Artificial Neural Network (ANN) has been widely used for engineering monitoring and diagnosis. However, there are still several important problems unsolved and one of them is the architecture design of the ANN (namely, choosing the number of nodes in the hidden layer). In this technical brief, a new method of ANN architecture is introduced based on the idea that an ANN represents a mapping of training samples. Hence, the best ANN should represent the mapping that is most similar to the training samples. The method is tested using three practical engineering monitoring and diagnosis examples, including tool condition monitoring in turning, cutting condition monitoring in tapping, and metallographic condition monitoring in welding. It is demonstrated that the proposed method can improve the monitoring and diagnosis by approximately 3 percent.

1.
Asoh
H.
, and
Otsu
N.
,
1989
, “
Nonlinear Data Analysis and Multilayer Perceptions
,”
Proceedings of IJCNN
, Vol.
I
, pp.
441
415
.
2.
Chauvian
Y.
,
1989
, “
Principal Component Analysis by Gradient Descent on a Constrained Linear Hebbain Cell
,”
Proceedings of IJCNN
, Vol.
1
, pp.
373
380
.
3.
Devijver, P. A., and Kittler, J., 1982, Pattern Recognition: A Statistical Approach, Prentice-Hall.
4.
Dornfeld
D. A.
,
1991
, “
Neural Networks Sensor Fusion for Tool Condition Monitoring
,”
Annual of CIRP
, Vol.
39/1
, pp.
101
105
.
5.
Du
R.
,
Elbestawi
M. A.
, and
Wu
S.
,
1994
, “
Automated Monitoring of Manufacturing Processes, Part 1: Monitoring Methods, Part 2: Applications
,”
ASME Journal of Engineering for Industry
, Vol.
117
, No.
2
, pp.
121
132
.
6.
Fogal
D. B.
,
1991
, “
An Information Criterion for Optimal Neural Network Selection
,”
IEEE Trans. on Neural Network
, Vol.
2
(
5
), pp.
490
497
.
7.
Gallinari
G.
, &
Thiria
S.
,
1988
, “
Multilayer Perceptions and Data Analysis
,”
Proceedings of IJCNN
, Vol.
I
, pp.
391
399
.
8.
Gutierrez
M.
,
Wang
J.
, and
Grondin
R.
,
1989
, “
Estimating Hidden Unit Number for Two-Layer Perceptions
,”
Proceedings of IJCNN
, Vol.
I
, pp.
677
681
.
9.
Kong
S. Y.
, &
Hang
J. W.
,
1988
, “
An Algebraic Projection Analysis for Optimal Hidden Units, Size and Learning Rates in Back-Propagation Learning
,”
Proceedings of IJCNN
, Vol.
I
, pp.
363
370
.
10.
Kramer
M. A.
,
1991
, “
Nonlinear Principal Component Analysis Using Autoassociative Neural Networks
,”
AIChE
, Vol.
37
(
2
), pp.
233
243
.
11.
Li, C. J., and Yu, X. L., 1993, “High Pressure Air Compressor Valve Fault Diagnosis Using Feedforward Neural Network,” 1993 ASME Winter Annual Meeting, PED-Vol. 64, pp. 375–380.
12.
Liu, T. I., & Lyons, C. S., 1993, “Monitoring for Glass Production Using Neural Networks,” 1993 ASME Winter Annual Meeting, PED-Vol. 64, pp. 217–224.
13.
Witcomb
R. C.
,
Skitt
P. J. C.
, and
Down
M. J.
,
1991
, “
Automating the Collection and Organization of Reference Spectra for use in Vibration Monitoring
,”
COMADEM
, Vol.
91
, pp.
17
24
.
14.
Rumelhart, D. E., and McClelland, J. L., 1986, Parallel Distributed Processing. Vol. 1: Foundations, MIT Press.
15.
Proceeding of 1993 International Neural Network Society Annual Meeting,” Portland, Oregon.
16.
Lendaris, G. L., Zwick, M., and Mathia, K., 1993, “On Matching ANN Structure to Problem Domain Structure,” Proceeding of 1993 World Congress on Neural Networks, Vol. III, pp. 488–493.
17.
Krishnakumar, K., 1993, “Optimization of the Neural Net Connectivity Pattern Using a Back-Propagation Algorithm,” Proceedings of 1993 World Congress on Neural Networks, Vol. III, pp. 498–501.
18.
Yuedong Chen, and R. Du, 1994, “The Use of Artificial Neural Network for Monitoring and Diagnosis of Engineering Processes,” submitted to J. of Mechanical Systems and Signal Processing.
This content is only available via PDF.
You do not currently have access to this content.