基于光纤传感技术的配电网故障检测系统

Fault Detection System for Distribution Network Based on Fiber Optic Sensing Technology

针对配电网故障检测中的实时性差、误报率高等问题,提出一种基于光纤传感技术的解决方案。通过布里渊光时域分析仪(Brillouin Optical Time Domain Analysis,BOTDA)、光时域反射仪(Optical Time Domain Reflectometer,OTDR)等光纤传感单元获取配电网状态信息,结合小波变换、希尔伯特-黄变换(Hilbert-Huang Transform,HHT)等信号处理算法提取故障特征,并使用支持向量机(Support Vector Machine,SVM)、卷积神经网络(Convolutional Neural Networks,CNN)等机器学习模型实现故障诊断与预警。实验结果表明,该系统整体能满足配电自动化要求。

Aiming at the problems of poor real-time performance and high false alarm rate in fault detection of distribution network,this paper puts forward a solution based on optical fiber sensing technology.The state information of distribution network is obtained by optical fiber sensing units such as Brillouin Optical Time Domain Analysis(BOTDA)and Optical Time Domain Reflectometer(OTDR),Combining wavelet transform,Hilbert-Huang Transform(HHT)and other signal processing algorithms to extract fault features,and using machine learning models such as Support Vector Machine(SVM)and Convolutional Neural Networks(CNN)to realize fault diagnosis and early warning.The experimental results show that the system meets the requirements of distribution automation.