期刊论文

Voltage disturbance signals improved LMD and identification based on neural network

中文

长沙理工大学学报(自然科学版)

1672-9331

2018

15

3

85-93

10.3969/j.issn.1672-9331.2018.03.014

国家自然科学基金资助项目（61473049）；

本校为第一机构

为了识别电力系统存在的扰动信号，减少扰动信号对系统安全的影响，提出了一种改进局部均值分解法（Improved Local Mean Decomposition，简称ILMD）与BP神经网络相结合的电压扰动信号分类器对电压扰动进行识别分类。通过ILMD对电压扰动信号进行3层分解，得到包含电压原始信号频率、幅值的乘积分量（Product Function，简称PF），将PF分量构建的信号能量值作为BP神经网络的输入，实现对电压扰动信号的识别分类。通过对系统中4种典型电压扰动信号进行识别试验，结果表明，基于LMD和神经网络的电压信号分类器准确度高，并具有较高的工作效率。

In order to identify the disturbance signal in the power system and reduce the in- fluence of disturbance signal on system security,a voltage disturbance signal classifier based on improved local mean decomposition and BP neural network is proposed. Disturbance sig- nals are decomposed in three layers by LMD, obtaining product function components with amplitude and frequency information of the voltage signal. The signal energy value construc- ted by the PF components is as an input of the BP neural network to identify and classify the voltage disturbance signal. Experiments on the four typical...