直流故障電弧的特征提取與識(shí)別
[Abstract]:Because DC arc has no periodicity and zero crossing, it is more difficult to detect DC fault arc than AC fault arc. The feature extraction of DC fault arc is lack of diversification at home and abroad, so the purpose of this paper is to enrich the characteristics of DC fault arc, and give the evaluation criteria from two aspects: feature extraction and recognition. The arc studied in this paper belongs to hot cathode, gas, series, DC, fault arc. The current data of normal operation and fault arc are collected by experimental method. The unstable phase of arc is selected as the data base of feature extraction. A total of 17 features were extracted from time domain, frequency domain, wavelet, spectral analysis and chaos analysis. In time-frequency analysis, four features in time domain, three features in frequency domain and three features in wavelet domain are extracted from current variation, statistics and wavelet transform respectively. In spectral analysis, three power spectral features are extracted from amplitude and three higher-order spectral features are extracted from amplitude and phase. In chaos analysis, time delay is calculated based on autocorrelation method, embedded dimension is calculated based on false nearest neighbor method, the phase space of arc current is reconstructed by these two parameters, and one feature of maximum Lyapunov exponent is extracted by the method of small amount of data. The index of feature evaluation in feature extraction level, that is, the percentage of value, is given, and the index value of each feature is calculated, among which the index value of chaotic feature is the largest. Support vector machine (Support Vector Machines,SVM) is used to identify fault arc features. The nonlinear support vector machine based on Gao Si kernel function is chosen as the final classifier. The parameters of SVM are optimized by grid search method and 3-fold cross validation method. The penalty parameter is 0.054409 and the kernel parameter is 1. One general classifier was trained, the accuracy rate was 99.999, and 17 comparative classifiers were all reduced, but the overall accuracy remained above 99.9%. The evaluation criterion of recognition level is given, that is, the degree of contribution to accuracy, and the index value of each feature is calculated, among which the index value of chaotic feature is the largest. The results show that the feature extraction method and pattern recognition strategy used in this paper are correct, the two indexes can be used to evaluate the features, and the problem of DC fault arc detection is essentially a chaotic identification problem. The research in this paper enriches the characteristic types of DC fault arc, and gives the evaluation criteria for feature validity.
【學(xué)位授予單位】:浙江大學(xué)
【學(xué)位級(jí)別】:碩士
【學(xué)位授予年份】:2017
【分類號(hào)】:TM501.2
【相似文獻(xiàn)】
相關(guān)期刊論文 前10條
1 李建基;;故障電弧情況下的人身和設(shè)備防護(hù)[J];華通技術(shù);2004年02期
2 藍(lán)會(huì)立;張認(rèn)成;;基于混沌的故障電弧早期弧聲檢測(cè)方法研究[J];計(jì)算機(jī)測(cè)量與控制;2010年12期
3 仲啟樹;張認(rèn)成;陳建陽;;基于混沌理論的故障電弧檢測(cè)方法研究[J];黎明職業(yè)大學(xué)學(xué)報(bào);2011年03期
4 孫鵬;秦猛;;采用波形比較法的串聯(lián)故障電弧快速診斷技術(shù)[J];低壓電器;2013年20期
5 印永嘉;陳洪亮;;關(guān)于檢測(cè)低壓故障電弧的初步研究[J];實(shí)驗(yàn)室研究與探索;2007年08期
6 楊藝;董愛華;付永麗;;低壓故障電弧檢測(cè)概述[J];低壓電器;2009年05期
7 呂輝;董愛華;;基于信息融合的配電箱故障電弧在線檢測(cè)[J];煤礦機(jī)械;2009年11期
8 鄒云峰;吳為麟;李智勇;;基于自組織映射神經(jīng)網(wǎng)絡(luò)的低壓故障電弧聚類分析[J];儀器儀表學(xué)報(bào);2010年03期
9 孫鵬;鄭志成;閆榮妮;高翔;;采用小波熵的串聯(lián)型故障電弧檢測(cè)方法[J];中國電機(jī)工程學(xué)報(bào);2010年S1期
10 竇甜華;段培永;段晨旭;石嘉川;;一種建筑物低壓供配電線路故障電弧檢測(cè)新方法[J];微計(jì)算機(jī)信息;2011年03期
相關(guān)會(huì)議論文 前4條
1 徐貞華;裴小青;;基于支持向量機(jī)的低壓故障電弧識(shí)別方法[A];2011第十六屆全國自動(dòng)化技術(shù)與應(yīng)用學(xué)術(shù)年會(huì)專輯[C];2011年
2 董愛華;谷彬;;低壓配電開關(guān)故障電弧檢測(cè)技術(shù)的發(fā)展趨勢(shì)[A];第九屆全國信息獲取與處理學(xué)術(shù)會(huì)議論文集Ⅰ[C];2011年
3 劉振國;孫鵬;;基于電流波形比較法診斷故障電弧的可靠性分析研究[A];第十一屆沈陽科學(xué)學(xué)術(shù)年會(huì)暨中國汽車產(chǎn)業(yè)集聚區(qū)發(fā)展與合作論壇論文集(信息科學(xué)與工程技術(shù)分冊(cè))[C];2014年
4 陳征;;淺談故障電弧防護(hù)技術(shù)在國內(nèi)電氣安全方面的應(yīng)用前景[A];中國職業(yè)安全健康協(xié)會(huì)2008年學(xué)術(shù)年會(huì)論文集[C];2008年
相關(guān)重要報(bào)紙文章 前1條
1 魯濤 天津市鴻遠(yuǎn)電氣設(shè)備有限公司總工程師;杜絕電力火災(zāi) 造福人類文明[N];中國建設(shè)報(bào);2013年
相關(guān)碩士學(xué)位論文 前10條
1 董榮剛;故障電弧診斷技術(shù)的研究[D];沈陽工業(yè)大學(xué);2009年
2 郭家穩(wěn);故障電弧模式識(shí)別方法的研究[D];沈陽工業(yè)大學(xué);2013年
3 張磊;故障電弧的識(shí)別及防護(hù)方法的研究[D];青島理工大學(xué);2015年
4 倪侃;故障電弧電信號(hào)模擬技術(shù)的研究與實(shí)現(xiàn)[D];溫州大學(xué);2015年
5 高源;光伏系統(tǒng)直流故障電弧的特征檢測(cè)與防治策略[D];復(fù)旦大學(xué);2014年
6 姜晨;基于物聯(lián)網(wǎng)的室內(nèi)用電安全智能監(jiān)控系統(tǒng)[D];杭州電子科技大學(xué);2015年
7 王仕巖;故障電弧檢測(cè)及其直流固態(tài)功率控制器的研究[D];天津大學(xué);2014年
8 孔林娟;基于突變理論的低壓故障電弧檢測(cè)方法研究[D];河南理工大學(xué);2015年
9 梁柱;故障電弧檢測(cè)裝置的研究與設(shè)計(jì)[D];湖南大學(xué);2016年
10 鄧海平;低壓電氣線路故障電弧監(jiān)測(cè)系統(tǒng)的設(shè)計(jì)[D];湖南大學(xué);2016年
,本文編號(hào):2271148
本文鏈接:http://www.sikaile.net/kejilunwen/dianlidianqilunwen/2271148.html