时间：2023年12月20日上午10:00-11:00
地点：湖南大学电气与信息工程学院院楼219报告厅
主讲人：Dr Feifei Bai （白菲菲），澳大利亚昆士兰大学高级讲师兼格里菲斯大学荣誉研究员。
主讲人简介：
Feifei Bai（IEEE的高级成员）于2010年和2016年分别获得了西南交通大学本科和博士学位，于2012年至2014年在美国田纳西大学进行博士课题研究。Dr Bai 于2018年获得了昆士兰州先进研究员奖，她目前是澳大利亚昆士兰大学高级讲师并兼任格里菲斯大学荣誉研究员。她的研究兴趣包括新能源并网及PMU的应用。
讲座简介：
The rapid deployment of distributed generators (e.g., solar photovoltaic-PV) has created many challenges to distribution power networks due to the bi-directional power flow and PV power fluctuations. These new issues may accelerate ageing and cause deterioration of electrical assets that were originally designed to be operated under a uni-directional and slow-changing power flow. The accelerated deterioration may stress aged distribution network assets. For example, in the Australian distribution network, a large number of equipment are still in operation beyond their designed life, which may pose a risk to reliable electricity supply. PMUs provide an opportunity to monitor equipment conditions proactively. This could be achieved by investigating the characteristics of PMU measurements over a period of time and determining possible relationships between asset conditions and PMU data variation features.
The asset health features have been distilled through laboratory experimentation, field asset failure event data analytics, and advanced artificial intelligence techniques based on large volumes of field PMU data. These field PMU data are collected from 100 PMUs installed in Queensland and Victoria distribution networks through a project collaboration with NOJA Power, Energy Queensland, and AusNet Services. This presentation will introduce a developed cost-effective method to monitor and predict equipment conditions by leveraging the big data measured via high-precision distribution PMUs. For the implementation of the proposed approaches, a real-time situational awareness platform has been developed. The effectiveness of the developed platform has been validated with real-time PMU data. This platform can be integrated into the network online early-warning system to prevent impending asset failures and to improve the network reliability.
