Comparison of Adaptive Techniques for the Prediction of the Equivalent Salt Deposit Density of Medium Voltage Insulators

One of the main reasons that flashover can occur in distribution lines is the sea salt contamination of medium voltage insulators. Equivalent salt deposit density (ESDD) expresses the contamination level of insulators and is used as the main criterion for scheduling the maintenance (washing) of insulators. In this paper two different adaptive techniques, a multi model partitioning filter (MMPF) and an artificial neural network (ANN), are developed and presented in order to predict the equivalent salt deposit density of medium voltage insulators. Real data are used for the MMPF modeling and the ANN training, as well as for the comparison of the produced by the two techniques ESDD results with actual measured ones. The proposed techniques can be very useful in the work of electrical maintenance engineers for estimating the insulator’s contamination easily, accurately and at minimum cost resulting in a more effective maintenance scheduling.

[1]  G. Beligiannis,et al.  A generic applied evolutionary hybrid technique , 2004, IEEE Signal Processing Magazine.

[2]  Spiridon D. Likothanassis,et al.  Adaptive on-line multiple source detection , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[3]  Xiuchen Jiang,et al.  Measurements of equivalent salt deposit density (ESDD) on a suspension insulator , 2002 .

[4]  Lambros Ekonomou,et al.  Adaptive load forecasting of the Hellenic electric grid , 2008 .

[5]  Lambros Ekonomou,et al.  Effective insulator maintenance scheduling using artificial neural networks , 2010 .

[6]  Lambros Ekonomou,et al.  Electricity demand load forecasting of the Hellenic power system using an ARMA model , 2010 .

[7]  Vassilios C. Moussas,et al.  Application of the multi-model partitioning theory for simultaneous order and parameter estimation of multivariate ARMA models , 2008, Int. J. Model. Identif. Control..

[8]  Lambros Ekonomou,et al.  Modeling of the grounding resistance variation using ARMA models , 2008, Simul. Model. Pract. Theory.

[9]  Grigorios N. Beligiannis,et al.  Genetically determined variable structure multiple model estimation , 2001, IEEE Trans. Signal Process..

[10]  A. S. Ahmad,et al.  Assessment of ESDD on high-voltage insulators using artificial neural network , 2004 .

[11]  D. Lainiotis,et al.  Partitioning: A unifying framework for adaptive systems, I: Estimation , 1976, Proceedings of the IEEE.

[12]  S. Pappas,et al.  ADAPTIVE NETWORK ANOMALY DETECTION USING BANDWIDTH UTILISATION DATA , 2006 .

[13]  D.G. Lainiotis,et al.  Partitioning: A unifying framework for adaptive systems, II: Control , 1976, Proceedings of the IEEE.

[14]  Sokratis K. Katsikas,et al.  Towed array shape estimation using multimodel partitioning filters , 1998 .

[15]  I. Ramirez-Vazquez,et al.  Criteria for the diagnostic of polluted ceramic insulators based on the leakage current monitoring technique , 1999, 1999 Annual Report Conference on Electrical Insulation and Dielectric Phenomena (Cat. No.99CH36319).

[16]  T. I. Maris,et al.  Artificial intelligence assessment of sea salt contamination of medium voltage insulators , 2008 .

[17]  Yukio Mizuno,et al.  A study on probabilistic assessment of contamination flashover of high voltage insulator , 1995 .

[18]  Lambros Ekonomou,et al.  Design of artificial neural network models for the estimation of distribution system voltage insulators' contamination , 2010 .