Forecasting on Electrical Power Distribution Transformers

Eyenubo Ogheneakpobo Jonathan

Abstract


Prediction of the remaining life of high-voltage power transformers is an important issue for energy usage because of the need for planning maintenance and capital expenditures. Lifetime data for such transformers are complicated because transformer lifetimes can extend over many decades and transformer designs and manufacturing practices have evolved. We were asked to develop statistically based predictions for the lifetimes of an energy company’s fleet of high-voltage transmission and distribution transformers. Data were collected from the utility main-substation in Warri a city in Delta State, Nigeria with transformer rating: 2 x 15 MVA, with HV/LV of 33/11kV. These data were obtained from the log of daily recordings. These data collected were processed by using Excel Tools and Analysis ToolPak for over a year. The data obtained was observed that the oil and winding temperatures are almost constant as there are variations in the IN_loads and OUT_loads data for transformers 1 and 2. A statistical procedure, based on age-adjusted life distributions was developed, for computing a prediction interval for remaining life for two transformers in service. Extension of the idea provide predictions and prediction intervals for the cumulative number of failures, over a range of time, for the overall fleet of transformers.


Full Text:

PDF

References


. Kermanshahi B, and R. Yokoyama Practical Implementation of Neural Nets for Weather- Dependent Load Forecasting and Reforecasting at A Power Utility, Power Systems Computer Conference, PSCC96, Dresden, 1996

Lu C. N., Wu H. T., and Vemuri S, (2003), ‘Neural Network Based Short Term Load Forecasting, IEEE Transations on Power Systems, vol.8, no. 1.

Gianfranco C, Roberto N and Federico P, (2001) “Load pattern clustering for Short-Term Load Forecasting of anomalous daysâ€, Power Tech Proceedings, 2001 IEEE Porto, Vol. 2,

A. Khotanzad, R. Tsun-Liang L. and Abaye A, (2007), “ANNSTLF-a neural-network-based electric load forecasting systemâ€, IEEE Transactions on Neural Networks, Vol. 8, No. 4, pp. 835 -846.

Ho K. L, Hsu Y. Y., and Chen K. K., (2009), “Short term load forecasting of Taiwan power system using a knowledge-based expert system,†IEEE Trans. Power Systems, vol. 5, no. 4, pp. 1214–1221.

Park J. H., Park Y. M., and Lee K. Y, (2001), “Composite modeling for adaptive short-term load forecasting,†IEEE Trans. Power Systems, vol. 6, no. 2, pp. 450–457.

I. Moghram, H. Y and S. Rahman, (2009), “Analysis and evaluation of five short-term load forecasting techniques,†IEEE Trans. Power Systems, vol. 4, no. 4, pp. 1484–1491, 1989.

Rumelheart D. E., Meeker W. Q. and Escobar, L. A, (2006), ‘Parallel Distributed Processing: Rumelheart and Maccleland Eds, Mit Press, Cambridge, Ma, USA.

V. Miranda, M. Matos, J. and Leão M.T., “Intelligent Tools in a Real-World DMS Environmentâ€, Proc. IEEE Summer Power meeting, July 2000, pp. 163-168, Seattle, USA.

. Jin, Z., Ying, Z. and Wei, L. J. (2001). A simple resampling method by perturbing the minimand. Biometrika 88 381–390.

. Meeker, W. Q. and Escobar, L. A. (2008). SPLIDA (S-PLUS life data analysis).

Available at www.public.iastate.edu/Ëœsplida.

. Nelson, W. (2001). Prediction of field reliability of units, each under differing dynamic

stresses, from accelerated test data. In Handbook of Statistics 20: Advances in Reliability, Chapter IX. North-Holland, Amsterdam.


Refbacks

  • There are currently no refbacks.