Modified Successive Geometric Segmentation Method Applied to Power Transformers Faults Diagnosis

This paper proposes a new approach to address the complex problem of the internal faults classification in power transformers. The fault classification is made using an algorithm based on a geometric approach to construct an artificial neural network. The input parameters are related to the concentrations of various gases dissolved in insulating oil. The proposed technique is able to generate both the topology and the weight for each neuron without specifying initial network parameters. Datasets of dissolved gas concentration in high-voltage transformers that have been found in the scientific literature are used to validate the methodology. The results indicate a high accuracy rate compared to other important computational intelligence methods used to high-voltage transformers faults classification.

[1]  J. Rolim,et al.  A hybrid tool for detection of incipient faults in transformers based on the dissolved gas analysis of insulating oil , 2006, 2006 IEEE Power Engineering Society General Meeting.

[2]  Gang Zheng,et al.  Multiclass support vector machines for power system disturbances classification based on wide-area frequency measurements , 2011, 2011 Proceedings of IEEE Southeastcon.

[3]  Ming-Ta Yang,et al.  Intelligent fault types diagnostic system for dissolved gas analysis of oil-immersed power transformer , 2013, IEEE Transactions on Dielectrics and Electrical Insulation.

[4]  Abdelkader Chaari,et al.  SVM-based decision for power transformers fault diagnosis using Rogers and Doernenburg ratios DGA , 2013, 10th International Multi-Conferences on Systems, Signals & Devices 2013 (SSD13).

[5]  Nirmal K. Bose,et al.  Neural network design using Voronoi diagrams , 1993, IEEE Trans. Neural Networks.

[6]  Michel Duval,et al.  Interpretation of gas-in-oil analysis using new IEC publication 60599 and IEC TC 10 databases , 2001 .

[7]  P. J. Griffin,et al.  An Artificial Neural Network Approach to Transformer Fault Diagnosis , 1996, IEEE Power Engineering Review.

[8]  S Singh,et al.  Dissolved gas analysis technique for incipient fault diagnosis in power transformers: A bibliographic survey , 2010, IEEE Electrical Insulation Magazine.

[9]  Ming C. Lin,et al.  A framework for fast and accurate collision detection for haptic interaction , 1998, Proceedings IEEE Virtual Reality (Cat. No. 99CB36316).

[10]  Leonardo Mello Honório,et al.  Construction of Artificial Neural Networks for Pattern Recognition Using a Successive Geometric Segmentation Method , 2014 .

[11]  Tapan Kumar Saha,et al.  Review of modern diagnostic techniques for assessing insulation condition in aged transformers , 2003 .

[12]  Michel Duval,et al.  A review of faults detectable by gas-in-oil analysis in transformers , 2002 .

[13]  Camillo Gentile,et al.  An improved Voronoi-diagram-based neural net for pattern classification , 2001, IEEE Trans. Neural Networks.

[14]  Kit Po Wong,et al.  A Self-Adaptive RBF Neural Network Classifier for Transformer Fault Analysis , 2010, IEEE Transactions on Power Systems.

[15]  Y. M. Kim,et al.  Development of dissolved gas analysis(DGA) expert system using new diagnostic algorithm for oil-immersed transformers , 2012, 2012 IEEE International Conference on Condition Monitoring and Diagnosis.

[16]  Cheng Haozhong,et al.  Fault diagnosis of power transformer based on multi-layer SVM classifier , 2005 .

[17]  Tereza Cristina B N Assuncao,et al.  Classification of the Power Transformers using Dissolved Gas Analysis , 2010 .

[18]  Q.H. Wu,et al.  Transformer Dissolved Gas Analysis Using Least Square Support Vector Machine and Bootstrap , 2006, 2007 Chinese Control Conference.

[19]  Lakhmi C. Jain,et al.  Recent Advances in Pattern Classification , 2012, Computational Intelligence Paradigms in Advanced Pattern Classification.

[20]  M. H. Wang,et al.  A Novel Extension Method for Transformer Fault Diagnosis , 2002, IEEE Power Engineering Review.

[21]  J. L. Guardado,et al.  A Comparative Study of Neural Network Efficiency in Power Transformers Diagnosis Using Dissolved Gas Analysis , 2001, IEEE Power Engineering Review.

[22]  B. Silverman Density estimation for statistics and data analysis , 1986 .

[23]  G.B. Gharehpetian,et al.  Modeling and detection of transformer internal incipient fault during impulse test , 2008, IEEE Transactions on Dielectrics and Electrical Insulation.

[24]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machine Classifiers , 1999, Neural Processing Letters.

[25]  M. Duval,et al.  Dissolved gas analysis: It can save your transformer , 1989, IEEE Electrical Insulation Magazine.

[26]  Khaled Elleithy,et al.  Technological Developments in Networking, Education and Automation , 2010 .