本文選題：直流電弧故障檢測(cè)　切入點(diǎn)：傅立葉分析　出處：《杭州電子科技大學(xué)》2017年碩士論文　論文類(lèi)型：學(xué)位論文

【摘要】：在光伏系統(tǒng)、航天航空、電動(dòng)汽車(chē)、大型機(jī)房等大功率直流電器設(shè)備應(yīng)用中,隨著設(shè)備損耗、絕緣層的損壞或者接頭的松動(dòng)都是會(huì)導(dǎo)致直流電弧故障的出現(xiàn),會(huì)造成火災(zāi)等不可想象的后果。因?yàn)橹绷麟娀」收吓c交流電弧故障的特性有著很大的不同,因此研究有效的直流電弧故障檢測(cè)方法對(duì)直流設(shè)備的安全使用有著重要的意義。本論文研究基于BP神經(jīng)網(wǎng)絡(luò)的直流電弧故障檢測(cè)技術(shù),提出一個(gè)基于BP神經(jīng)網(wǎng)絡(luò)的直流電弧故障檢測(cè)方法,利用BP神經(jīng)網(wǎng)絡(luò)根據(jù)輸入的電流特征量做出是否發(fā)生直流電弧故障的判斷。論文采用了小波變換對(duì)原始電流采樣數(shù)據(jù)進(jìn)行降噪處理,并用傅里葉分析和小波分析等方法對(duì)降噪后的電流數(shù)據(jù)分別在時(shí)域、頻域和時(shí)頻域進(jìn)行直流電弧故障特征分析,確定若干可用于BP神經(jīng)網(wǎng)絡(luò)檢測(cè)直流電弧故障的特征量,作為BP神經(jīng)網(wǎng)絡(luò)模型檢測(cè)直流電弧故障的輸入。論文針對(duì)直流電弧故障檢測(cè)問(wèn)題設(shè)計(jì)BP神經(jīng)網(wǎng)絡(luò),確定BP神經(jīng)網(wǎng)絡(luò)模型的輸入層神經(jīng)元個(gè)數(shù)、隱藏層神經(jīng)元個(gè)數(shù)、輸出層神經(jīng)元個(gè)數(shù)等結(jié)果參數(shù),并針對(duì)BP神經(jīng)網(wǎng)絡(luò)存在的訓(xùn)練收斂慢、容易陷入局部最優(yōu)值的問(wèn)題,采用遺傳算法優(yōu)化BP神經(jīng)網(wǎng)絡(luò)的初始權(quán)值,提出了一個(gè)完整的采用遺傳算法優(yōu)化初始權(quán)值的BP神經(jīng)網(wǎng)絡(luò)訓(xùn)練流程。論文對(duì)BP神經(jīng)網(wǎng)絡(luò)進(jìn)行了直流電弧故障特征量樣本訓(xùn)練,對(duì)訓(xùn)練好的BP神經(jīng)網(wǎng)絡(luò)對(duì)直流電弧故障的檢測(cè)效果(檢測(cè)準(zhǔn)確率以及誤判率)進(jìn)行了測(cè)試實(shí)驗(yàn)。實(shí)驗(yàn)結(jié)果表明,論文提出的方法對(duì)直流電弧故障的檢測(cè)準(zhǔn)確率和誤判率都達(dá)到了預(yù)期的要求。
[Abstract]:In the application of high power DC electrical equipment such as photovoltaic system, aerospace, electric vehicle, large machine room, etc., with the loss of equipment, the damage of insulation layer or the loosening of joint, it will lead to the occurrence of DC arc fault. It can lead to unimaginable consequences such as fire, because the characteristics of DC arc faults and AC arc faults are very different. Therefore, the study of effective DC arc fault detection method is of great significance to the safe use of DC equipment. In this paper, the DC arc fault detection technology based on BP neural network is studied. A DC arc fault detection method based on BP neural network is proposed. The BP neural network is used to judge whether DC arc fault occurs according to the input current characteristic. In this paper, wavelet transform is used to reduce the noise of the original current sampling data. Fourier analysis and wavelet analysis are used to analyze the characteristics of DC arc fault in time domain, frequency domain and time frequency domain, respectively, and some characteristic quantities which can be used in BP neural network to detect DC arc fault are determined. As the input of BP neural network model to detect DC arc fault, the paper designs BP neural network for DC arc fault detection, determines the number of input layer neurons and hidden layer neurons of BP neural network model. In view of the problem that the training convergence of BP neural network is slow and it is easy to fall into local optimum value, genetic algorithm is used to optimize the initial weight of BP neural network. A complete BP neural network training flow using genetic algorithm to optimize the initial weights is proposed. The BP neural network is trained with the DC arc fault characteristic sample in this paper. The effect of BP neural network (BP neural network) on DC arc fault detection (detection accuracy and error rate) is tested. The experimental results show that, The method proposed in this paper meets the expected requirements for DC arc fault detection accuracy and error rate.
【學(xué)位授予單位】：杭州電子科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：TP183;TM501.2

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 劉金琰;栗惠;章建兵;黃兢業(yè);;電弧故障斷路器UL標(biāo)準(zhǔn)研究[J];低壓電器;2011年18期

2 司禎禎;;傅里葉變換與小波變換在信號(hào)去噪中的應(yīng)用[J];電子設(shè)計(jì)工程;2011年04期

3 劉濤;王華;;傳感器非線(xiàn)性校正的遺傳支持向量機(jī)方法[J];電子測(cè)量與儀器學(xué)報(bào);2011年01期

4 張堅(jiān)新;;光電式電弧光保護(hù)系統(tǒng)的設(shè)計(jì)[J];電工電氣;2010年08期

5 盧其威;王聰;程紅;胡少英;;電弧故障斷路器及故障電弧的辨別[J];電氣應(yīng)用;2009年24期

6 陳衛(wèi)東;雷軍;;基于第二代小波變換的脈搏信號(hào)去噪處理[J];測(cè)繪科學(xué);2009年06期

7 馬耀庭;邵毅全;;傅里葉變換在應(yīng)用中的局限性及克服方法[J];內(nèi)江師范學(xué)院學(xué)報(bào);2008年12期

8 董澤;黃宇;韓璞;;量子遺傳算法優(yōu)化RBF神經(jīng)網(wǎng)絡(luò)及其在熱工辨識(shí)中的應(yīng)用[J];中國(guó)電機(jī)工程學(xué)報(bào);2008年17期

9 高美靜;趙勇;談愛(ài)玲;;基于遺傳小波神經(jīng)網(wǎng)絡(luò)的多傳感器信息融合技術(shù)的研究[J];儀器儀表學(xué)報(bào);2007年11期

10 張斌;孫靜;;基于Mallat算法和快速傅里葉變換的電能質(zhì)量分析方法[J];電網(wǎng)技術(shù);2007年19期

相關(guān)碩士學(xué)位論文 前1條

1 吳建建;航空故障電弧檢測(cè)技術(shù)的研究[D];大連理工大學(xué);2009年

，

本文編號(hào)：1602640