Self-Organizing Map Improved for Classification of Partial Discharge using Desirability Function

This paper presents an analysis for Self Organizing Map (SOM) using Response Surface Methodology (RSM) and Desirability Function to find the optimal parameters to improve performance. This comparative explores the relationship between explanatory variables (numerical and categorical) such a competitive algorithm and learning rate and response variables as training time and quality metrics for SOM. Response surface plots were used to determine the interaction effects of main factors and optimum conditions to the performance in classification of partial discharge (PD).

[1]  M. Salama,et al.  PD pattern recognition with neural networks using the multilayer perceptron technique , 1993 .

[2]  V. Frišták,et al.  Response surface methodology as optimization tool in study of competitive effect of Ca2+ and Mg2+ ions in sorption process of Co2+ by dried activated sludge. , 2012 .

[3]  Stanley C. Ahalt,et al.  Competitive learning algorithms for vector quantization , 1990, Neural Networks.

[4]  Trevor Blackburn,et al.  Data Mining Techniques to Assess the Condition of High Voltage Electrical Plant , 2002 .

[5]  Sung-Kwun Oh,et al.  Partial Discharge Pattern Recognition Using Fuzzy-Neural Networks (FNNs) Algorithm , 2008, 2008 IEEE International Power Modulators and High-Voltage Conference.

[6]  Georg Pölzlbauer.  Survey and Comparison of Quality Measures for Self-Organizing Maps , 2004 .

[7]  N.F. Ab Aziz,et al.  Analysis of Partial Discharge Measurement Data Using a Support Vector Machine , 2007, 2007 5th Student Conference on Research and Development.

[8]  Erkki Oja,et al.  Engineering applications of the self-organizing map , 1996, Proc. IEEE.

[9]  Hans Edin,et al.  Partial Discharges Studied with Variable Frequency of the Applied Voltage , 2001 .

[10]  Xu Guo-zheng,et al.  Study on Partial Discharge Localization by Ultrasonic Measuring in Power Transformer Based on Particle Swarm Optimization , 2008, 2008 International Conference on High Voltage Engineering and Application.

[12]  Esa Alhoniemi,et al.  Clustering of the self-organizing map , 2000, IEEE Trans. Neural Networks Learn. Syst..

[13]  Hong-Tzer Yang,et al.  Application of self organizing map approach to partial discharge pattern recognition of cast-resin current transformers , 2008 .

[14]  Angela M. Dean,et al.  Design and analysis of experiment , 2013 .

[15]  Cecilia Forssén.  Modelling of cavity partial discharges at variable applied frequency , 2008 .

[16]  S. Tenbohlen,et al.  Detection and location of partial discharges in power transformers using acoustic and electromagnetic signals , 2008, IEEE Transactions on Dielectrics and Electrical Insulation.

[17]  William A. Thue,et al.  Electrical Power Cable Engineering, Third Edition , 2016 .

[18]  S. Venkatesh,et al.  ROLE OF PARTITIONING BASED CLUSTERING ALGORITHMS IN CLASSIFYING MULTI-SOURCE PARTIAL DISCHARGE PATTERNS USING PROBABILSTIC NEURAL NETWORK AND ITS ADAPTIVE VERSION – A REVIEW , 2012 .

[19]  H. Hirose,et al.  Diagnosis of electric power apparatus using the decision tree method , 2008, IEEE Transactions on Dielectrics and Electrical Insulation.

[20]  A. Krivda,et al.  Automated recognition of partial discharges , 1995 .

[21]  Carlos Alberto Ochoa Ortíz Zezzatti,et al.  A comparative study of partial discharge by classification's kind , 2012, 2012 12th International Conference on Hybrid Intelligent Systems (HIS).

[22]  T.R. Blackburn,et al.  Descriptive data mining of partial discharge using decision tree with genetic algorithm , 2008, 2008 Australasian Universities Power Engineering Conference.