本文關(guān)鍵詞：基于深度學(xué)習(xí)理論與相速度的電纜故障在線診斷方法研究　出處：《西安科技大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 電纜故障 在線檢測(cè) 深度學(xué)習(xí) 深度信念網(wǎng)絡(luò) 卷積神經(jīng)網(wǎng)絡(luò) 相速度

【摘要】：隨著電力電纜的廣泛使用,電纜故障的離線檢測(cè)方法給電力部門帶來(lái)了巨大的診斷壓力,為了保證電網(wǎng)的安全運(yùn)行同時(shí)降低人工維修成本,電纜故障的診斷方法應(yīng)由離線檢測(cè)診斷轉(zhuǎn)變?yōu)樵诰�檢測(cè)�，F(xiàn)階段電纜故障的診斷仍以離線的方法為主,在線診斷方法多仍處于探索研究階段,很多理論尚存在很多問(wèn)題,導(dǎo)致在線診斷的方法的真實(shí)性和準(zhǔn)確性欠佳難以運(yùn)用到實(shí)際中,不能滿足新形勢(shì)下電纜故障診斷技術(shù)的新要求。針對(duì)以上提出的問(wèn)題,本文建立一個(gè)地下電纜分布系統(tǒng)仿真模型用于采集不同情況下不同故障類型的電壓和電流信號(hào),引入深度學(xué)習(xí)的概念來(lái)分析電纜故障的類型,把故障等效的阻抗融入到電纜中根據(jù)電纜雙端信號(hào)波形的相位差來(lái)確定故障距離。本文取得了一下的研究成果:(1)建立了一個(gè)擁有16根地下電力電纜分布的三相供電系統(tǒng)仿真模型,在不同位置電纜上設(shè)置了不同類型的故障,從理論上的角度模擬了電纜發(fā)生各種故障的情況,彌補(bǔ)了實(shí)際系統(tǒng)中故障可調(diào)性差和數(shù)據(jù)不足的缺點(diǎn)。(2)創(chuàng)建基于深度學(xué)習(xí)理論的深度信念網(wǎng)絡(luò)(DBN)和卷積神經(jīng)網(wǎng)絡(luò)(CNN)用于電纜故障的識(shí)別。該深度神經(jīng)網(wǎng)絡(luò)利用大量的故障數(shù)據(jù)能夠自動(dòng)完成故障信號(hào)特征的分類并提取將故障準(zhǔn)確地定位到具體電纜上并識(shí)別出故障類型。(3)針對(duì)行波測(cè)距方法的缺點(diǎn),提出基于相速度的方法來(lái)獲取故障距離,根據(jù)實(shí)際的電纜雙端電壓電流波形的相位差,推導(dǎo)出相位差與故障距離的數(shù)學(xué)表達(dá)式,所需要的數(shù)據(jù)易采集計(jì)算過(guò)程簡(jiǎn)單。(4)基于MATLAB-GUI設(shè)計(jì)了一個(gè)可視化的檢測(cè)系統(tǒng),將仿真模型、電纜故障識(shí)別、故障距離計(jì)算算法與波形顯示功能集成到該系統(tǒng)里,故障設(shè)置方便簡(jiǎn)單、識(shí)別與計(jì)算結(jié)果直觀形象。通過(guò)實(shí)驗(yàn)對(duì)比了基于深度學(xué)習(xí)的DBN和CNN與傳統(tǒng)淺層神經(jīng)網(wǎng)絡(luò)對(duì)電纜故障的識(shí)別,DBN和CNN的故障平均識(shí)別正確率為89%、93%,傳統(tǒng)的BP為50.8%,RBF為67%,SVM為83%。與傳統(tǒng)的電纜診斷方法相比,本文所提出的方法利用海量的數(shù)據(jù)反映了電纜運(yùn)行的狀況和故障發(fā)生的規(guī)律,在故障類型識(shí)別正確率和故障定位精準(zhǔn)性都有明顯的提高,可作為電纜實(shí)際運(yùn)行中故障診斷技術(shù)的有效補(bǔ)充,具有一定的理論意義和使用價(jià)值。
[Abstract]:With the wide use of power cables, off-line detection of cable faults has brought huge diagnostic pressure to the power sector, in order to ensure the safe operation of the grid and reduce the cost of manual maintenance. The method of cable fault diagnosis should be changed from off-line detection to on-line detection. At present, the main method of cable fault diagnosis is off-line, and most on-line diagnosis methods are still in the stage of exploration and research. There are still many problems in many theories, which leads to the lack of authenticity and accuracy of online diagnosis methods. Can not meet the new requirements of cable fault diagnosis technology under the new situation. In this paper, a simulation model of underground cable distribution system is established to collect voltage and current signals of different fault types under different conditions, and the concept of depth learning is introduced to analyze the types of cable faults. The equivalent impedance of the fault is integrated into the cable to determine the fault distance according to the phase difference of the signal waveform of the two ends of the cable. A simulation model of three-phase power supply system with 16 underground power cables is established. Different types of faults are set up on the cable in different positions, and the various faults of the cable are simulated from the angle of theory. It makes up for the shortcomings of poor fault tunability and insufficient data in the actual system. (2) Establishment of Deep belief Network (DBN) and Convolutional Neural Network (CNN) based on depth Learning Theory (DLT) and convolutional Neural Network (CNN). For cable fault identification, the depth neural network can automatically classify fault signal features by using a large number of fault data and extract fault accurately to locate the fault on a specific cable and identify the fault type. Aiming at the shortcomings of traveling wave ranging method. A method based on phase velocity is proposed to obtain the fault distance. According to the phase difference of the actual voltage and current waveform, the mathematical expression between the phase difference and the fault distance is derived. A visual detection system is designed based on MATLAB-GUI. The simulation model is used to identify the cable fault. The fault distance calculation algorithm and waveform display function are integrated into the system, and the fault setting is convenient and simple. The results of recognition and calculation are visualized and compared by experiments between DBN and CNN based on depth learning and traditional shallow neural networks for cable fault identification. The average correct rate of fault identification for DBN and CNN is 89 / 93.The traditional BP is 50.8 and 673SVM is 833.Compared with the traditional cable diagnosis method. The method presented in this paper reflects the status of cable operation and the rule of fault occurrence using massive data, and improves the accuracy of fault type identification and fault location obviously. It can be used as an effective supplement of fault diagnosis technology in practical operation of cable and has certain theoretical significance and practical value.
【學(xué)位授予單位】：西安科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TM75

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 石俊飛;劉芳;林耀海;劉璐;;基于深度學(xué)習(xí)和層次語(yǔ)義模型的極化SAR分類[J];自動(dòng)化學(xué)報(bào);2017年02期

2 廖曉輝;趙肖健;梁恒娜;;一種基于Hilbert-Huang變換的電力電纜故障測(cè)距方法[J];電力系統(tǒng)保護(hù)與控制;2017年03期

3 周飛燕;金林鵬;董軍;;卷積神經(jīng)網(wǎng)絡(luò)研究綜述[J];計(jì)算機(jī)學(xué)報(bào);2017年06期

4 李鳴;張鴻;;基于卷積神經(jīng)網(wǎng)絡(luò)迭代優(yōu)化的圖像分類算法[J];計(jì)算機(jī)工程與設(shè)計(jì);2017年01期

5 范斌;劉輝;汪繁榮;譚文龍;;狼群算法優(yōu)化BP神經(jīng)網(wǎng)絡(luò)的電纜故障測(cè)距算法[J];云南大學(xué)學(xué)報(bào)(自然科學(xué)版);2016年06期

6 趙敏;尚鵬輝;;井下配電網(wǎng)電纜故障在線雙端行波測(cè)距方法[J];工礦自動(dòng)化;2016年11期

7 王民;蘇利博;王稚慧;要趁紅;;采用STRAIGHT模型和深度信念網(wǎng)絡(luò)的語(yǔ)音轉(zhuǎn)換方法[J];計(jì)算機(jī)工程與科學(xué);2016年09期

8 段艷杰;呂宜生;張杰;趙學(xué)亮;王飛躍;;深度學(xué)習(xí)在控制領(lǐng)域的研究現(xiàn)狀與展望[J];自動(dòng)化學(xué)報(bào);2016年05期

9 孫勁光;孟凡宇;;基于深度神經(jīng)網(wǎng)絡(luò)的特征加權(quán)融合人臉識(shí)別方法[J];計(jì)算機(jī)應(yīng)用;2016年02期

10 王新;王建順;周濤;;電力電纜故障定位與檢測(cè)信號(hào)去噪研究[J];計(jì)算機(jī)仿真;2015年11期

相關(guān)碩士學(xué)位論文 前1條

1 崔晉軍;電力電纜故障定位方法研究及在線檢測(cè)裝置實(shí)現(xiàn)[D];華北電力大學(xué);2015年

，

本文編號(hào)：1389229