基于卷積神經(jīng)網(wǎng)絡(luò)的電力巡檢絕緣子檢測(cè)研究
發(fā)布時(shí)間：2018-07-16 08:19
【摘要】：電力巡檢是保障電網(wǎng)安全運(yùn)行不可或缺的手段,新興的無(wú)人機(jī)巡檢通過(guò)搭載的高清相機(jī)和圖傳設(shè)備可獲取大量詳實(shí)的巡檢影像。這些巡視數(shù)據(jù)僅憑人工分析和處理,工作量龐大,效率低下,存在由工作人員經(jīng)驗(yàn)和素質(zhì)引起的偏差。而絕緣子是電力系統(tǒng)中的常見(jiàn)部件,由于常年暴露在外,因而故障多發(fā),嚴(yán)重威脅電網(wǎng)安全,需要引入智能化的識(shí)別方法自動(dòng)進(jìn)行故障診斷。本文結(jié)合四川省電力公司科技項(xiàng)目的需求,從以下幾個(gè)方面展開(kāi)研究:(1)本文通過(guò)搭建和改進(jìn)卷積神經(jīng)網(wǎng)絡(luò)實(shí)現(xiàn)對(duì)絕緣子的檢測(cè),解決傳統(tǒng)檢測(cè)算法魯棒性差,泛化能力不強(qiáng),準(zhǔn)確率不高等問(wèn)題。首先通過(guò)研究卷積神經(jīng)網(wǎng)絡(luò)的特點(diǎn)和廣泛應(yīng)用,結(jié)合工程需求和硬件支持,完成對(duì)卷積神經(jīng)網(wǎng)絡(luò)各個(gè)部件的選型和設(shè)計(jì),搭建適宜本課題網(wǎng)絡(luò)模型。其次利用無(wú)人機(jī)在不同線(xiàn)路和時(shí)間采集玻璃和陶瓷絕緣子樣本并進(jìn)行人為拓展,作為訓(xùn)練樣本。然后本文選擇開(kāi)源的Caffe作為工具,結(jié)合相關(guān)調(diào)參技術(shù)對(duì)網(wǎng)絡(luò)結(jié)構(gòu)進(jìn)行改進(jìn)和在訓(xùn)練過(guò)程中進(jìn)行優(yōu)化。通過(guò)自動(dòng)學(xué)習(xí)絕緣子特征的本質(zhì)和分布式表達(dá),實(shí)現(xiàn)在復(fù)雜航拍背景中的絕緣子檢測(cè),訓(xùn)練準(zhǔn)確率為95%,測(cè)試準(zhǔn)確率為92%。(2)本文結(jié)合已訓(xùn)練完備的卷積神經(jīng)網(wǎng)絡(luò)完成絕緣子自爆的識(shí)別,解決人工分析工作量大,效率低等問(wèn)題。首先利用卷積神經(jīng)網(wǎng)絡(luò)層級(jí)結(jié)構(gòu)對(duì)全局和局部特征的綜合與抽象,將訓(xùn)練完備的網(wǎng)絡(luò)模型作為絕緣子特征抽取的工具,融入自組織特征映射網(wǎng)絡(luò),實(shí)現(xiàn)顯著性檢測(cè)的改良。其次在顯著性檢測(cè)的基礎(chǔ)上,快速提取絕緣子,舍棄背景,然后結(jié)合超像素分割和輪廓檢測(cè)等圖像處理方法建立絕緣子模型,提出一種針對(duì)絕緣子自爆故障的識(shí)別算法,準(zhǔn)確率在90%以上,取代人工分析,降低憑巡檢工作人員經(jīng)驗(yàn)判定的風(fēng)險(xiǎn)和誤差,保障電網(wǎng)安全可靠運(yùn)行。(3)本文對(duì)絕緣子檢測(cè)及自爆故障識(shí)別分別進(jìn)行測(cè)試驗(yàn)證和對(duì)比試驗(yàn)。首先針對(duì)不同背景,不同種類(lèi),不同數(shù)量的情況進(jìn)行了絕緣子檢測(cè)測(cè)試,并與傳統(tǒng)的DPM和基于HoG的SVM算法進(jìn)行對(duì)比。同時(shí)通過(guò)可視化效果分析網(wǎng)絡(luò)的性能。然后對(duì)不同背景下的自爆識(shí)別算法進(jìn)行了驗(yàn)證。最后以工程項(xiàng)目為依托,簡(jiǎn)單介紹電力巡檢絕緣子檢測(cè)系統(tǒng)平臺(tái)的構(gòu)架和應(yīng)用效果。經(jīng)驗(yàn)證,絕緣子檢測(cè)和自爆識(shí)別均達(dá)到工程要求,有效體現(xiàn)巡視數(shù)據(jù)的價(jià)值,提升電力巡檢的效率和智能化水平。
[Abstract]:Power inspection is an indispensable means to ensure the safe operation of the power grid. The emerging UAV patrol can obtain a large number of detailed inspection images by carrying high-definition cameras and graphic transmission equipment. These patrol data only depend on manual analysis and processing, the workload is huge, the efficiency is low, and the deviation caused by the staff's experience and quality exists. Insulator is a common component in power system. Because it is exposed all the year round, the fault is frequently occurred, which seriously threatens the security of power network, so it is necessary to introduce intelligent identification method to diagnose the fault automatically. According to the demand of Sichuan Electric Power Company's scientific and technological project, this paper studies the following aspects: (1) this paper realizes the detection of insulators by building and improving convolutional neural networks, which solves the problem of poor robustness and poor generalization ability of traditional detection algorithms. The accuracy is not high and so on. Firstly, by studying the characteristics and wide application of convolution neural network, combining with engineering demand and hardware support, the selection and design of each component of convolutional neural network are completed, and the network model suitable for this topic is built. Secondly, using UAV to collect glass and ceramic insulator samples on different lines and time, and to carry out artificial expansion, as a training sample. Then the open source Caffe is chosen as a tool to improve the network structure and optimize the training process. By automatically learning the nature and distributed expression of insulator features, the insulator detection in complex aerial photography background is realized. The accuracy of training is 95 and the accuracy of test is 92. (2) in this paper, the self-explosion identification of insulator is completed by using the fully trained convolution neural network to solve the problems of large workload and low efficiency in manual analysis. Firstly, using the hierarchical structure of convolution neural network to synthesize and abstract the global and local features, the well-trained network model is used as the tool of insulator feature extraction, and the self-organizing feature mapping network is integrated into the self-organizing feature mapping network to achieve the improvement of salience detection. Secondly, on the basis of salience detection, the insulator is quickly extracted and the background is discarded. Then the insulator model is established by combining the image processing methods such as super-pixel segmentation and contour detection, and an algorithm for identifying insulator self-detonation fault is proposed. The accuracy rate is over 90%, which replaces manual analysis, reduces the risk and error judged by the experience of inspection staff, and ensures the safe and reliable operation of power grid. (3) the insulator detection and fault identification of self-explosion are tested and compared in this paper. Firstly, the insulator detection test is carried out for different background, different kinds and different numbers of insulators, and compared with traditional DPM and SVM algorithm based on HoG. At the same time, the performance of the network is analyzed by visual effect. Then the self-detonation recognition algorithm under different background is verified. Finally, based on the project, the frame and application effect of the platform of insulator detection system for electric power inspection are briefly introduced. It is verified that both insulator detection and self-detonation identification meet the engineering requirements, effectively reflect the value of patrol data, and improve the efficiency and intelligence level of power inspection.
【學(xué)位授予單位】：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;TM755
本文編號(hào)：2125809
[Abstract]:Power inspection is an indispensable means to ensure the safe operation of the power grid. The emerging UAV patrol can obtain a large number of detailed inspection images by carrying high-definition cameras and graphic transmission equipment. These patrol data only depend on manual analysis and processing, the workload is huge, the efficiency is low, and the deviation caused by the staff's experience and quality exists. Insulator is a common component in power system. Because it is exposed all the year round, the fault is frequently occurred, which seriously threatens the security of power network, so it is necessary to introduce intelligent identification method to diagnose the fault automatically. According to the demand of Sichuan Electric Power Company's scientific and technological project, this paper studies the following aspects: (1) this paper realizes the detection of insulators by building and improving convolutional neural networks, which solves the problem of poor robustness and poor generalization ability of traditional detection algorithms. The accuracy is not high and so on. Firstly, by studying the characteristics and wide application of convolution neural network, combining with engineering demand and hardware support, the selection and design of each component of convolutional neural network are completed, and the network model suitable for this topic is built. Secondly, using UAV to collect glass and ceramic insulator samples on different lines and time, and to carry out artificial expansion, as a training sample. Then the open source Caffe is chosen as a tool to improve the network structure and optimize the training process. By automatically learning the nature and distributed expression of insulator features, the insulator detection in complex aerial photography background is realized. The accuracy of training is 95 and the accuracy of test is 92. (2) in this paper, the self-explosion identification of insulator is completed by using the fully trained convolution neural network to solve the problems of large workload and low efficiency in manual analysis. Firstly, using the hierarchical structure of convolution neural network to synthesize and abstract the global and local features, the well-trained network model is used as the tool of insulator feature extraction, and the self-organizing feature mapping network is integrated into the self-organizing feature mapping network to achieve the improvement of salience detection. Secondly, on the basis of salience detection, the insulator is quickly extracted and the background is discarded. Then the insulator model is established by combining the image processing methods such as super-pixel segmentation and contour detection, and an algorithm for identifying insulator self-detonation fault is proposed. The accuracy rate is over 90%, which replaces manual analysis, reduces the risk and error judged by the experience of inspection staff, and ensures the safe and reliable operation of power grid. (3) the insulator detection and fault identification of self-explosion are tested and compared in this paper. Firstly, the insulator detection test is carried out for different background, different kinds and different numbers of insulators, and compared with traditional DPM and SVM algorithm based on HoG. At the same time, the performance of the network is analyzed by visual effect. Then the self-detonation recognition algorithm under different background is verified. Finally, based on the project, the frame and application effect of the platform of insulator detection system for electric power inspection are briefly introduced. It is verified that both insulator detection and self-detonation identification meet the engineering requirements, effectively reflect the value of patrol data, and improve the efficiency and intelligence level of power inspection.
【學(xué)位授予單位】：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;TM755
【參考文獻(xiàn)】
相關(guān)期刊論文 前9條
1 李彥冬;郝宗波;雷航;;卷積神經(jīng)網(wǎng)絡(luò)研究綜述[J];計(jì)算機(jī)應(yīng)用;2016年09期
2 翟永杰;王迪;趙振兵;;基于目標(biāo)建議與結(jié)構(gòu)搜索的絕緣子識(shí)別方法[J];華北電力大學(xué)學(xué)報(bào)(自然科學(xué)版);2016年04期
3 趙振兵;徐磊;戚銀城;蔡銀萍;;基于Hough檢測(cè)和C-V模型的航拍絕緣子自動(dòng)協(xié)同分割方法[J];儀器儀表學(xué)報(bào);2016年02期
4 李岳云;許悅雷;馬時(shí)平;史鶴歡;;深度卷積神經(jīng)網(wǎng)絡(luò)的顯著性檢測(cè)[J];中國(guó)圖象圖形學(xué)報(bào);2016年01期
5 高強(qiáng);陽(yáng)武;李倩;;基于稀疏差異深度信念網(wǎng)絡(luò)的絕緣子故障識(shí)別算法[J];電測(cè)與儀表;2016年01期
6 姜浩然;金立軍;閆書(shū)佳;;航拍圖像中絕緣子的識(shí)別與故障診斷[J];機(jī)電工程;2015年02期
7 黃凱奇;任偉強(qiáng);譚鐵牛;;圖像物體分類(lèi)與檢測(cè)算法綜述[J];計(jì)算機(jī)學(xué)報(bào);2014年06期
8 趙振兵;王樂(lè);;一種航拍絕緣子串圖像自動(dòng)定位方法[J];儀器儀表學(xué)報(bào);2014年03期
9 張少平;楊忠;黃宵寧;吳懷群;顧元政;;航拍圖像中玻璃絕緣子自爆缺陷的檢測(cè)及定位[J];太赫茲科學(xué)與電子信息學(xué)報(bào);2013年04期
，本文編號(hào)：2125809
本文鏈接：http://sikaile.net/kejilunwen/zidonghuakongzhilunwen/2125809.html
最近更新
教材專(zhuān)著
