Power transformers are major elements of the electric power transmission and distribution infrastructure. Transformer failure has severe economical impacts from the utility industry and customers. This paper presents analysis, design, development, and experimental evaluation of a robust failure diagnostic technique. Hopfield neural networks are used to identify variations in physical parameters of the system in a systematic way, and adapt the transformer model based on the state of the system. In addition, the Hopfield network is used to design an observer which provides accurate estimates of the internal states of the transformer that can not be accessed or measured during operation. Analytical and experimental results of this adaptive observer for power transformer diagnostics are presented.

Issue Section:
Technical Papers
Keywords:
power transformers, computerised monitoring, adaptive systems, fault diagnosis, Hopfield neural nets, power engineering computing
Topics:
Power transformers, Temperature, Artificial neural networks, Monitoring systems
1.
Douglas
,
J.
,
1995
, “
The Maintenance Revolution
,”
EPRI J.
,
207
, No.
9
, May/June, pp.
6
–
15
.
2.
Allan
,
D. J.
,
1987
, “
Editorial
,”
Electra
, , No. 114, Oct, pp.
3
–
6
.
3.
Pierce
,
L. W.
,
1994
, “
Predicting Liquid Filled Transformer Loading Capability
,”
IEEE Trans. Ind. Appl.
,
30
, No.
1
, Jan./Feb., pp.
170
–
178
.
4.
Pierce
,
L. W.
,
1992
, “
An Investigation of the Thermal Performance of an Oil Filled Transformer Winding
,”
IEEE Trans. Power Deliv.
,
7
, No.
3
, July, pp.
1347
–
1358
.
5.
Lesieutre
,
B. C.
,
Hagman
,
W. H.
, and
Kirtley
,
J. L.
Jr.,
1997
, “
An Improved Transformer Top Oil Temperature Model for Use in an On-Line Monitoring and Diagnostic System
,”
IEEE Trans. Power Deliv.
,
12
, No.
1
, Jan., pp.
249
–
254
.
6.
Shoureshi, R., and McLaughlin, K., 1983, “Analytical and Experimental Investigation of Flow-Reversible Heat Exchangers Using Temperature-Entropy Bond Graphs,” Proc. Amer. Control Conf., pp. 93–98.
7.
Shoureshi, R., and McLaughlin, K., 1985, “Application of Bond Graph to Thermo-Fluid Processes and Systems,” Proc. Amer. Control Conf. pp. 595–600.
8.
Ioannou, P., and Sun, J., 1996, Robust Adaptive Control, Prentice-Hall, Upper Saddle River, NJ.
9.
Narendra, K. S., Annaswamy, A. M., 1989, Stable Adaptive Systems, Prentice-Hall, New Jersey.
10.
Chen, C. T., 1984, Linear Systems Theory and Design, Holt, Rinehart and Winston, New York, NY.
11.
Hopfield, J. J., 1982, “Neural Networks and Physical Systems with Emergent Collective Computational Abilities,” Proc. Natl. Acad. Science, Vol. 79, pp. 2554–2558.
12.
Hopfield, J. J., 1984, “Neurons with Graded Response Have Collective Computational Properties Like Those of Two-State Neurons,” Proc. Natl. Acad. Sci., Vol. 81, pp. 3088–3092.
13.
Krelsselmeir
,
G.
,
1977
, “
Adaptive Observers with Exponential Rate of Convergence
,”
IEEE Trans. Autom. Control
,
AC-22
, Feb., pp.
2
–
8
.
14.
Chu, R., 1992, “Neural Networks For System Identification and State Observation of Dynamical Systems,” PhD. Thesis, Purdue University, Aug.
15.
Chu, R., Shoureshi, R., and Tenorio, M., 1992, “Neural Networks for System Identification,” Proc. Amer. Control Conf. 1989, pp. 916–921.
16.
Chu, R., and Shoureshi, R., 1994, “Simultaneous Parameter Identification and State Estimation Using Neural Networks,” Proc. 10th IFAC Symposium on System Identification, Vol. 2, pp. 331–335.
Copyright © 2001
 by ASME
You do not currently have access to this content.