tmp685D TMP
tmp685D TMP
tmp685D TMP
Artificial neural network approach for the prediction of abrasive wear behavior of
carbon fabric reinforced epoxy composite
K Sudarshan Raoa*, Y S Varadarajanb & N Rajendraa
a
Department of Mechanical Engineering, Vivekananda College of Engineering & Technology, Puttur 574 203, India
b
Department of Industrial & Production Engineering, National Institute of Engineering, Mysore 570 008, India
Received 15 March 2013; accepted 27 September 2013
Artificial neural networks have emerged as a good candidate to mathematical wear models, due to their capabilities of
handling nonlinear behavior, learning from experimental data and generalization. In the present work the potential of using
neural networks for the prediction of abrasive wear properties of unfilled and graphite filled carbon fabric reinforced epoxy
composite under various testing conditions is investigated. Back propagation neural network with 3-5-1 architecture has
been used to predict the weight loss in abrasive wear situation. The network performance of different training algorithms is
evaluated using the coefficient of determination B, sum squared error, mean relative error, mean squared error and
regression as a quality measure. The results show that the performance of Levenberg-Marquardt (LM) training algorithm is
superior to all other algorithms. Finally, the well-optimized and trained neural network with LM training algorithm is used
to predict the wear properties as a function of testing conditions, according to the input data sets. The results show that the
predicted data are perfectly acceptable when compared to the actual experimental test results. Hence, a well-trained artificial
neural networks system is expected to be very helpful for estimating the weight loss in the complex three-body abrasive
wear situation of polymer composites.
Keywords: Neural network, Back propagation, Carbon fabric, Epoxy, Graphite filler, Three-body abrasive wear
17
18
19
20
0
0
0
0
0
0
0
0
0
2
2
2
2
2
2
2
2
2
4
4
4
4
4
4
4
4
4
6
6
6
6
6
6
6
6
6
Load N
Sliding distance
m
Wear loss,
g
11
11
11
23
23
23
35
35
35
11
11
11
23
23
23
35
35
35
11
11
11
23
23
23
35
35
35
11
11
11
23
23
23
35
35
35
300
600
900
300
600
900
300
600
900
300
600
900
300
600
900
300
600
900
300
600
900
300
600
900
300
600
900
300
600
900
300
600
900
300
600
900
0.0843
0.1066
0.1576
0.2348
0.3964
0.4923
0.4533
0.5881
0.738
0.0788
0.1646
0.1909
0.275
0.3301
0.4872
0.4502
0.6888
0.7192
0.0829
0.1428
0.245
0.2531
0.4312
0.5972
0.4051
0.6116
0.8326
0.0821
0.1675
0.2221
0.3092
0.6823
0.6388
0.5959
0.6942
0.8354
i =1[Opi Oi ] 2
B =1
M
i =1[Oi O]2
(2)
M
i
=1[Oi Opi ]
(3)
MRE=
M
i
=1
[Oi Opi ]
Oi
(4)
MRE
LM
9.5952
BFG
13.9415
SSE
MSE
Regression
0.0356 0.0002
0.9853
0.9820
0.0633 0.0042
0.9634
0.9680
BR
13.4349
0.0987 0.0066
0.9762
0.9502
GD
38.5671
0.6124 0.0119
0.8347
0.6909
GDM
20.9231
0.1333 0.0039
0.9674
0.9327
GDA
20.8730
0.1352 0.0032
0.9685
0.9318
GDX
21.0957
0.1327 0.0037
0.9688
0.9330
RP
13.8479
0.0828 0.0015
0.9756
0.9582
SCG
18.4063
0.1172 0.0097
0.9639
0.9408
21
22
1
2
3
4
5
6
7
8
9
10
11
12
Filler content % wt
0
0
0
2
2
2
4
4
4
6
6
6
Load N
11
23
35
11
23
35
11
23
35
11
23
35
Sliding distance m
300
600
900
600
900
300
900
600
300
300
900
600
Conclusions
An experimental approach to the evaluation of
abrasive wear characteristics of carbon epoxy
composites using back propagation neural network is
proposed in the present study. Initially, the number
of neurons in the hidden layer is optimized by trial
and error method. Then the neural network 3-5-1
( three input neurons, five hidden neurons in one
hidden layer and one output neuron) is trained using
nine different training algorithms and the network
performance is evaluated using the coefficient of
determination B, sum squared error, mean relative
error, mean squared error and regression as a quality
measure. For Levenberg-Marquardt (LM) training
algorithm, the value of mean relative error was found
to be 9.5952, sum-squared error 0.035616, mean
squared error 0.00016, regression 0.98528 and
coefficient
of
determination
B
0.9820.
The performance of LM algorithm was superior to
all others. Finally, the well-optimized and trained
neural network with LM training algorithm was
used to predict the wear rate as a function of filler
content, normal load and sliding distance. The
results show that the predicted data are perfectly
acceptable when compared to the actual experimental
test results. Hence, a well-trained ANN system is
expected to be very helpful for estimating the
Wear loss, g
Experimental
ANN Predicted
Error %
0.0843
0.3964
0.7380
0.1646
0.4872
0.4502
0.2450
0.4312
0.4051
0.0821
0.6388
0.6942
0.0883
0.3827
0.7280
0.1583
0.4899
0.4345
0.2475
0.4120
0.4040
0.0825
0.6369
0.7027
4.53
3.58
1.37
3.98
0.55
3.61
1.01
4.66
0.27
0.48
0.30
1.21