN from experimental (55 rows for training, 15 rows for validation and 10 for testing) data. Software instructed programme has been used individually for training, validation and testing in MATLAB 2010a to find the corresponding prediction output. Two fold cross over technique (TFCT) were used to developed distinguish (S1 and S2) models and also developed more models depending on numbers of neurons used in primary and secondary hidden layers. The model adequacy is very satisfactory as correlation coefficient (R2) is found to be 99.1% and adjusted (Radj.2) statistics is 98.5. It is found those spark time ON/OFF, wire feed rate, wire tension, gap voltage and flush rate and few of their interactions have significant effect on SR.
Department of Mechanical Engineering, ASET, Amity University, India
N.K. Singh
Indian Institute of Technology (ISM), India
B.P. Sharma
Department of Mechanical Engineering, ASET, Amity University, India
S. Sivarao
UTeM, Malaysia
*Address all correspondence to: u.k.vates@gmail.com
1. Introduction
Wire electrical discharge machining is the metal removal process by means of repeated spark created between the wire electrode and work piece. It is considered as unique adaptation of the conventional EDM, which used an electrode to create the sparking within kerfs [11]. However, WEDM utilizes a continuously traveling chromium coated copper wire electrode ranging diameter 0.05–0.35 mm, which is capable to achieve very good sharpness of edge [4]. Very high temperature ranging 8000–10,000°C creates within the kerfs gap during machining, so that material removal may takes place by not only melting but directly vaporizations also. WEDM is used for the high precision machining to all type of electrically conductive metallic alloys, tool and die, graphite, and few ceramic and composite materials of any hardness which cannot be machined easily by conventional machining methods [1, 5].
Manufacturing processes (WEDM) has been chosen depending on the material characteristics and the type of responses required to be evaluating. The present study aimed to optimization of responses i.e. surface roughness with corresponding MRR of D2 steel by conducting 80 rows of experimental data using frictional factorial (26–2) design of experiment of five different set at three levels [3]. Four layered BPANN architecture has been used for modeling, where independent process variables are Vg, Fr Ton, Toff, Wf and Wt to get the précised and optimized values of responses Ra [6, 8, 10]. Best model S2 has been found on the basis of correlation coefficient (R2) between observed and predicted responses (SR) [12]. The response (SR) is expressed as the irregularities of material resulted from various machining operations. It is represented as ‘Ra’ symbol and used to be called center line arithmetic average roughness for the sampling length [2].
The optimum process parameters are much essential to achieve better surface finish with adequate material removal rate (MRR) or shrink of total machining time; lot of research attempts has been reported for modeling and investigation of WEDM process parameters [7], but sum of root mean square error (SRMSE) approach have been used to optimize the process parameters by taking 55 rows of training data [9].
A chrome coated cylindrical pure copper wire electrode having 0.25 mm in diameter and high tensile strength were selected for conducting machining operation on 18 mm diameter of D2 steel rod to cut 5 mm thickness of disk using Electronica Maxicut, WEDM process. It is very clear that D2 is hard die steel and conducting material with high carbon and chromium content (
Table 1
).
C
SI
Cr
Mo
V
HRC
Conductivity
1.50%
0.30%
12.00%
0.80%
0.90%
56
22 (W/mk)
Table 1.
Metallurgical component analysis: D2 steel.
The experiment has carried out on Wire Electrical Discharge Machine, model ELECTRONICA-MAXICUT, SLNO -250, (F:09:0002:01) having the facilities to hold the work piece within the place provided by the help of conductive fixture, so that they can complete the circuit between electrode and work piece. The spark is created depending upon gap voltage applied between the conductive work piece, electrode, and machining performance influence the major independent process parameter which selected for experiment as characteristics of screening test. Commercials grade of deionized water (density = 832 kg/m3) was used as dielectric fluid. 18 mm cylindrical rod of D2 steel was used as the work piece with negative polarity and the power supply has the provision to connect the 0.25 mm chromium coated pure copper tool electrode with positive polarity so that the material removal may takes place by influence of heat generated within kerfs due to applied voltage within it (
Figure 1
).
Figure 1.
D2 steel machining using WEDM process.
The surface roughness Ra of the processed material have been measured precisely by using Surftest SJ-210 tester having center line average value (CLA), where least count of the equipment is 0.001 μm for the travel length of 0.85 mm (
Figure 2
).
Figure 2.
Surftest SJ-210 (Mitutoyo).
2.2 Design of experiment and objective
Five different set of fractional factorial (26–2 = 16) experimental design have been selected at two levels, so that 80 rows of experimental data can be observed at three level of replication on D2 using WEDM. In this study the main aim to minimize the surface roughness of D2 on best possible maximum MRR during WEDM (
Table 2
).
Factors/three level (coding)
1
2
3
Gap voltage (Vg): (volt)
30
60
90
Flush rate (Fr): (L/min)
4
6
8
Pulse on time (Ton): (μS)
1.05
1.15
1.25
Pulse of time (Toff): (μS)
130
160
190
Wire feed rate (Wf):(m/min)
2
5
8
Wire tension (Wt): (g)
300
600
900
Table 2.
Factors for screening test.
2.3 ANN architecture and training
The hit and trail method based on literature have been adapted to find 7 and 10 neurons in primary and secondary hidden layers respectively, which effects on the R-square statistics for best prediction modeling. Tan sigmoid activation (squashing) function used as the (infinite input to finite output range) learning capability by the controllable instructed programme in MATLAB 2010a. Steepest descent problem used for the training algorithm to train the multilayer network, where the values of gradient was smallest because of the small changes in weight and biases. p1, p2, p3,p4, p5 and p6 are the six input layer neurons and Oi is the single neurons in output layer, whereas I11-I17 and I21-I29 (7 neurons present in primary and 10 in secondary hidden layers) are the hidden layers (
Figure 3
).
Two models (S1 and S2) were developed from 80 rows of experimental data performed of D2. Only training result of best performing model (S2) of 55 rows is presented here for achieving the aimed to optimization of influencing process parameters (
Figures 4
and
5
).
Figure 4.
Predictions against observations of Ra for model-D2, S2, 7 N (training dataset).
Figure 5.
Predictions against observations of Ra for model-D2, S2, 7 N (validation dataset).
OPTIMIZATION OF PROCESS PARAMETER Ra: D2, 7 Neurons in hidden layer.
The best model needs to be predicted among Model-S1 and S2, in D2 steel. Effect of individual input parameters will be observed on the Ra (
Tables 3
–
6
).
SN
Gap voltage (Vg)
Flush rate (Fr)
Spark time (TON)
Spark time (TOFF)
Wire feed (Wf)
Wire tension (Wt)
Surface roughness (Ra) Obs.
Surface roughness (Ra) Pred.
Material removal (MRR)
Square of residuals
(V)
(Lit./min)
(μS)
(μS)
(m/min)
(g)
(μm)
(μm)
(mg/min)
(μm)2
1
30
4
1.05
130
2
300
1.6858
1.6863
102
2.5E−07
2
30
4
1.05
160
2
600
1.4452
1.4451
92
1E−08
3
30
4
1.15
130
5
600
1.3884
1.3713
133
0.0002924
4
30
4
1.15
160
5
300
1.4658
1.4428
95
0.000529
5
30
6
1.05
130
5
600
1.3836
1.3788
125
2.304E−05
6
30
6
1.05
160
5
300
1.5278
1.5553
110
0.0007562
7
30
6
1.15
130
2
300
1.676
1.6756
97
1.6E−07
8
30
6
1.15
160
2
600
1.564
1.4909
95
0.0053436
9
60
4
1.05
130
5
300
1.1772
1.1754
104
3.24E−06
10
60
4
1.05
160
5
600
1.2076
1.2083
88
4.9E−07
11
60
4
1.15
130
2
600
1.273
1.2663
136
4.489E−05
12
60
4
1.15
160
2
300
1.3476
1.3455
116
4.41E−06
13
60
6
1.05
130
2
600
1.3322
1.3277
110
2.025E−05
14
60
6
1.05
160
2
300
1.1598
1.1371
115
0.0005153
15
60
6
1.15
130
5
300
1.248
1.1945
118
0.0028623
16
30
8
1.15
160
8
900
1.5124
1.5422
145
0.000888
17
30
8
1.15
190
8
600
1.363
1.3482
108
0.000219
18
30
8
1.25
160
5
600
2.1256
2.128
206
5.76E−06
19
30
8
1.25
190
5
900
1.6794
1.6823
101
8.41E−06
20
90
4
1.15
160
8
600
1.1098
1.1096
88
4E−08
21
90
4
1.15
190
8
900
1.1096
1.0952
63
0.0002074
22
90
4
1.25
160
5
900
1.3572
1.3664
107
8.464E-05
23
90
4
1.25
190
5
600
1.3218
1.3425
88
0.0004285
24
90
8
1.15
160
5
900
1.2286
1.2292
91
3.6E−07
25
90
8
1.15
190
5
600
1.1194
1.1062
64
0.0001742
26
60
6
1.15
160
5
600
1.4038
1.4023
155
2.25E−06
27
60
8
1.05
130
5
900
1.4592
1.459
162
4E−08
28
60
8
1.05
160
5
600
1.3601
1.3441
139
0.000256
29
60
8
1.25
130
2
600
1.5208
1.5302
202
8.836E−05
30
60
8
1.25
160
2
900
1.5435
1.5535
168
0.0001
31
90
6
1.05
130
5
600
1.3127
1.3118
78
8.1E−07
32
90
6
1.05
160
5
900
1.2973
1.3023
72
2.5E−05
33
90
6
1.25
130
2
900
1.1823
1.1867
117
1.936E−05
34
90
6
1.25
160
2
600
1.0832
1.0812
105
4E−06
35
90
8
1.05
130
2
900
1.2396
1.2696
89
0.0009
36
90
8
1.05
160
2
600
1.1838
1.1739
81
9.801E−05
37
90
8
1.25
130
5
600
1.1413
1.1524
92
0.0001232
38
90
8
1.25
160
5
900
1.1125
1.1364
112
0.0005712
39
60
6
1.05
130
2
600
1.4536
1.4546
128
1E−06
40
60
6
1.05
160
2
900
1.3208
1.3474
114
0.0007076
41
90
8
1.05
130
2
900
1.1369
1.1423
96
2.916E−05
42
90
8
1.05
160
2
600
1.0962
1.0905
78
3.249E−05
43
90
8
1.25
130
5
600
1.1551
1.1551
99
0
44
90
8
1.25
160
5
900
1.1723
1.1153
74
0.003249
45
30
4
1.15
160
2
300
1.6813
1.6628
112
0.0003422
46
30
4
1.15
190
2
900
1.5782
1.5577
108
0.0004202
47
30
4
1.25
160
8
900
1.4935
1.5283
163
0.001211
48
30
4
1.25
190
8
300
1.4658
1.4666
155
6.4E−07
49
30
6
1.15
160
8
900
1.6402
1.6368
121
1.156E−05
50
30
6
1.15
190
8
300
1.6128
1.6021
132
0.0001145
51
30
6
1.25
160
2
300
1.6368
1.6354
103
1.96E−06
52
30
6
1.25
190
2
900
1.5609
1.5668
108
3.481E−05
53
60
4
1.15
160
8
300
1.2136
1.1945
123
0.0003648
54
60
4
1.15
190
8
900
1.1871
1.1878
128
4.9E−07
55
60
4
1.25
160
2
900
1.2036
1.2035
148
1E−08
Average
1.3654
113.8
Table 3.
D2, S1, 7N, training data (combined parameters).
SN
Gap voltage (Vg)
Flush rate (Fr)
Spark ON time (TON)
Spark OFF time (TOFF)
Wire feed (Wf)
Wire tension (Wt)
Surface roughness (Ra) obs.
Surface roughness (Ra) predicted.
(Residual)2
Material removal predicted (MRR)
(V)
(Lit./min)
(μS)
(μS)
(m/min)
(g)
(μm)
(μm)
(μm)2
(mg/min)
1
30
4
1.05
130
2
300
1.6858
1.6863
2.5E−07
105
2
30
4
1.05
160
2
600
1.4452
1.4451
1E−08
95
3
30
4
1.15
130
5
600
1.3884
1.3713
0.0002924
119
4
30
4
1.15
160
5
300
1.4658
1.4428
0.000529
102
5
30
6
1.05
130
5
600
1.3836
1.3788
2.304E−05
115
6
30
6
1.05
160
5
300
1.5278
1.5553
0.0007562
116
7
30
6
1.15
130
2
300
1.676
1.6756
1.6E−07
114
8
30
6
1.15
160
2
600
1.564
1.4909
0.0053436
102
9
60
4
1.05
130
5
300
1.1772
1.1754
3.24E−06
108
10
60
4
1.05
160
5
600
1.2076
1.2083
4.9E−07
96
11
60
4
1.15
130
2
600
1.273
1.2663
4.489E−05
131
12
60
4
1.15
160
2
300
1.3476
1.3455
4.41E−06
123
13
60
6
1.05
130
2
600
1.3322
1.3277
2.025E−05
111
14
60
6
1.05
160
2
300
1.1598
1.1371
0.0005153
117
15
60
6
1.15
130
5
300
1.248
1.1945
0.0028623
112
16
30
8
1.15
160
8
900
1.5124
1.5422
0.000888
136
17
30
8
1.15
190
8
600
1.363
1.3482
0.000219
105
18
30
8
1.25
160
5
600
2.1256
2.128
5.76E−06
189
19
30
8
1.25
190
5
900
1.6794
1.6823
8.41E−06
97
20
90
4
1.15
160
8
600
1.1098
1.1096
4E−08
79
21
90
4
1.15
190
8
900
1.1096
1.0952
0.0002074
70
22
90
4
1.25
160
5
900
1.3572
1.3664
8.464E−05
110
23
90
4
1.25
190
5
600
1.3218
1.3425
0.0004285
92
24
90
8
1.15
160
5
900
1.2286
1.2292
3.6E−07
101
25
90
8
1.15
190
5
600
1.1194
1.1062
0.0001742
69
26
60
6
1.15
160
5
600
1.4038
1.4023
2.25E−06
153
27
60
8
1.05
130
5
900
1.4592
1.459
4E−08
158
28
60
8
1.05
160
5
600
1.3601
1.3441
0.000256
143
29
60
8
1.25
130
2
600
1.5208
1.5302
8.836E−05
208
30
60
8
1.25
160
2
900
1.5435
1.5535
0.0001
163
31
90
6
1.05
130
5
600
1.3127
1.3118
8.1E−07
74
32
90
6
1.05
160
5
900
1.2973
1.3023
2.5E−05
93
33
90
6
1.25
130
2
900
1.1823
1.1867
1.936E−05
122
34
90
6
1.25
160
2
600
1.0832
1.0812
4E−06
111
35
90
8
1.05
130
2
900
1.2396
1.2696
0.0009
97
36
90
8
1.05
160
2
600
1.1838
1.1739
9.801E−05
86
37
90
8
1.25
130
5
600
1.1413
1.1524
0.0001232
81
38
90
8
1.25
160
5
900
1.1125
1.1364
0.0005712
106
39
60
6
1.05
130
2
600
1.4536
1.4546
1E−06
135
40
60
6
1.05
160
2
900
1.3208
1.3474
0.0007076
111
41
90
8
1.05
130
2
900
1.1369
1.1423
2.916E−05
96
42
90
8
1.05
160
2
600
1.0962
1.0905
3.249E−05
74
43
90
8
1.25
130
5
600
1.1551
1.1551
0
94
44
90
8
1.25
160
5
900
1.1723
1.1153
0.003249
88
45
30
4
1.15
160
2
300
1.6813
1.6628
0.0003422
117
46
30
4
1.15
190
2
900
1.5782
1.5577
0.0004202
100
47
30
4
1.25
160
8
900
1.4935
1.5283
0.001211
158
48
30
4
1.25
190
8
300
1.4658
1.4666
6.4E−07
163
49
30
6
1.15
160
8
900
1.6402
1.6368
1.156E−05
115
50
30
6
1.15
190
8
300
1.6128
1.6021
0.0001145
141
51
30
6
1.25
160
2
300
1.6368
1.6354
1.96E−06
112
52
30
6
1.25
190
2
900
1.5609
1.5668
3.481E−05
109
53
60
4
1.15
160
8
300
1.2136
1.1945
0.0003648
123
54
60
4
1.15
190
8
900
1.1871
1.1878
4.9E−07
125
55
60
4
1.25
160
2
900
1.2036
1.2035
1E−08
144
Average
1.3654
0.002642
114.8
Table 4.
Training data for model: S2, Ra, N7, D2 steel.
SN
Gap voltage (Vg)
Flush rate (Fr)
Spark time (TON)
Spark time (TOFF)
Wire feed (Wf)
Wire tension (Wt)
Surface roughness (Ra)
Material removal (MRR)
Square of residuals (Ra)
(V)
(Lit./min)
(μS)
(μS)
(m/min)
(g)
(μm)
(mg/min)
(μm)2
Vg
2
30
4
1.05
160
2
600
1.4452
92
1E−08
7
30
6
1.15
130
2
300
1.676
97
1.6E−07
27
60
8
1.05
130
5
900
1.4592
162
4E−08
54
60
4
1.15
190
8
900
1.1871
128
4.9E−07
20
90
4
1.15
160
8
600
1.1098
88
4E−08
43
90
8
1.25
130
5
600
1.1551
99
0
Fr
1
30
4
1.05
130
2
300
1.6858
102
2.5E−07
55
60
4
1.25
160
2
900
1.2036
148
1E−08
7
30
6
1.15
130
2
300
1.676
97
1.6E−07
31
90
6
1.05
130
5
600
1.3127
78
8.1E−07
27
60
8
1.05
130
5
900
1.4592
162
4E−08
43
90
8
1.25
130
5
600
1.1551
99
0
Ton
41
90
8
1.05
130
2
900
1.1369
96
2.916E−05
42
90
8
1.05
160
2
600
1.0962
78
3.249E−05
54
60
4
1.15
190
8
900
1.1871
128
4.9E−07
20
90
4
1.15
160
8
600
1.1098
88
4E−08
55
60
4
1.25
160
2
900
1.2036
148
1E−08
43
90
8
1.25
130
5
600
1.1551
99
0
Toff
7
30
6
1.15
130
2
300
1.676
97
1.6E−07
27
60
8
1.05
130
5
900
1.4592
162
4E−08
55
60
4
1.25
160
2
900
1.2036
148
1E−08
36
90
8
1.05
160
2
600
1.1838
81
9.801E−05
21
90
4
1.15
190
8
900
1.1096
63
0.0002074
54
60
4
1.15
190
8
900
1.1871
128
4.9E−07
Wf
34
90
6
1.25
160
2
600
1.0832
105
4E−06
2
30
4
1.05
160
2
600
1.4452
92
1E−08
43
90
8
1.25
130
5
600
1.1551
99
0
31
90
6
1.05
130
5
600
1.3127
78
8.1E−07
48
30
4
1.25
190
8
300
1.4658
155
6.4E−07
16
30
8
1.15
160
8
900
1.5124
145
0.000888
Wt
7
30
6
1.15
130
2
300
1.6760
97
1.6E−07
1
30
4
1.05
130
2
300
1.6858
102
2.5E−07
2
30
4
1.05
160
2
600
1.4452
92
1E−08
31
90
6
1.05
130
5
600
1.3127
78
8.1E−07
54
60
4
1.15
190
8
900
1.1871
128
4.9E−07
21
90
4
1.15
190
8
900
1.1096
63
0.0002074
Table 5.
D2, S2, 7N, training data (individual parameters corresponding to least square of residuals).
Correlation coefficient (R2): Training data of D2 steel (best performing model S2) using 7 and 10 neurons in primary and secondary hidden layers.
Material
Model
R2 value
Equation of lines (correlation between obs. and pred. values of Ra)
Average predicted Ra (μm)
Root mean square error (μm)
Percentage RMSE (%)
Average % RMSE RMSE
D2
S1 Training
0.983
y = 1.005x - 0.010
1.3864
0.003401
0.2453
0.8129 0.7353
S1 Validation
0.967
y = 1.067x - 0.090
1.3008
0.01077
0.8279
S1, Testing Testing
0.963
y = 0.879x + 0.154
1.4016
0.01914
1.3655
S2 set, Training Training
0.991
y = 1.004x - 0.008
1.3654
0.002642
0.1934
0.3865
S2 validation
0.988
y = 0.984x + 0.028
1.3888
0.007015
0.5051
S2, testing testing
0.979
y = 1.006x - 0.006
1.4232
0.006565
0.4612
Table 6.
Summary of R2 values of training validation and testing data: 7 N in 1st and 10 N in 2nd L, Ra.
It is evident from
Table 3
, that each independent influencing input parameter has corresponding values of their square of residuals at each three levels. Two values at each level (2 × 3 = 6 rows) has been taken for each inputs, where lowest possible square of residuals are available, to draw the
Figure 6(a–f)
.
Figure 6.
(a–f) 3D scattered plot between Ra vs. MRR vs. individual independent parameter.
Figure 6
(a–f) shows the relations between individual influencing parameters (Vg, Fr, Ton, Toff, Wf and Wt) to their optimized response, surface roughness (Ra) with corresponding values of MRR.
Table 5
also indicates that unique values of each influencing parameters (corresponding to its serial numbers of
Table 5
) gives optimum responses, which has been highlighted.
Again experiment has been conducted on D2 steel using WEDM by setting the individual optimum parametric combinations (Vg, Fr, Ton, Toff, Wf and Wt) as 90 (V), 8 (Lit./min), 1.05 (μS), 190 (μS), 2 (m/min) and 900 (g) respectively and found the values of Ra = 0.9638 (μm) at MRR = 105 (mg/min) (
Table 7
).
SN
Gap voltage (Vg)
Flush rate (Fr)
Spark time (TON)
Spark time (TOFF)
Wire feed (Wf)
Wire tension (Wt)
Surface roughness (Ra) obs.
Surface roughness (Ra) predicted
(Zero residual)2
Material removal predicted (MRR)
(V)
(Lit./min)
(μS)
(μS)
(m/min)
(g)
(μm)
(μm)
(μm)2
(mg/min)
20
90
4
1.15
160
8
600
1.1098
1.1096
4.00E−08
79
43
90
8
1.25
130
5
600
1.1551
1.1551
0
94
42
90
8
1.05
160
2
600
1.0962
1.0905
3.25E−05
74
54
60
4
1.15
190
8
900
1.1871
1.1878
4.90E−07
125
34
90
6
1.25
160
2
600
1.0832
1.0812
4.00E−06
111
54
60
4
1.15
190
8
900
1.1871
1.1878
4.90E−07
125
Table 7.
Best parametric combination with their possible responses.
It has been concluded that the best fitted model (S2) for material removal rate and surface roughness of D2 steel has been achieved by artificial neural network using WEDM. From best modeled training data, optimum parametric combinations (Vg, Fr, Ton, Toff, Wf and Wt) observed as 90 V, 8 Lit./min, 1.05 μS, 190 μS, 2 m/min and 900 g respectively and found the values of Ra = 0.9638 μm at MRR = 105 mg/min, whereas the average Ra = 1.3654 μm at MRR = 114.8 mg/min. It has been concluded that ANN modeling technique is best fitted for surface roughness prediction and able to successfully minimize (SR) is 29.41% with 8.53% decreases the MRR from its average values on D2 steel using BPANN under WEDM. Such combinations may be applied for industrial application, where it is needed.
References
1.Gatto A, Luliano L. Cutting mechanisms and surface features of WEDM metal matrix composite. Journal of Material Processing Technology. 1997;65:209-214
2.Azouzi R, Guillot M. On-line prediction of surface finish and dimensional deviation in turning neural network base sensor fusion. International Journal of Machine Tools and Manufacture. 1997;37:1201-1217
3.Montgomery DC. Design and Analysis of Experiments. Singapore: Wiley; 1991
4.Ho KH, Newman ST, Rahimifard S, Allen RD. State of the art wire electrical discharge machining (EDM). International Journal of Machine Tools and Manufacture. 2004;44:1247-1259
5.Puertas I, Lues CJ. A study on the machining parameters optimization of electrical discharge machining. Journal of Material Processing Technology. 2003;143-144:521-526
6.Sanchez JA, Lopez de Lacalle LN, Lamikiz A, Bravo U. Dimensional accuracy optimization of multi-stage planetary EDM. International Journal of Machine Tools & Manufacture. 2002;42:1643-1648
7.Mondal D, Pal SK, Saha P. Modelling of electrical discharge machining process using back propagation neural network and multi- objective optimizations using non-dominating sorting genetic algorithm-2nd. Journal of Materials Processing Technology. 2007;186:154-162
8.Panda DK, Bhoi RK. Artificial neural network prediction of material removal rate in electro-discharge machining. Materials and Manufacturing Processes. 2005;20:645-672
9.Fisher RA. Statistical Methods for Research Worker. London: Oliver & Boyd; 1925
10.Sahoo GB, Ray C, Wade HF. Pesticide prediction in ground water in North Carolina domestic wells using artificial neural networks. Ecological Modelling. 2005;183(1):29-46
11.Kexing S, Jiandong X, Qiming D, et al. Optimization of the processing parameters during internal oxidation of Cu–Al alloy powders using an artificial neural network. Materials & Design. 2005;26(4):337-341
12.Juan-Hua S, Qi-Ming D, Ping L. Simulation of aging process of lead frame copper alloy by an artificial neural network. Transactions of the Nonferrous Metals Society of China. 2003;13(6):1419-1423
Written By
Umesh K. Vates, N.K. Singh, B.P. Sharma and S. Sivarao
Submitted: 26 September 2018Reviewed: 02 October 2018Published: 31 May 2019
Open access peer-reviewed chapter
