A cognitive system for fault prognosis in power transformers

Abstract The power transformer is one of the most critical and expensive equipments in an electric power system. If it is out of service in an unexpected way, the damage for both society and electric utilities is very significant. Over the last decades, many computational tools have been developed to monitor the ‘health’ of such an important equipment. The classification of incipient faults in power transformers via Dissolved Gas Analysis (DGA) is, for instance, a very well known technique for this purpose. In this paper we present an intelligent system based on cognitive systems for fault prognosis in power transformers. The proposed system combines both evolutionary and connectionist mechanisms into a hybrid model that can be an essential tool in the development of a predictive maintenance technology, to anticipate when any equipment fault might occur and to prevent or reduce unplanned reactive maintenance. The proposed procedure has been applied to real databases derived from chromatographic tests of power transformers found in the literature. The obtained results are fully described showing the feasibility and validity of the new methodology. The proposed system can help Transformer Predictive Maintenance programmes offering a low cost and highly flexible solution for fault prognosis.

[1]  Joseph Mathew,et al.  Rotating machinery prognostics. State of the art, challenges and opportunities , 2009 .

[2]  M. Pecht,et al.  Review of offshore wind turbine failures and fault prognostic methods , 2012, Proceedings of the IEEE 2012 Prognostics and System Health Management Conference (PHM-2012 Beijing).

[3]  Sung-wook Kim,et al.  New methods of DGA diagnosis using IEC TC 10 and related databases Part 1: application of gas-ratio combinations , 2013, IEEE Transactions on Dielectrics and Electrical Insulation.

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

[5]  Dilip Kumar,et al.  Wishbone bus Architecture - A Survey and Comparison , 2012, VLSIC 2012.

[6]  Emiliano Sisinni,et al.  Fast, Versatile, and Low-Cost Interface Circuit for Electrochemical and Resistive Gas Sensor , 2014, IEEE Sensors Journal.

[7]  Pavlos S. Georgilakis,et al.  A novel validated solution for lightning and surge protection of distribution transformers , 2014 .

[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]  Thomas Bäck,et al.  Evolutionary algorithms in theory and practice - evolution strategies, evolutionary programming, genetic algorithms , 1996 .

[10]  Graham Williams,et al.  Conference on Electrical Insulation and Dielectric Phenomena , 1982, IEEE Transactions on Electrical Insulation.

[11]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[12]  Anderson Michael,et al.  AAAI Fall Symposium , 2005 .

[13]  Wei Zhan,et al.  Development of a Low-Cost Self-Diagnostic Module for Oil-Immerse Forced-Air Cooling Transformers , 2015, IEEE Transactions on Power Delivery.

[14]  J. L. Johnson,et al.  Gas Evolution From Transformer Oils Under High-Voltage Stress , 1965 .

[15]  Pavlos S. Georgilakis.  Spotlight on Modern Transformer Design , 2009 .

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

[17]  V.G. Arakelian,et al.  The long way to the automatic chromatographic analysis of gases dissolved in insulating oil , 2004, IEEE Electrical Insulation Magazine.

[18]  Yann-Chang Huang,et al.  Dissolved gas analysis of mineral oil for power transformer fault diagnosis using fuzzy logic , 2013, IEEE Transactions on Dielectrics and Electrical Insulation.

[19]  T. Brescia,et al.  A fuzzy-logic approach to preventive maintenance of critical power transformers , 2009 .

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

[21]  Mokhtar Shasadeghi,et al.  Fault prognosis in power transformers using adaptive-network-based fuzzy inference system , 2014, J. Intell. Fuzzy Syst..

[22]  Yilu Liu,et al.  Wavelet Networks in Power Transformers Diagnosis Using Dissolved Gas Analysis , 2009, IEEE Transactions on Power Delivery.

[23]  V. M. Catterson.  Prognostic modeling of transformer aging using Bayesian particle filtering , 2014, 2014 IEEE Conference on Electrical Insulation and Dielectric Phenomena (CEIDP).

[24]  Andrew Kusiak,et al.  The prediction and diagnosis of wind turbine faults , 2011 .

[25]  Chengrong Li,et al.  Data Requisites for Transformer Statistical Lifetime Modelling—Part I: Aging-Related Failures , 2013, IEEE Transactions on Power Delivery.

[26]  Jeng-Shyang Pan,et al.  Fourth International Conference on Innovative, Computing, Information and Control , 2009 .

[27]  Kimon P. Valavanis,et al.  A Systematic Stochastic Petri Net Based Methodology for Transformer Fault Diagnosis and Repair Actions , 2006, J. Intell. Robotic Syst..

[28]  Fu Wan,et al.  Using a sensitive optical system to analyze gases dissolved in samples extracted from transformer oil , 2014, IEEE Electrical Insulation Magazine.

[29]  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.

[30]  A Kusiak,et al.  A Data-Driven Approach for Monitoring Blade Pitch Faults in Wind Turbines , 2011, IEEE Transactions on Sustainable Energy.

[31]  Weigen Chen,et al.  Fault diagnostic method of power transformers based on hybrid genetic algorithm evolving wavelet neural network , 2008 .

[32]  Noureddine Zerhouni,et al.  Data-driven prognostic method based on Bayesian approaches for direct remaining useful life prediction , 2016, J. Intell. Manuf..

[33]  Pavlos S. Georgilakis,et al.  Condition monitoring and assessment of power transformers using computational intelligence. W.H. Tang, Q.H. Wu. Springer, London (2011). , 2011 .

[34]  Yu Sun,et al.  Forecasting dissolved gases content in power transformer oil based on support vector machine with genetic algorithm , 2008 .

[35]  S. Terry,et al.  A gas chromatographic air analyzer fabricated on a silicon wafer , 1979, IEEE Transactions on Electron Devices.

[36]  Lijun Yang,et al.  Forecasting dissolved gases content in power transformer oil based on weakening buffer operator and least square support vector machine–Markov , 2012 .

[37]  E. P. Dadios,et al.  A hybrid algorithm based on neural-fuzzy system for interpretation of dissolved gas analysis in power transformers , 2012, TENCON 2012 IEEE Region 10 Conference.

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

[39]  Donald F. Specht,et al.  A general regression neural network , 1991, IEEE Trans. Neural Networks.

[40]  Arnd Schirrmann,et al.  Making use of prognostics health management information for aerospace spare components logistics network optimisation , 2011, Comput. Ind..

[41]  Jiawei Han,et al.  Machine Learning and Knowledge Discovery for Engineering Systems Health Management , 2011 .

[42]  N. B. Grover,et al.  A Gas Chromatographic Air Analyzer Fabricated on a Silicon Wafer , 1979 .

[43]  S. Seifeddine,et al.  Power transformer fault diagnosis based on dissolved gas analysis by artificial neural network , 2012, 2012 First International Conference on Renewable Energies and Vehicular Technology.

[44]  P. Zylka,et al.  Electrochemical gas sensors can supplement chromatography-based DGA , 2005 .

[45]  Q. H. Wu,et al.  Condition Monitoring and Assessment of Power Transformers Using Computational Intelligence , 2011 .

[46]  Frank L. Lewis,et al.  Intelligent Fault Diagnosis and Prognosis for Engineering Systems , 2006 .

[47]  Ieee Standards Board.  IEEE guide for the interpretation of gases generated in oil-immersed transformers , 1992 .

[48]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[49]  Jay Lee,et al.  Design of a reconfigurable prognostics platform for machine tools , 2010, Expert Syst. Appl..

[50]  João A. Vasconcelos,et al.  Application of neural networks in the classification of incipient faults in power transformers: A study of case , 2011, The 2011 International Joint Conference on Neural Networks.

[51]  Feng Zhao,et al.  A decision tree approach for power transformer insulation fault diagnosis , 2008, 2008 7th World Congress on Intelligent Control and Automation.

[52]  Q. Henry Wu,et al.  Power Transformer Fault Classification Based on Dissolved Gas Analysis by Implementing Bootstrap and Genetic Programming , 2009, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[53]  João A. Vasconcelos,et al.  A Comparative Study of the Application of Neural Networks and Decision Trees in the Classification of Incipient Faults in Power Transformers , 2016 .

[54]  Taner Bilgiç,et al.  Predictive Maintenance using Dynamic Probabilistic Networks , 2006, Probabilistic Graphical Models.

[55]  Frank K. Tittel,et al.  Compact QEPAS sensor for trace methane and ammonia detection in impure hydrogen , 2012 .

[56]  R. Naresh,et al.  An Integrated Neural Fuzzy Approach for Fault Diagnosis of Transformers , 2008, IEEE Transactions on Power Delivery.

[57]  Tsair-Fwu Lee,et al.  Fault Diagnosis of Power Transformers Using SVM/ANN with Clonal Selection Algorithm for Features and Kernel Parameters Selection , 2006, First International Conference on Innovative Computing, Information and Control - Volume I (ICICIC'06).

[58]  Kai Goebel,et al.  A Survey of Artificial Intelligence for Prognostics , 2007, AAAI Fall Symposium: Artificial Intelligence for Prognostics.