Call for Paper - June 2019 Edition
IJCA solicits original research papers for the June 2019 Edition. Last date of manuscript submission is May 20, 2019. Read More

FPGA Realization of Transformer Impulse Fault Classification Scheme based on DWT and LVQ Neural Network

Print
PDF
IJCA Proceedings on National Conference Potential Research Avenues and Future Opportunities in Electrical and Instrumentation Engineering
© 2014 by IJCA Journal
ETEIAC
Year of Publication: 2014
Authors:
Vanamadevi N
S. Santhi
P. Abdul Ameen

Vanamadevi N, S Santhi and Abdul P Ameen. Article: FPGA Realization of Transformer Impulse Fault Classification Scheme based on DWT and LVQ Neural Network. IJCA Proceedings on National Conference Potential Research Avenues and Future Opportunities in Electrical and Instrumentation Engineering ETEIAC:22-29, July 2014. Full text available. BibTeX

@article{key:article,
	author = {Vanamadevi N and S. Santhi and P. Abdul Ameen},
	title = {Article: FPGA Realization of Transformer Impulse Fault Classification Scheme based on DWT and LVQ Neural Network},
	journal = {IJCA Proceedings on National Conference Potential Research Avenues and Future Opportunities in Electrical and Instrumentation Engineering},
	year = {2014},
	volume = {ETEIAC},
	pages = {22-29},
	month = {July},
	note = {Full text available}
}

Abstract

Impulse test is a routine test for transformers and is performed to assess their winding insulation strength. If any fault occur during impulse test, the winding current contain typical signature depending on the nature and type of the faults. Among the various impulse faults the series fault or shunt fault that may occur in the winding needs special attention since it results in heavy damage. This work is dedicated to detection and classification of such faults based on a simulation study conducted on the lumped parameter model of a specially designed 6. 6kV voltage transformer winding. The neutral currents have been recorded with series fault/shunt fault introduced in the ten sections of the winding model simulated using circuit simulation package. These current records are discrete wavelet transformed using the db5 analysis filter bank. The statistical features extracted from the third level approximation are considered for discriminating the defined faults and are classified by training a Learning Vector Quantization (LVQ) network. The clustering of the extracted discrimination features is done using possibilistic fuzzy c means (PFCM) algorithm to obtain voronoi/initial weight vectors required for training the LVQ network. The impulse fault classification achieved with this scheme is satisfactory with 95% accuracy. This scheme is developed using MATLAB. The hardware realization of this scheme is carried out using Xilinx System generator for DSP in Xilinx SPARTAN6 FPGA.

References

  • IEC 60076 – Part IV. (2002). Power transformers. Guide to the lightning impulse and switching impulse testing-Power transformers and Reactors. IEC. Geneva. Switzerland.
  • Chakravorti, S. , Dey, D. ,and Chatterjee, B. (2013). Recent Trends in the Condition Monitoring of Transformers. Power Systems. Springer_Verlag. London.
  • Malewski, R. , and Poulin,B. (1988). Impulse testing of power transformer using the transfer function method. IEEE Transactions on Power Delivery. Vol. 3. 476-489.
  • Satish,L. (1998). Short time Fourier and Wavelet transform for fault detection in power transformers during impulse tests. IEEE proc. sci. meas. technol. vol. 145. NO. 2. 77-84.
  • Purkait,P. , Chakravorti,S. (2002). Time and frequency domain analyses based expert system for impulse fault diagnosis in transformers. IEEE Transaction on dielectric and electrical insulation. vol. 9. no. 3. 433-443.
  • Santhi,S. , Jayashankar,V. , Jagadeesh Kumar, V. (2008). Time frequency analysis method for the detection of winding deformation in transformers during short citcuit test. Instrumentation and Measurement Technology Conference proceedings. Victoria. Vancouver Island. Canada. May(12-15).
  • Rao,M. R,. singh,B. P. (2001). Detection and localization of interturn fault in the HV winding of a power transformer using wavelets. IEEE transactions on dielectrics and electrical insulation, Vol 8. 652-657.
  • Purkait,P. , Chakrovorti,S. (2002). Pattern classification of Impulse faults in transformer by wavelet analysis. IEEE Trans. On Dielectrics and Electrical Insulation. vol. 9. No. 4.
  • Mujtahid Ansari,M. , Patil Bhushan Prataprao. , Dr. Beg,M. A. (2013) Application of Signal Analysis for Fault Diagnosis in Transformer by Discrete Wavelet Transform. International Journal of Engineering Research & Technology (IJERT). Vol. 2 Issue 2.
  • Prema Kumar, N. , Amarnath, J. , Shrivastava,K. D. , Singh,B. P. (2005). Identification of Winding Faults in Power Transformers by Low Voltage Impulse Test and Neutral Current Method using Wavelet Transform Approach. IEEE Trans. On Electrical Insulation and Dielectric Phenomena.
  • Omar A. S. Youssef. (2004). Applications of fuzzy-logic wavelet-based techniques for transformers Inrush currents identification and ique for power system faults classfication. IEEE Conf. on Power systems and exposition. vol. 1. pp 553-55.
  • Vanamadevi N, Santhi S. (2013). Impulse Fault Detection and Classification in power transformers with wavelet and fuzzy based technique. Springer -Recent advancements in System Modeling applications - Lecture Notes in Electrical Engineering. Vol 188. pp. 261-273.
  • Hossam A. Nabwey, E. A. Rady, A. M. Kozae, A. N. Ebady. , Fault Diagnosis of Power Transformer Based on Fuzzy Logic, Rough Set theory and Inclusion Degree Theory. The Online Journal on Power and Energy Engineering (OJPEE). Vol. 1. No. 2.
  • Vanamadevi. N,Arivamudhan. M,Santhi. S. (2008). Detection and Classification of Impulse Faults in transformer using Wavelet Transform and Artificial Neural Network. Proceedings of IEEE. ICSET 2008. Nov 24-27.
  • Paraskar,SR. ,Beg,M. A. ,. Dhole,G. M. (2011). Discrimination between Inrush and Fault in Transformer: ANN Approach. International Journal of Advancements in Technology. Vol 2, No 2.
  • Eric Monmasson and Marcian. N. Cirstea. (2007). FPGA design methodology for industrial control systems-A review. IEEE transactions on industrial electronics, vol. 54. No. 4.
  • Mohammed Bahoura and Hassan Ezzaidi. (2010). Real-Time Implementation of Discrete Wavelet Transform on FPGA. ICSP Proceedings. 191-194.
  • Cabal-Yepez, E. , and Osornio-Rios,R. A. (2009). FPGA-based Online Induction Motor Multiple-fault Detection with Fused FFT and Wavelet Analysis. International conference on Reconfigurable computing and FPGAs. 101-106.
  • Bahoura, M. , and Ezzaidi,H. (2009). FPGA-implementation of a sequential adaptive noise canceller using Xilinx System Generator International Conference on Microelectronic. pp. 213-216.
  • Gavrincea Ciprian. , Tisan Alin. , Doiga Stefan. , Buchman Attila. , FPGA- based discrete Wavelet transform design using MatLab/Simulink. International Symposium for Design and Technology of Electronic Packages, 13th Edition. Baiamare. Romania.
  • Mohamed boubaker. ,Khaled ben khalifa. ,Bernard girau. ,Mohamed dogui and Mohamed hedi bedoui. , (2008). On-line arithmetic based reprogrammable hardware implementation of LVQ neural network for alertness classification. IJCSNS International Journal of computer science and network security. vol. 8 No. 3.
  • Simi P. Valsan and Shanti Swarup, K. (2009). High speed fault classification in power lines:Theory and FPGA based implementation. IEEE Transactions on industrial electronics. vol. 56. No. 5.
  • Grover Fredrick W. (1946) Inductance calculations- working formulas and tables. Dover Publications Inc. New York
  • Simon Haykin. (2006). Neural Networks. A comprehensive foundation. Second Edition. Pretice –Hall. India.