Use of Machine Learning for Partial Discharge Discrimination

Hao, L, Lewin, P L and Swingler, S G (2009) Use of Machine Learning for Partial Discharge Discrimination. The 11th International Electrical Insulation Conference, Birmingham, United Kingdom. 26 - 28 May 2009. pp. 115-120 .

Record type: Conference or Workshop Item (Paper)

Abstract

Partial discharge (PD) measurements are an important tool for assessing the condition of power equipment. Different sources of PD have different effects on the insulation performance of power apparatus. Therefore, discrimination between PD sources is of great interest to both system utilities and equipment manufacturers. This paper investigates the use of a wide bandwidth PD on-line measurement system to facilitate automatic PD source identification. Three artificial PD models were used to simulate typical PD sources which may exist within power systems. Wavelet analysis was applied to pre-process the obtained measurement data. This data was then processed using correlation analysis to cluster the discharges into different groups. A machine learning technique, namely the support vector machine (SVM) was then used to identify between the different PD sources. The SVM is trained to differentiate between the inherent features of each discharge source signal. Laboratory experiments indicate that this approach is applicable for use with field measurement data.

Text

Insucon_2009_southampton_Hao_v2.pdf - Accepted Manuscript

Download (443kB)