串联型故障电弧检测方法的研究

发布时间：2018-06-23 13:40

本文选题：故障电弧 + 特征向量　；参考：《辽宁工程技术大学》2015年硕士论文

【摘要】：本文开展低压串联型故障电弧的研究工作,研究低压串联型故障电弧的特性,寻找检测低压串联型故障电弧的有效方法,对保证供电系统的稳定安全运行和提高供电质量有重大意义。首先根据UL1699标准搭建了串联故障电弧发生装置,并针对不同类型负载进行实验,获得了供电线路正常工作状态和发生故障电弧状态下的电流信号实验数据。应用小波变换对电流信号进行分解重构,通过近似熵(ApEn)算法对分解重构后各频段信号的不规则程度进行量化,构造出电流信号的特征向量,并将其输入到支持向量机(SVM)。通过SVM对电流信号特征向量进行分类,完成故障电弧的检测识别。结果表明,通过小波近似熵算法得到的故障电弧特征向量能够作为诊断识别故障电弧的有效依据。
[Abstract]:In this paper, the research work of low voltage series fault arc is carried out, the characteristics of low voltage series fault arc are studied, and the effective method to detect the low voltage series fault arc is found. It is of great significance to ensure the stable and safe operation of the power supply system and improve the quality of power supply. According to the experiments of different types of load, the normal working state of the power supply line and the experimental data of current signal under the state of fault arc are obtained. The wavelet transform is used to decompose and reconstruct the current signal, and the irregular degree of each frequency signal is quantized by the approximate entropy (ApEn) algorithm, and the current signal is constructed. The feature vector is input to the support vector machine (SVM). The feature vector of current signal is classified by SVM to complete the detection and recognition of the fault arc. The result shows that the fault arc feature vector obtained by the wavelet approximate entropy algorithm can be used as an effective basis for diagnosis and identification of fault arc.
【学位授予单位】：辽宁工程技术大学
【学位级别】：硕士
【学位授予年份】：2015
【分类号】：TM501.2

【相似文献】