《電子技術(shù)應(yīng)用》
您所在的位置:首頁(yè) > 其他 > 設(shè)計(jì)應(yīng)用 > 基于時(shí)頻色譜圖的串聯(lián)故障電弧識(shí)別
基于時(shí)頻色譜圖的串聯(lián)故障電弧識(shí)別
2022年電子技術(shù)應(yīng)用第8期
王 毅1,羅章權(quán)1,李松濃2,陳 濤2,侯興哲2,付秀元3
1.重慶郵電大學(xué) 通信與信息工程學(xué)院,重慶400065;2.國(guó)網(wǎng)重慶市電力公司電力科學(xué)研究院,重慶400014; 3.國(guó)家電投集團(tuán)數(shù)字科技有限公司,北京100080
摘要: 由于電力線老化損壞以及連接處松動(dòng)會(huì)產(chǎn)生故障電弧,可能會(huì)意外引起嚴(yán)重的電氣火災(zāi)。不同類型的負(fù)載所引起的故障電弧存在差異,導(dǎo)致住宅區(qū)故障電弧識(shí)別變得困難。提出了一種基于時(shí)頻圖和深度卷積神經(jīng)網(wǎng)絡(luò)的串聯(lián)故障電弧識(shí)別的方法。通過(guò)故障電弧實(shí)驗(yàn)采集了負(fù)載正常工作和故障電弧的電流數(shù)據(jù)。單個(gè)負(fù)載半周期電流數(shù)據(jù)將通過(guò)連續(xù)小波變換轉(zhuǎn)換為三維特征圖像,然后將這些圖像輸入到改進(jìn)的深度卷積神經(jīng)網(wǎng)絡(luò)中進(jìn)行訓(xùn)練、測(cè)試。實(shí)驗(yàn)結(jié)果表明,單個(gè)負(fù)載正常和電弧狀態(tài)識(shí)別的精度在99.31%,對(duì)多個(gè)負(fù)載工作狀態(tài)的識(shí)別準(zhǔn)確率平均可以達(dá)到99.2%。
中圖分類號(hào): TM501.2
文獻(xiàn)標(biāo)識(shí)碼: A
DOI:10.16157/j.issn.0258-7998.212349
中文引用格式: 王毅,羅章權(quán),李松濃,等. 基于時(shí)頻色譜圖的串聯(lián)故障電弧識(shí)別[J].電子技術(shù)應(yīng)用,2022,48(8):70-75.
英文引用格式: Wang Yi,Luo Zhangquan,Li Songnong,et al. Identification of series fault arc based on time-frequency chromatogram[J]. Application of Electronic Technique,2022,48(8):70-75.
Identification of series fault arc based on time-frequency chromatogram
Wang Yi1,Luo Zhangquan1,Li Songnong2,Chen Tao2,Hou Xingzhe2,F(xiàn)u Xiuyuan3
1.Communication and Information Engineering,Chongqing University of Posts and Telecommunications,Chongqing 400065,China; 2.Electric Power Research Institute of State Grid Chongqing Electric Power Company,Chongqing 400014,China; 3.State Power Investment Corporation Digital Technology Co.,Ltd.,Beijing 100080,China
Abstract: The aging and damage of the power line and the loose connection will cause a fault arc, which may accidentally cause a serious electrical fire. There are differences in arc faults caused by different types of loads, which makes it difficult to identify arc faults in residential areas. This paper presents a method of series fault arc recognition based on time-frequency diagram and deep convolutional neural network. Through the arc fault experiment, the current data of the normal load and the fault arc are collected. The single load half-cycle current data will be converted into three-dimensional feature images through continuous wavelet transform(CWT), and then these images will be input into the improved convolutional neural network(CNN) for training and testing. The experimental results show that the accuracy of identifying the normal and arc status of a single load is above 99.31%,the accuracy of identifying the working status of multiple loads can reach 99.2% on average.
Key words : series fault arc;time-frequency diagram;convolutional neural network

0 引言

    故障電弧是住宅區(qū)電氣線路火災(zāi)的最重要的原因之一,它能產(chǎn)生極高的溫度,并容易引燃周圍的可燃材料[1]。據(jù)應(yīng)急保障管理部消防救援局最新數(shù)據(jù)的統(tǒng)計(jì),2020年全國(guó)共接報(bào)火災(zāi)25.2萬(wàn)起,直接財(cái)產(chǎn)損失40.09億元。其中,電氣引發(fā)的較大火災(zāi)36起,在各類火災(zāi)中排名第一,高達(dá)55.4%,大部分電氣火災(zāi)是由故障電弧引起的。因此,識(shí)別故障電弧對(duì)減少火災(zāi)發(fā)生,提高居民財(cái)產(chǎn)安全有著重大的意義。

    隨著國(guó)內(nèi)外對(duì)故障電弧火災(zāi)危險(xiǎn)性認(rèn)識(shí)的不斷加深,國(guó)內(nèi)外分別制定了GB14287與UL1699標(biāo)準(zhǔn)[2-3],標(biāo)志著國(guó)內(nèi)外故障電弧檢測(cè)技術(shù)的發(fā)展進(jìn)入了一個(gè)新階段[4]。近年來(lái),許多學(xué)者已經(jīng)開(kāi)始研究故障電弧。一些學(xué)者通過(guò)熱、光、電磁輻射、電壓等信息進(jìn)行特征進(jìn)行故障電弧檢測(cè)[5-7]。由于故障電弧的位置是未知的,因此很難通過(guò)以上方法對(duì)住宅區(qū)故障電弧進(jìn)行檢測(cè)。相反,故障電弧電流測(cè)量的方便性使其成為了故障電弧檢測(cè)的理想特征。Jiang[8]等人通過(guò)主成分分析算法將提取到的9個(gè)電流信號(hào)的時(shí)域和頻域特征降維為3個(gè)特征,結(jié)合支持向量機(jī)(Support Vector Machine,SVM)進(jìn)行故障電弧識(shí)別;龍官微[9]等人將電流信號(hào)的傅里葉系數(shù)、梅爾倒譜系數(shù)和小波特征作為特征量輸入到深層神經(jīng)網(wǎng)絡(luò),用于識(shí)別正常和故障電流;Wang[10]等人在通過(guò)電流的諧波分量占比、時(shí)域的積分、方差等特征對(duì)負(fù)載類型識(shí)別之后,再結(jié)合不同的神經(jīng)網(wǎng)絡(luò)進(jìn)行故障電弧識(shí)別;鮑光海[11]等人通過(guò)分析電弧熄滅重燃時(shí)高頻剩余磁通的耦合信號(hào),利用高階統(tǒng)計(jì)量工具計(jì)算出耦合信號(hào)的峭度值并得出統(tǒng)一的閾值進(jìn)行電弧識(shí)別。




本文詳細(xì)內(nèi)容請(qǐng)下載:http://theprogrammingfactory.com/resource/share/2000004654。




作者信息:

王  毅1,羅章權(quán)1,李松濃2,陳  濤2,侯興哲2,付秀元3

(1.重慶郵電大學(xué) 通信與信息工程學(xué)院,重慶400065;2.國(guó)網(wǎng)重慶市電力公司電力科學(xué)研究院,重慶400014;

3.國(guó)家電投集團(tuán)數(shù)字科技有限公司,北京100080)




wd.jpg

此內(nèi)容為AET網(wǎng)站原創(chuàng),未經(jīng)授權(quán)禁止轉(zhuǎn)載。