Development of an integrated low-power rf partial discharge detector

This paper presents the results from integrating a low-power partial discharge detector with a wireless sensor node designed for operating as part of an IEEE 802.15.4 sensor network, and applying an on-line classifier capable of classifying partial discharges in real-time. Such a system is of benefit to monitoring engineers as it provides a means to exploit the RF technique using a low-cost device while circumventing the need for any additional cabling associated with new condition monitoring systems. The detector uses a frequency-based technique to differentiate between multiple defects, and has been integrated with a SunSPOT wireless sensor node hosting an agent-based monitoring platform, which includes a data capture agent and rule induction agent trained using experimental data. The results of laboratory system verification are discussed, and the requirements for a fully robust and flexible system are outlined.