摘要
提出一种基于VMD-LSTM的故障选线方法。首先通过VMD算法将各出线零序电流分解为表征其特性的高、中、低频分量,分时段计算各分量能量值,并依次输入到LSTM神经网络中,通过建立各分量能量随时序变化特征与故障线路的联系,从而实现故障选线。仿真结果表明,该方法不受故障初始相角、接地电阻以及故障距离等因素影响,且在有噪声干扰、异步采样和采样频率较低时依然可以取得良好的选线效果。
The paper proposes a fault line selection method based on VMD-LSTM.In this paper,the zero-sequence current of each line is decomposed into high,medium and low frequency components characterizing its characteristics by VMD algorithm,the energy value of each component is calculated by time,and then input into the LSTM neural network in turn by establishing the relationship between the characteristics of the energy changes of each component and the fault line to realize fault line selection.The simulation results show that the method is not affected by factors such as the initial phase angle,the grounding resistance and the distance of the fault,and it can still achieve good line selection effect when there is noise interference,asynchronous sampling and low sampling frequency.
作者
翟二杰
舒征宇
汪俊
黄志鹏
ZHAI Er-jie;SHU Zheng-yu;WANG Jun;HUANG Zhi-peng(College of Electrical Engineering and New Energy, China Three Gorges University, Yichang 443000, China)
出处
《电工电能新技术》
CSCD
北大核心
2021年第1期70-80,共11页
Advanced Technology of Electrical Engineering and Energy
基金
国家自然科学基金资助项目(61876097)。
关键词
小电流接地系统
故障选线
变分模态分解
长短期记忆神经网络
small current grounding system
fault line selection
variational modal decomposition
long short-term memory neural network
