Bushing diagnosis using artificial intelligence and dissolved gas analysis

This dissertation is a study of artificial intelligence for diagnosing the condition of high voltage bushings. The techniques include neural networks, genetic algorithms, fuzzy set theory, particle swarm optimisation, multi-classifier systems, factor analysis, principal component analysis, multidimensional scaling, data-fusion techniques, automatic relevance determination and autoencoders. The classification is done using Dissolved Gas Analysis (DGA) data based on field experience together with criteria from IEEEc57.104 and IEC60599. A review of current literature showed that common methods for the diagnosis of bushings are: partial discharge, DGA, tan(dielectric dissipation factor), water content in oil, dielectric strength of oil, acidity level (neutralisation value), visual analysis of sludge in suspension, colour of the oil, furanic content, degree of polymerisation (DP), strength of the insulating paper, interfacial tension or oxygen content tests. All the methods have limitations in terms of time and accuracy in decision making. The fact that making decisions using each of these methods individually is highly subjective, also the huge size of the data base of historical data, as well as the loss of skills due to retirement of experienced technical staff, highlights the need for an automated diagnosis tool that integrates information from the many sensors and recalls the historical decisions and learns from new information. Three classifiers that are compared in this analysis are radial basis functions (RBF), multiple layer perceptrons (MLP) and support vector machines (SVM). In this work 60699 bushings were classified based on ten criteria. Classification was done based on a majority vote. The work proposes the application of neural networks with particle swarm optimisation (PSO) and genetic algorithms (GA) to compensate for missing data in classifying high voltage bushings. The work also proposes the application of fuzzy set theory (FST) to diagnose the condition of high voltage bushings. The relevance and redundancy detection methods were able to prune the redundant measured variables and accurately diagnose the condition of the bushing with fewer variables. Experimental results from bushings that were evaluated in the field verified the simulations. The results of this work can help to develop real-time monitoring and decision making tools that combine information from chemical, electrical and mechanical measurements taken from bushings.

[1]  Kenneth E. Barner,et al.  Fuzzy ranking: theory and applications , 2000, Signal Process..

[2]  S. Gottwald,et al.  Fuzzy sets, fuzzy logic, fuzzy methods with applications , 1995 .

[3]  Kenneth Levenberg.  A METHOD FOR THE SOLUTION OF CERTAIN NON – LINEAR PROBLEMS IN LEAST SQUARES , 1944 .

[4]  M. Kramer.  Nonlinear principal component analysis using autoassociative neural networks , 1991 .

[5]  James Llinas,et al.  Handbook of Multisensor Data Fusion , 2001 .

[6]  J. Ross Quinlan,et al.  Unknown Attribute Values in Induction , 1989, ML.

[7]  D. O. Hebb,et al.  The organization of behavior , 1988 .

[8]  B. L. Betechuoh.  Optimal selection of stocks using computational intelligence methods , 2006 .

[9]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[10]  Lefteri H. Tsoukalas,et al.  Fuzzy and neural approaches in engineering , 1997 .

[11]  G. Stevens,et al.  Microstructural characterization of XLPE electrical insulation in power cables: determination of void size distributions using TEM , 2003 .

[12]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[13]  Keinosuke Fukunaga,et al.  Introduction to Statistical Pattern Recognition , 1972 .

[14]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[15]  Michael Weber,et al.  Independent Component Analysis of Incomplete Data , 1999 .

[16]  Ebrahim H. Mamdani,et al.  An Experiment in Linguistic Synthesis with a Fuzzy Logic Controller , 1999, Int. J. Hum. Comput. Stud..

[17]  Thokozani Majozi,et al.  A combined fuzzy set theory and MILP approach in integration of planning and scheduling of batch plants - Personnel evaluation and allocation , 2005, Comput. Chem. Eng..

[18]  Salwa Ammar,et al.  Applying fuzzy-set theory to performance evaluation , 2000 .

[19]  W. T. Illingworth,et al.  Practical guide to neural nets , 1991 .

[20]  Sivaji Chakravorti,et al.  Investigations on the usefulness of an expert system for impulse fault analysis in distribution transformers , 2003 .

[21]  Lotfi A. Zadeh,et al.  Outline of a New Approach to the Analysis of Complex Systems and Decision Processes , 1973, IEEE Trans. Syst. Man Cybern..

[22]  J. Kuffel,et al.  High Voltage Engineering: Fundamentals , 1984 .

[23]  Ian T. Nabney,et al.  Netlab: Algorithms for Pattern Recognition , 2002 .

[24]  S. Gunn.  Support Vector Machines for Classification and Regression , 1998 .

[25]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[26]  A. E. Maxwell,et al.  Factor Analysis as a Statistical Method. , 1964 .

[27]  G. Seber.  Multivariate observations / G.A.F. Seber , 1983 .

[28]  T. Marwala,et al.  Cost benefit of using a committee of parallel neural networks for bushing diagnostics , 2005, 2005 IEEE Power Engineering Society Inaugural Conference and Exposition in Africa.

[29]  Hans Michael Muhr,et al.  Transformer Diagnostics: Common Used and New Methods , 2006 .

[30]  Sven Behnke,et al.  Competitive neural trees for pattern classification , 1998, IEEE Trans. Neural Networks.

[31]  T. Marwala,et al.  An application of SVM, RBF and MLP with ARD on bushings , 2004, IEEE Conference on Cybernetics and Intelligent Systems, 2004..

[32]  B. Everitt,et al.  Applied Multivariate Data Analysis. , 1993 .

[33]  C. Malsburg,et al.  How patterned neural connections can be set up by self-organization , 1976, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[34]  Zbigniew Michalewicz,et al.  Genetic Algorithms + Data Structures = Evolution Programs , 1996, Springer Berlin Heidelberg.

[35]  S. Boggs,et al.  Defect tolerance of solid dielectric transmission class cable , 2005, IEEE Electrical Insulation Magazine.

[36]  Martin Fodslette Meiller.  A Scaled Conjugate Gradient Algorithm for Fast Supervised Learning , 1993 .

[37]  H. Bourlard,et al.  Auto-association by multilayer perceptrons and singular value decomposition , 1988, Biological Cybernetics.

[38]  S. M. Dhlamini,et al.  Bushing diagnostics using an ensemble of parallel neural networks , 2005, Proceedings of 2005 International Symposium on Electrical Insulating Materials, 2005. (ISEIM 2005)..

[39]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[40]  J. P. Holman,et al.  Experimental methods for engineers , 1971 .

[41]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[42]  Carl G. Looney,et al.  Pattern recognition using neural networks: theory and algorithms for engineers and scientists , 1997 .

[43]  R. Rummel.  Applied Factor Analysis , 1970 .

[44]  E. Nasser.  Fundamentals of gaseous ionization and plasma electronics , 1971 .

[45]  Sizwe M. Dblamini,et al.  Bushing monitoring using MLP and RBF , 2004 .

[46]  S. M. Dhlamini,et al.  Condition Monitoring of HV Bushings in the Presence of Missing Data Using Evolutionary Computing , 2007, ArXiv.

[47]  Terrence J. Sejnowski,et al.  An Information-Maximization Approach to Blind Separation and Blind Deconvolution , 1995, Neural Computation.

[48]  Zhenyuan Wang,et al.  Artificial Intelligence Applications in the Diagnosis of Power Transformer Incipient Faults , 2000 .

[49]  Michael I. Jordan,et al.  Mixture models for learning from incomplete data , 1997, COLT 1997.

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

[51]  Tshilidzi Marwala.  Probabilistic Fault Identification Using a Committee of Neural Networks and Vibration Data , 2001 .

[52]  Tshilidzi Marwala,et al.  The use of genetic algorithms and neural networks to approximate missing data in database , 2005, IEEE 3rd International Conference on Computational Cybernetics, 2005. ICCC 2005..

[53]  P.H.F. Morshuis,et al.  Transition from streamer to Townsend mechanisms in dielectric voids , 1990 .

[54]  Jerome H. Friedman,et al.  A Recursive Partitioning Decision Rule for Nonparametric Classification , 1977, IEEE Transactions on Computers.

[55]  Vojislav Kecman,et al.  Learning and Soft Computing: Support Vector Machines, Neural Networks, and Fuzzy Logic Models , 2001 .

[56]  Slobodan Skundric,et al.  Monitoring and diagnostics of power transformer insulation , 2006 .

[57]  Eric Kubica,et al.  Modelling balance and posture control mechanisms of the upper body using conventional and fuzzy techniques , 1995 .

[58]  Ian T. Jolliffe,et al.  Applied Factor Analysis in the Natural Sciences. , 1994 .

[59]  Zbigniew Michalewicz,et al.  Genetic Algorithms + Data Structures = Evolution Programs , 1992, Artificial Intelligence.

[60]  H. Deutsch.  Principle Component Analysis , 2004 .

[61]  Peter S. Pacheco.  Parallel programming with MPI , 1996 .

[62]  S. M. Dhlamini,et al.  Fuzzy and Multilayer Perceptron for Evaluation of HV Bushings , 2006, 2006 IEEE International Conference on Systems, Man and Cybernetics.

[63]  Dorian Pyle,et al.  Data Preparation for Data Mining , 1999 .

[64]  Jiawei Han,et al.  Data Mining: Concepts and Techniques , 2000 .

[65]  Michio Sugeno,et al.  Industrial Applications of Fuzzy Control , 1985 .

[66]  Lotfi A. Zadeh,et al.  Fuzzy Sets , 1996, Inf. Control..

[67]  George Bojadziev,et al.  Fuzzy Sets, Fuzzy Logic, Applications , 1996, Advances in Fuzzy Systems - Applications and Theory.

[68]  D. Bartholomew.  Latent Variable Models And Factor Analysis , 1987 .

[69]  Man-Wai Mak,et al.  Speaker identification using multilayer perceptrons and radial basis function networks , 1994, Neurocomputing.

[70]  S. M. Dhlamini,et al.  Sensor Failure Compensation Techniques for HV Bushing Monitoring using Evolutionary Computing , 2005 .