The modeling capability of an artificial neural network is studied through three different manufacturing processes. The first case study is a linear separable pattern classification problem in manufacturing process diagnosis. The performance between the neural network and the probability voting classifier is compared. The second case study uses a design of experiment to study an SMC compression molding process. Modeling and predicting performances between a regression model and a neural network model are compared in linear as well as nonlinear cases. The third case study investigates correlation models between the operating conditions and product quality defects of an automotive painting process. Results from a neural network model are compared with those of a probability voting classifier. An ad hoc modification named focused learning paradigm on the back-propagation algorithm is also introduced to speed up network learning.

Issue Section:
Technical Papers
Topics:
Artificial neural networks, Manufacturing, Modeling, Neural network models, Probability, Algorithms, Compression molding, Experimental design, Painting, Particle filtering (numerical methods), Product quality, Regression models, Sheet molding compound (Plastics), Sliding mode control, Surface mount components
1.
Chan
 
L. W.
, and
Fallside
 
F.
,
1987
, “
An Adaptive Training Algorithm for Back Propagation Networks
,”
Computer Speech and Language
, Vol.
2
, pp.
205
–
218
.
2.
Chen
 
Y. B.
,
Sha
 
J. L.
, and
Wu
 
S. M.
,
1990
, “
Diagnosis of the Tapping Process by Information Measure and Probability Voting Approach
,”
ASME JOURNAL OF ENGINEERING FOR INDUSTRY
, Vol.
112
, pp.
319
–
325
.
3.
Hornik
 
K.
,
Stinchcombe
 
M.
, and
White
 
H.
,
1989
, “
Multilayer Feedforward Networks are Universal Approximators
,”
Neural Networks
, Vol.
2
, pp.
359
–
366
.
4.
Jacobs
 
R. A.
,
1988
, “
Increased Rates of Convergence through Learning Rate Adaptation
,”
Neural Networks
, Vol.
1
, pp.
295
–
307
.
5.
Khalil, H. K., 1992, Nonlinear Systems, Macmillan Publishing Co., New York.
6.
Khanna, T., 1990, Foundations of Neural Networks, pp. 69–74, Addison-Wesley Inc., New York.
7.
Kuschewski
 
J. G.
,
Hui
 
S.
, and
Zak
 
S. H.
,
1993
, “
Application of Feedforward Neural Networks to Dynamic System Identification and Control
,”
IEEE Trans. on Control Systems and Technology
, Vol.
1
, No.
1
, pp.
37
–
49
.
8.
Lan
 
M. S.
,
Lin
 
P.
, and
Bain
 
L. J.
,
1992
, “
Modeling and Control of the Lithographic Offset Color Printing Process using Artificial Neural Networks
,”
ASME WAM
, PED-Vol.
57
, pp.
1
–
10
.
9.
Lippmann, R., 1987, “An Introduction to Computing with Neural Nets,” IEEE ASSP Magazine, 4–22.
10.
McClelland, J. L., Rumelhart, D. E., and Hinton, G. E., 1986, Parallel Distributed Processing, Vols. 1 and 2., The MIT Press, Cambridge, MA.
11.
McCulloch
 
W. S.
, and
Pitts
 
W. H.
,
1943
, “
A Logical Calculus of the Ideas Immanent in Nervous Activity
,”
Bulletin of Mathematical Biophysics
, Vol.
5
, pp.
115
–
133
.
12.
Minsky, M., and Papert, S., 1969, Perceptrons: An Introduction to Computational Geometry, Cambridge, MA, The MIT Press.
13.
Narendra, K. S., and Parthasarathy, K., 1990, “Identification and Control of Dynamical Systems using Neural Networks,” IEEE Trans. on Neural Networks, Vol. 1, No. 1.
14.
Nguyen
 
D.
, and
Windrow
 
B.
,
1990
, “
Improving the Learning Speed of 2-Layer Neural Networks by Choosing Initial Values of the Adaptive Weights
,”
International Joint Conference of Neural Networks
, Vol.
3
, pp.
21
–
26
, July.
15.
Pallett, T. J., and Ahmad, S., 1991, “Real-time Helicopter Flight Control: Modeling and Control by Linearization and Neural Networks,” Tech. Rep. TREE 91-35, Purdue Univ., West Lafayette, IN.
16.
Rangwala
 
S.
, and
Dornfeld
 
D.
,
1990
, “
Sensor Integration using Neural Networks for Intelligent Tool Condition Monitoring
,”
ASME JOURNAL OF ENGINEERING FOR INDUSTRY
, Vol.
112
, No.
3
, pp.
219
–
228
.
17.
Santhanam, N., Chiang, H. H., Himasekhar, K., Tuschak, P., and Wang, K. K., 1992, “Postmolding and Load-Induced Deformation Analysis of Plastic Parts in the Injection Molding Process,” AC Tech., Ithaca, NY.
18.
Taguchi, G., 1986, Introduction to Quality Engineering, Asian Productivity Organization.
19.
Tansel, I. N., and McLaughlin, C., 1991, “Monitoring of Tool Breakage with Restricted Coulomb Energy Type Neural Networks,” Proceedings of 1991 ASME Winter Annual Meetings: Sensors, Controls, and Quality Issues in Manufacturing.
20.
Tseng, S. C., and Osswald, T. A., 1993, “Prediction of Shrinkage and Warpage of Fiber Reinforced Thermoset Composite Parts,” Proceedings of SPI Annual Conference.
21.
Tversky
 
A.
, and
Kahneman
 
D.
,
1974
, “
Judgment under Uncertainty: Heuristics and Biases
,”
Science
, Vol.
185
, pp.
1124
–
31
.
22.
Vogl
 
T. P.
,
Mangis
 
J. K.
,
Rigler
 
A. K.
,
Zink
 
W. T.
, and
Alkon
 
D. L.
,
1988
, “
Accelerating the Convergence of the Backpropagation Method
,”
Biological Cybernetics
, Vol.
59
, pp.
257
–
263
.
23.
Wan
 
E. A.
,
1990
, “
Neural Network Classification: A Bayesian Interpretation
,”
IEEE Trans. on Neural Networks
, Vol.
1
, No.
4
, pp.
303
–
305
.
24.
Wessels
 
L.
, and
Barnard
 
E.
,
1992
, “
Avoiding False Local Minima by Proper Initialization of Connections
,”
IEEE Trans. on Neural Networks
, Vol.
3
, No.
6
, pp.
899
–
905
.
25.
Wu, S. M., Ni, J., and Hu, S., 1989, “Next Generation Quality Control in Manufacturing—Real-time Defect Prevention,” Proceedings of the 1989 ASME Winter Annual Meeting.
This content is only available via PDF.
Copyright © 1995
 by The American Society of Mechanical Engineers
You do not currently have access to this content.