摘要
准确识别过电压类型是过电压事故处理的首要任务。针对浅层分类器难以识别高维特征的问题,提出了原子分解(atomic decomposition,AD)结合卷积神经网络(convolution neural network,CNN)的配电网内部过电压识别方法。该方法利用原子分解法分解母线三相电压,依据频率重构最优原子得到高维特征-特征原子谱,然后将特征原子谱输入到CNN中,即可实现7类典型内部过电压的识别。在仿真和物理实验平台上对所提方法进行了验证,结果表明:CNN相对于浅层学习的支持向量机和极限学习机具有更强的自主学习能力;相对于低维特征结合浅层分类器的识别算法,所提方法具有更高的识别率和更强的适应性,该识别方法能较好地适用于配电网内部过电压的识别。论文研究可为配电网内部过电压的识别提供一定的参考。
The accurate identification of over-voltages is the primary task when disposing over-voltage accidents. Because of the difficulty in identifying high-dimensional features by shallow classifiers, we proposed an internal over-voltage identification method based on atomic decomposition (AD) and convolution neural network (CNN). The AD algorithm was used to decompose the three-phase voltages of the bus, and the optimal atoms were reconstructed according to the frequency to obtain the characteristic atomic spectrum in this method. Then characteristic atomic spectrum was input into the CNN to realize the identification of seven typical internal over-voltages. The method introduced in this paper was ver ified through the simulation and physics experiment platform. The results show that, compared with the shallow learning support vector machine and extreme learning machine, CNN has stronger self-learning ability;and the proposed method has a higher recognition rate and stronger adaptability than the traditional low-dimensional features combined with shal low learning algorithms. The identification method can be well applied to identify the internal over-voltage in the distribution network. The research can provide a reference for the identification of over-voltage in distribution network.
作者
廖宇飞
杨耿杰
高伟
郭谋发
陈永往
LIAO Yufei;YANG Gengjie;GAO Wei;GUO Moufa;CHEN Yongwang(College of Electrical Engineering and Automation, Fuzhou University, Fuzhou 350116, China;Fuzhou Power Supply Company, State Grid Fujian Electric Power Co., Ltd., Fuzhou 350009, China;Jinjiang Power Supply Company, State Grid Fujian Electric Power Co., Ltd., Quanzhou 362200, China)
出处
《高电压技术》
EI
CAS
CSCD
北大核心
2019年第10期3182-3191,共10页
High Voltage Engineering
基金
国家自然科学基金(51677030)
福建省自然科学基金(2016J01218)
晋江市科技计划项目(2017C006)~~
关键词
配电网
过电压识别
原子分解
匹配追踪算法
帝国殖民竞争算法
特征原子谱
卷积神经网络
distribution network
over-voltage identification
atomic decomposition
matching pursuit algorithm
imperialist competitive algorithm
characteristic atomic spectrum
convolution neural network
