Instrumentation system for acoustic detection of multiple sources of partial discharges

In this paper we propose a method based on blind-source-separation of acoustic emissions of partial discharges in power equipment. The goal is to build an on-line monitoring system for automatic detection and localization of partial discharges and defects in the insulation. We have built a test bech to generate acoustic signals similar to those produced by partial discharges inside a propagating media and a data acquisition system with multiple acoustic detectors. We show that the INFOMAX algorithm used for blind-source-separation is able to decouple at least two different sources of partial discharges from the signal of two acoustic detector located at fixed positions.