基于遗传算法和神经网络的故障电弧检测算法研究  

Research of fault arc detection algorithm based on genetic algorithm and neural network

作　　者：黄佳平[1] 马琪[1] 竺红卫[2] Huang Jiaping Ma Qi Zhu Hongwei(CADResearchCenter, HangzhouDianziUniversity, Hangzhou, 310018, China VLSI Design Research Institute, Zhejiang University, Hangzhou, 310027, China)

机构地区：[1]杭州电子科技大学微电子CAD研究所 [2]浙江大学超大规模集成电路设计研究所

出　　处：《电子世界》2016年第21期36-38,共3页Electronics World

摘　　要：由于采集的原始信号含有过多的干扰信号,首先在对信号分析之前对原始信号进行了降噪,,然后利用小波分析对非平稳和非线性的信号能够很好的分析其局部变化的特点,用于对故障电弧在时频域内的分解并提取了用于神经网络输入的多个相关特征量,同时在实验期间针对BP神经网络存在的容易陷入局部优化和训练过慢等特点,采用了遗传算法来对神经网络进行进一步的优化。实验结果表明,该直流电弧故障检测方法的判断准确率和误判率令人满意。Because the original signal contains too much interference in the signal analysis, first before the original signal noise, and then use wavelet analysis to analysis the characteristics of the local variation of the good signal to the nonlinear and non-stationary, for arc fault in time and frequency domain decomposition for multiple extraction the relevant features of neural network input, at the same time during the experiment for BP neural network is easy to fall into local optimization and slow training characteristics, use the genetic algorithm to optimize the neural network.The experimental results show that the fault detection method of the DC arc fault detection accuracy and false positive rate is satisfactory.

关 键 词：小波分析 电弧故障检测 遗传算法 神经网络 

分 类 号：P631.83[天文地球—地质矿产勘探]