A new thermographic NDT for condition monitoring of electrical components using ANN with confidence level analysis.

Infrared thermography technology is one of the most effective non-destructive testing techniques for predictive faults diagnosis of electrical components. Faults in electrical system show overheating of components which is a common indicator of poor connection, overloading, load imbalance or any defect. Thermographic inspection is employed for finding such heat related problems before eventual failure of the system. However, an automatic diagnostic system based on artificial neural network reduces operating time, human efforts and also increases the reliability of system. In the present study, statistical features and artificial neural network (ANN) with confidence level analysis are utilized for inspection of electrical components and their thermal conditions are classified into two classes namely normal and overheated. All the features extracted from images do not produce good performance. Features having low performance reduce the diagnostic performance. The study reveals the performance of each feature individually for selecting the suitable feature set. In order to find the individual feature performance, each feature of thermal image was used as input for neural network and the classification of condition types were used as output target. The multilayered perceptron network using Levenberg-Marquardt training algorithm was used as classifier. The performances were determined in terms of percentage of accuracy, specificity, sensitivity, false positive and false negative. After selecting the suitable features, the study introduces the intelligent diagnosis system using suitable features as inputs of neural network. Finally, confidence percentage and confidence level were used to find out the strength of the network outputs for condition monitoring. The experimental result shows that multilayered perceptron network produced 79.4% of testing accuracy with 43.60%, 12.60%, 21.40, 9.20% and 13.40% highest, high, moderate, low and lowest confidence level respectively.

[1]  Soib Taib,et al.  Suitable features selection for monitoring thermal condition of electrical equipment using infrared thermography , 2013 .

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

[3]  Kolla,et al.  Identifying three-phase induction motor faults using artificial neural networks , 2000, ISA transactions.

[4]  H.J.A. Martins,et al.  Intelligent Thermographic Diagnostic Applied to Surge Arresters: A New Approach , 2009, IEEE Transactions on Power Delivery.

[5]  Kee Tung. Wong,et al.  Texture features for image classification and retrieval. , 2002 .

[6]  Z. Azmat,et al.  Infrared thermography and its role in rural utility environment , 2005, Rural Electric Power Conference, 2005.

[7]  Javad Haddadnia,et al.  Intelligent fault detection of electrical equipment in ground substations using thermo vision technique , 2010, 2010 2nd International Conference on Mechanical and Electronics Engineering.

[8]  Niancang Hou.  The infrared thermography diagnostic technique of high-voltage electrical equipments with internal faults , 1998, POWERCON '98. 1998 International Conference on Power System Technology. Proceedings (Cat. No.98EX151).

[9]  M. Florkowski,et al.  Thermography based diagnostics of power equipment , 2001 .

[10]  Shutao Zhao,et al.  HV Power Equipment Diagnosis Based on Infrared Imaging Analyzing , 2006, 2006 International Conference on Power System Technology.

[11]  Soib Taib,et al.  A semi-automatic approach for thermographic inspection of electrical installations within buildings , 2012 .

[12]  Michal Kolcun.  IMPROVING RELIABILITY AND DECREASING LOSSES OF ELECTRICAL SYSTEM WITH INFRARED THERMOGRAPHY , 2008 .

[13]  R. A. Epperly,et al.  A tool for reliability and safety: predict and prevent equipment failures with thermography , 1997, Record of Conference Papers. IEEE Industry Applications Society 44th Annual Petroleum and Chemical Industry Conference.

[14]  Yang Cao,et al.  Infrared technology in the fault diagnosis of substation equipment , 2008, 2008 China International Conference on Electricity Distribution.

[15]  Fevzullah Temurtas,et al.  A comparative study on thyroid disease diagnosis using neural networks , 2009, Expert Syst. Appl..

[16]  Toshimitsu Ishii,et al.  On the NDT and E for the diagnosis of defects using infrared thermography , 1999 .

[17]  Ken-ichi Funahashi,et al.  On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

[18]  Soib Taib,et al.  Application of infrared thermography for predictive/preventive maintenance of thermal defect in electrical equipment , 2013 .

[19]  John E. Gilley,et al.  Artificial Neural Network estimation of soil erosion and nutrient concentrations in runoff from land application areas , 2008 .

[20]  Noraliza Hamzah,et al.  Internal fault classification using Artificial Neural Network , 2010, 2010 4th International Power Engineering and Optimization Conference (PEOCO).

[21]  Michael Alan Kregg.  Benefits of using infrared thermography in utility substations , 2004, SPIE Defense + Commercial Sensing.

[22]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[23]  M.K. Sanders,et al.  National Fire Protection Association 70B Recommended Practice for Electrical Equipment Maintenance 2006 Edition , 2007, 2007 IEEE/IAS Industrial & Commercial Power Systems Technical Conference.

[24]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

[25]  Constantinos A. Balaras,et al.  Infrared thermography for building diagnostics , 2002 .

[26]  Shahid Kabir.  Imaging-based detection of AAR induced map-crack damage in concrete structure , 2010 .

[27]  D. Titman.  Applications of thermography in non-destructive testing of structures , 2001 .

[28]  Xavier Maldague,et al.  Applications of infrared thermography in nondestructive evaluation , 2000 .

[29]  T. Jayakumar,et al.  Medical applications of infrared thermography: A review , 2012, Infrared Physics & Technology.

[30]  Leehter Yao,et al.  Automatic Diagnostic System of Electrical Equipment Using Infrared Thermography , 2009, 2009 International Conference of Soft Computing and Pattern Recognition.

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

[32]  Soib Taib,et al.  Recent Progress in Diagnosing the Reliability of Electrical Equipment by Using Infrared Thermography , 2012 .

[33]  A. Ebrahimzadeh,et al.  Control chart pattern recognition using an optimized neural network and efficient features. , 2010, ISA transactions.

[34]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[35]  Boguslaw Wiecek,et al.  Advanced Thermal Image Processing , 2006 .

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

[37]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[38]  Rui Faria,et al.  Thermography as a technique for monitoring early age temperatures of hardening concrete , 2011 .

[39]  Christian Scheuerlein,et al.  Non-destructive testing of Cu solder connections using active thermography , 2012 .

[40]  Thierry Denoeux,et al.  Neural networks for process control and optimization: two industrial applications. , 2003, ISA transactions.

[41]  Paul Gill,et al.  Electrical Power Equipment Maintenance and Testing , 1997 .

[42]  Nor Ashidi Mat Isa,et al.  Suitable features selection for the HMLP and MLP networks to identify the shape of aggregate , 2008 .