An Efficient PC-Based Environment for the Improvement of Magnetic Cores Industrial Process

  • P. S. Georgilakis
  • N. D. Hatziargyriou
  • N. D. Doulamis
  • A. D. Doulamis
  • J. A. Bakopoulos
Conference paper
Part of the Advanced Manufacturing book series (ADVMANUF)


Distribution transformer losses constitute a significant amount of the total losses in distribution networks. In Greece, for example, it is estimated that transformer iron losses are about 10% of the total distribution network losses [1]. In an industrial environment, dealing with construction of wound core distribution transformers, prediction of iron losses of individual cores is a crucial task, since the latter significantly affect both the quality and the performance of the finally produced three phase transformers. However, there is no simple analytical relationship for estimating iron losses of individual cores, due to the fact that many parameters, both qualitative and quantitative, are involved in the process.


Neural Network Architecture Load Forecast Iron Loss Individual Core Absolute Relative Error 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Papadopoulos M 1994 Electric Energy Distribution Networks. NTUA, Athens (in Greek)Google Scholar
  2. 2.
    Beal R, Jackson T 1990 Neural Computing: An Introduction. IOP Publishing Ltd., Bristol, UKCrossRefGoogle Scholar
  3. 3.
    Haykin S 1994 Neural Networks:A Comprehensive Foundation. Macmillan, New YorkMATHGoogle Scholar
  4. 4.
    Peng T M, Hubele N F, Karady G G 1992 Advancement in the Application of Neural Networks for Short-Term Load Forecasting. IEEE Trans, on Power Systems 7:250–257CrossRefGoogle Scholar
  5. 5.
    Lu C N, Wu H T, Vemuri S 1993 Neural Network Based Short Term Load Forecasting. IEEE Trans, on Power Systems 8:336–342CrossRefGoogle Scholar
  6. 6.
    Park D C, El-Sharkawi M A, Marks R J II, Atlas L E, Dambong M J 1991 Electric Load Forecasting Using an Artificial Neural Network. IEEE Trans, on Power Systems 6:442–448CrossRefGoogle Scholar
  7. 7.
    Pecas-Lopes J A, Fidalgo J N, Miranda V, Hatziargyriou N 1994 Neural Networks Used for On-Line Dynamic Security Assessment of Isolated Power Systems with a Large Penetration from Wind Production - A Real Case Study. In: 3 rd International Workshop on Rough Sets and Soft Computing (RSSC’94). San Jose, CaliforniaGoogle Scholar
  8. 8.
    Sobajic D J, Pao Y H 1989 Artificial Neural-Net Based Dynamic Security Assessment for Electric Power Systems. IEEE Trans. On Power System 4:220–228CrossRefGoogle Scholar
  9. 9.
    Weerasooriya S, El-Sharkawi M A, Dambong M, Marks R J II 1992 Towards Static Security Assessment of a Large Scale Power System Using Neural Networks.IEE Proc., Part C 139:64–70Google Scholar
  10. 10.
    Georgilakis P S, Bakopoulos J A, Hatziargyriou N D 1997 A Decision Tree Method for Prediction of Distribution Transformer Iron Losses. In: 32 nd Universities Power Engineering Conference (UPEC ’97), Vol. 1. Manchester, pp 257–260Google Scholar
  11. 11.
    AI Ware 1989 NNET 210 User’s Manual. AI Ware Incorporated, Cleveland, OHGoogle Scholar
  12. 12.
    Kollias S, Anastassiou D 1989 An Adaptive Least Squares Algorithm for the Efficient Training of Artificial Neural Networks. IEEE Trans, on Circuits & Systems 36:1092–1101CrossRefGoogle Scholar
  13. 13.
    Kollias S 1996 A Multiresolution Neural Network Approach to Invariant Image Recognition. Neurocomputing 12: 35–57CrossRefGoogle Scholar
  14. 14.
    Taguchi G, Konishi S 1987 Taguchi Methods: Orthogonal Arrays and Linear Graphs; Tools for Quality Engineering. ASI, Dearborn, MI, USAGoogle Scholar
  15. 15.
    Logothetis N 1992 Managing for Total Quality. Prentice Hall International, UKGoogle Scholar

Copyright information

© Springer-Verlag London Limited 1999

Authors and Affiliations

  • P. S. Georgilakis
  • N. D. Hatziargyriou
  • N. D. Doulamis
  • A. D. Doulamis
  • J. A. Bakopoulos

There are no affiliations available

Personalised recommendations