Failure prediction in power system components

尽管电力系统保护技术在过去十年中取得了最近的进步，但现有的保护仍然只有在故障扰乱电力系统部件的健康运行后才能运行。因此，保护技术在本质上仍然是反应性的。这种方法在减少停电时间和提高电网可靠性方面有一定的局限性。该项目通过Ali Hooshya教授与合作伙伴组织Hyperion Sensors的合作，将试图从根本上改变这种方法，并开发可预测电力系统组件(例如地下电缆或变压器绕组)未来故障的保护技术。因此，可以在终端用户经历断电之前进行必要的维护，以消除该故障的根本原因。Hyperion传感器采用的技术是基于使用光纤网络对机械量(如温度和压力)进行分布式测量。光纤沿着电力设备的不同部分分布在空间上，既可以作为传感器，也可以作为传输被测量的通信介质。光纤可以通过诸如布里渊原理之类的各种原理来测量温度。实现该技术所要应对的挑战是：(I)识别光纤测量的适当的机械量，以及(Ii)在测量量中找到可用于预测未来故障的模式。Hyperion传感器公司正在获取其首套地下电缆的温度测量数据。该公司将向申请者提供数据，以研究可用于应对上述挑战的不同波形识别和人工智能技术。这些技术将在Hyperion传感器开发的保护设备中实施。这样的保护装置将减少停电时间，提高电网的可靠性。

Despite recent advances in power system protection technologies over the last decade, existing protectiverelays still operate only after a fault disrupts the healthy operation of a power system component. Therefore, theprotection technology has remained reactive in nature. This approach has a limit for reducing the outage timeand increasing the reliability of the grid. This project through a partnership between Professor Ali Hooshyarand partner organization, Hyperion Sensors, will attempt to fundamentally change this approach and developprotection technologies that predict a future failure in a power system component, e.g., an underground cable ora transformer winding. Therefore, the necessary maintenance to remove the root cause of that fault can becarried out before the end users experience power outage. The technique adopted by Hyperion Sensors toimplement this approach is based on distributed measurement of mechanical quantities (such as, temperatureand pressure) using a network of optical fibre. The optical fibre is distributed spatially alongside different partsof the power equipment, and operates both as the sensor and the communication medium to transfer themeasured quantities. The optical fibre can measure, e.g., temperature through a variety of principles, such asBrillouin principle.The challenges that are to be met for the realization of this technology are (i) identifying the appropriatemechanical quantity measured by the optical fibre, and (ii) finding the patterns in the measured quantities thatcan be used to predict a future failure. Hyperion Sensors is acquiring its first set of temperature measurementsfor an underground cable. The company will provide the data to the applicant to investigate differentwaveshape recognition and artificial intelligence techniques that can be used to address the above challenges.These techniques will be implemented in the protective device developed by Hyperion Sensors. Such aprotective device will reduce the outage time and increase the reliability of the power grid.