Diagnosing Faults in Power Transformers With Autoassociative Neural Networks and Mean Shift

This paper presents a new approach to incipient fault diagnosis in power transformers, based on the results of dissolved gas analysis. A set of autoassociative neural networks or autoencoders is trained, so that each becomes tuned with a particular fault mode or no fault condition. The scarce data available forms clusters that are densified using an Information Theoretic Mean Shift algorithm, allowing all real data to be used in the validation process. Then, a parallel model is built where the autoencoders compete with one another when a new input vector is entered and the closest recognition is taken as the diagnosis sought. A remarkable accuracy of 100% is achieved with this architecture, in a validation data set using all real information available.

[1]  Yann-Chang Huang,et al.  Evolving neural nets for fault diagnosis of power transformers , 2003 .

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

[3]  Vladimiro Miranda,et al.  Transformer fault diagnosis based on autoassociative neural networks , 2011, 2011 16th International Conference on Intelligent System Applications to Power Systems.

[4]  V. Miranda,et al.  Knowledge discovery in neural networks with application to transformer failure diagnosis , 2005, IEEE Transactions on Power Systems.

[5]  R.J. Marks,et al.  Implicit learning in autoencoder novelty assessment , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[6]  Yilu Liu,et al.  Rough set and fuzzy wavelet neural network integrated with least square weighted fusion algorithm based fault diagnosis research for power transformers , 2008 .

[7]  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.

[8]  A. de Medeiros Martins,et al.  Information Theoretic Mean Shift Algorithm , 2006, 2006 16th IEEE Signal Processing Society Workshop on Machine Learning for Signal Processing.

[9]  Terence D. Sanger,et al.  Optimal unsupervised learning in a single-layer linear feedforward neural network , 1989, Neural Networks.

[10]  José Carlos Príncipe,et al.  Advanced search algorithms for information-theoretic learning with kernel-based estimators , 2004, IEEE Transactions on Neural Networks.

[11]  José Carlos Príncipe,et al.  Mean shift: An information theoretic perspective , 2009, Pattern Recognit. Lett..

[12]  P. J. Griffin,et al.  A combined ANN and expert system tool for transformer fault diagnosis , 1998 .

[13]  Sung-Soo Kim,et al.  Diagnosis of Power Transformer using Fuzzy Clustering and Radial Basis Function Neural Network , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[14]  Xiao-Yun Sun,et al.  The study of fault diagnosis model of DGA for oil-immersed transformer based on fuzzy means Kernel clustering and SVM multi-class object simplified structure , 2008, 2008 International Conference on Machine Learning and Cybernetics.

[15]  E. Parzen.  On Estimation of a Probability Density Function and Mode , 1962 .

[16]  V. Miranda,et al.  Improving the IEC table for transformer failure diagnosis with knowledge extraction from neural networks , 2005, IEEE Transactions on Power Delivery.

[17]  Li Honglei,et al.  Wavelet ANN based transformer fault diagnosis using gas-in-oil analysis , 2000, Proceedings of the 6th International Conference on Properties and Applications of Dielectric Materials (Cat. No.00CH36347).

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

[19]  Hong-Tzer Yang,et al.  Adaptive fuzzy diagnosis system for dissolved gas analysis of power transformers , 1999 .

[20]  Meng-Hui Wang,et al.  A novel clustering algorithm based on the extension theory and genetic algorithm , 2009, Expert Syst. Appl..

[21]  Raj Aggarwal,et al.  Analysis of power transformer dissolved gas data using the self-organizing map , 2003 .

[22]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[23]  Sheng-wei Fei,et al.  Fault diagnosis of power transformer based on support vector machine with genetic algorithm , 2009, Expert Syst. Appl..

[24]  Khmais Bacha,et al.  Power transformer fault diagnosis based on dissolved gas analysis by support vector machine , 2012 .

[25]  Terrence J. Sejnowski,et al.  Sex Recognition from Faces Using Neural Networks , 1995 .

[26]  Nor Ashidi Mat Isa,et al.  Clustered-Hybrid Multilayer Perceptron network for pattern recognition application , 2011, Appl. Soft Comput..

[27]  Kevin Tomsovic,et al.  A fuzzy information approach to integrating different transformer diagnostic methods , 1993 .

[28]  J. Príncipe,et al.  Information-Theoretic Learning Using Renyi's Quadratic Entropy , 1999 .

[29]  Nathalie Japkowicz,et al.  Nonlinear Autoassociation Is Not Equivalent to PCA , 2000, Neural Computation.

[30]  W.H. Tang,et al.  A Probabilistic Classifier for Transformer Dissolved Gas Analysis With a Particle Swarm Optimizer , 2008, IEEE Transactions on Power Delivery.

[31]  Deniz Erdogmus,et al.  Generalized information potential criterion for adaptive system training , 2002, IEEE Trans. Neural Networks.

[32]  M. K. Fleming,et al.  Categorization of faces using unsupervised feature extraction , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

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