Statistical error tolerances of partial discharge recognition rates.

Mas'ud, Abdullahi Abubakar; Eltayeb, Mohammed E.; Muhammad-Sukki, Firdaus; Bani, Nurul Aini

Abstract

This paper compares the statistical error tolerances of the single neural network (SNN) and the ensemble neural network (ENN) recognition efficiencies, when both the SNN and ENN are applied to recognize partial discharge (PD) patterns. Statistical fingerprints from the phased and amplitude resolved patterns of PDs, have been applied for training and testing the SNN and the ENN. Statistical mean and variances of the SNN and ENN recognition rates were compared and evaluated over several iterations in order to obtain an acceptable value. The results show that the ENN is generally more robust and often provides an improved recognition rate with higher mean value and lower variance when compared with the SNN. The result implies that it is possible to determine the accurate statistical error tolerances for the SNN and ENN recognition probability for correct diagnosis of PD fault.

Citation

MAS'UD, A.A., ELTAYEB, M., MUHAMMAD-SUKKI, F. and BANI, N.A. 2015. Statistical error tolerances of partial discharge recognition rates. In Proceedings of the Institute of Electrical and Electonic Engineers (IEEE) conference on sustainable utilization and development in engineering and technology (CSUDET 2015), 15-17 October 2015, Selangor, Malaysia. Piscataway: IEEE [online], article ID 7446217. Available from: https://dx.doi.org/10.1109/CSUDET.2015.7446217

• Conference Name: 2015 Institute of Electrical and Electronics Engineers (IEEE) conference on sustainable utilization and development in engineering and technology 2015 (CSUDET 2015)
• Conference Location: Selangor, Malaysia
• Start Date: Oct 15, 2015
• End Date: Oct 17, 2015
• Acceptance Date: Oct 15, 2015
• Online Publication Date: Oct 17, 2015
• Publication Date: Apr 4, 2016
• Deposit Date: Sep 16, 2016
• Publicly Available Date: Sep 16, 2016
• Publisher: IEEE Institute of Electrical and Electronics Engineers
• Article Number: 7446217
• DOI: https://doi.org/10.1109/CSUDET.2015.7446217
• Keywords: Ensemble neural network; Partial discharge; Single neural network
• Public URL: http://hdl.handle.net/10059/1748