Classification of EMI discharge sources using time–frequency features and multi-class support vector machine

Abstract This paper introduces the first application of feature extraction and machine learning to electromagnetic interference (EMI) signals for discharge sources classification in high voltage power generating plants. This work presents an investigation on signals that represent different discharge sources, which are measured using EMI techniques from operating electrical machines within power plant. The analysis involves time–frequency image calculation of EMI signals using general linear chirplet analysis (GLCT) which reveals both time and frequency varying characteristics. Histograms of uniform local binary patterns (LBP) are implemented as a feature reduction and extraction technique for the classification of discharge sources using multi-class support vector machine (MCSVM). The novelty that this paper introduces is the combination of GLCT and LBP applications to develop a new feature extraction algorithm applied to EMI signals classification. The proposed algorithm is demonstrated to be successful with excellent classification accuracy being achieved. For the first time, this work transfers expert's knowledge on EMI faults to an intelligent system which could potentially be exploited to develop an automatic condition monitoring system.

[1]  Alan Nesbitt,et al.  Trending of EMI data over years and overnight , 2014, 2014 IEEE Electrical Insulation Conference (EIC).

[2]  Matti Pietikäinen,et al.  Robust Texture Classification by Subsets of Local Binary Patterns , 2000, ICPR.

[3]  Xiaodong Zheng,et al.  Spectral decomposition using general linear chirplet transform , 2017 .

[4]  J M Lesniak,et al.  Comparative evaluation of support vector machine classification for computer aided detection of breast masses in mammography , 2012, Physics in medicine and biology.

[5]  Magdy M. A. Salama,et al.  Partial discharge pattern classification using the fuzzy decision tree approach , 2005, IEEE Transactions on Instrumentation and Measurement.

[6]  B. K. Julsing,et al.  Face Recognition with Local Binary Patterns , 2012 .

[7]  José M. Vallejo,et al.  Condition assessment of electrical apparatus with EMI diagnostics , 2015, 2015 IEEE Petroleum and Chemical Industry Committee Conference (PCIC).

[8]  F. H. Kreuger.  Industrial High Voltage: 4. Coordinating, 5. Testing, 6. Measuring , 1992 .

[9]  Ayman H. El-Hag,et al.  Toward High-Accuracy Estimation of Partial Discharge Location , 2016, IEEE Transactions on Instrumentation and Measurement.

[10]  Hazlee Azil Illias,et al.  Partial discharge classifications: Review of recent progress , 2015 .

[11]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[12]  J. Stein,et al.  Assessment of Partial Discharge and Electromagnetic Interference On-Line Testing of Turbine-Driven Generator Stator Winding Insulation Systems , 2003 .

[13]  Bo-Suk Yang,et al.  Support vector machine in machine condition monitoring and fault diagnosis , 2007 .

[14]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[15]  Guillermo Robles,et al.  Multiple partial discharge source discrimination with multiclass support vector machines , 2016, Expert Syst. Appl..

[16]  Eduardo Fontana,et al.  Optical Detection of Partial Discharges on Insulator Strings of High-Voltage Transmission Lines , 2009, IEEE Transactions on Instrumentation and Measurement.

[17]  Clyde V. Maughan.  Electromagnetic interference (EMI) testing of electrical equipment , 2011, 2011 Electrical Insulation Conference (EIC)..

[18]  Eva Rajo-Iglesias,et al.  Antenna Parametrization for the Detection of Partial Discharges , 2013, IEEE Transactions on Instrumentation and Measurement.

[19]  Ayman H. El-Hag,et al.  A Novel Bias Detection Technique for Partial Discharge Localization in Oil Insulation System , 2016, IEEE Transactions on Instrumentation and Measurement.

[20]  James E. Timperley.  Detection of insulation deterioration through electrical spectrum analysis , 1983, 1983 EIC 6th Electrical/Electronical Insulation Conference.

[21]  J. E. Timperley.  Comparison of PDA and EMI diagnostic measurements [for machine insulation] , 2002, Conference Record of the the 2002 IEEE International Symposium on Electrical Insulation (Cat. No.02CH37316).

[22]  Ju Tang,et al.  Feature extraction and recognition of UHF partial discharge signals in GIS based on dual‐tree complex wavelet transform , 2009 .

[23]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[24]  James E. Timperley.  Generator Condition Assessment Through EMI Diagnostics , 2008 .

[25]  Santosh Chapaneri,et al.  Exploring Textural Features for Automatic Music Genre Classification , 2015, 2015 International Conference on Computing Communication Control and Automation.

[26]  Sridhar Krishnan,et al.  Combining Temporal Features by Local Binary Pattern for Acoustic Scene Classification , 2017, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[27]  Venizelos Efthymiou,et al.  Feature extraction of partial discharge signals using the wavelet packet transform and classification with a probabilistic neural network , 2010 .

[28]  J.E. Timperley.  Audio spectrum analysis of EMI patterns , 2007, 2007 Electrical Insulation Conference and Electrical Manufacturing Expo.

[29]  Julio E. Posada-Roman,et al.  Instrumentation System for Location of Partial Discharges Using Acoustic Detection With Piezoelectric Transducers and Optical Fiber Sensors , 2014, IEEE Transactions on Instrumentation and Measurement.

[30]  M Esfahanian,et al.  Using local binary patterns as features for classification of dolphin calls. , 2013, The Journal of the Acoustical Society of America.

[31]  M. Melamed.  Detection , 2021, SETI: Astronomy as a Contact Sport.

[32]  Tao Hong,et al.  Detection and classification of partial discharge using a feature decomposition-based modular neural network , 2001, IEEE Trans. Instrum. Meas..

[33]  L. Satish,et al.  Artificial neural networks for recognition of 3-d partial discharge patterns , 1994 .

[34]  James E. Timperley,et al.  Electric Generation Condition Assessment With Electromagnetic Interference Analysis , 2018, IEEE Transactions on Industry Applications.

[35]  G. B. Kumbhar,et al.  Detection, Measurement, and Classification of Partial Discharge in a Power Transformer: Methods, Trends, and Future Research , 2018 .

[36]  Thomas P. Trappenberg,et al.  A Heuristic for Free Parameter Optimization with Support Vector Machines , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[37]  B. Kordi,et al.  On-line monitoring of partial discharges in a HVDC station environment , 2012, IEEE Transactions on Dielectrics and Electrical Insulation.

[38]  Kai Ming Ting,et al.  Confusion Matrix , 2010, Encyclopedia of Machine Learning and Data Mining.

[39]  Min Wu,et al.  An overview of state-of-the-art partial discharge analysis techniques for condition monitoring , 2015, IEEE Electrical Insulation Magazine.

[40]  Matti Pietikäinen,et al.  Face Recognition with Local Binary Patterns , 2004, ECCV.

[41]  P. Lewin,et al.  Comparison of on-line partial discharge detection methods for HV cable joints , 2002 .

[42]  Chih-Jen Lin,et al.  A comparison of methods for multiclass support vector machines , 2002, IEEE Trans. Neural Networks.

[43]  Gang Yu,et al.  General linear chirplet transform , 2016 .

[44]  M. Talib,et al.  Identification of Different Types of Partial Discharge Sources from Acoustic Emission Signals in the Time-Frequency Representation , 2006, 2006 IEEE International Power and Energy Conference.

[45]  Nicholas W. D. Evans,et al.  Acoustic context recognition using local binary pattern codebooks , 2015, 2015 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA).

[46]  Luiz Eduardo Soares de Oliveira,et al.  Music genre classification using LBP textural features , 2012, Signal Process..

[47]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[48]  Gordon Morison,et al.  Classification of partial discharge EMI conditions using permutation entropy-based features , 2017, 2017 25th European Signal Processing Conference (EUSIPCO).

[49]  Ramy Hussein,et al.  Robust Feature Extraction and Classification of Acoustic Partial Discharge Signals Corrupted With Noise , 2017, IEEE Transactions on Instrumentation and Measurement.