發(fā)布時(shí)間：2018-02-20 04:50

  本文關(guān)鍵詞： 電接觸 紅外熱像 故障等級識別 圖像去噪 圖像分割 概率神經(jīng)網(wǎng)絡(luò)　出處：《湖南大學(xué)》2015年碩士論文　論文類型：學(xué)位論文

【摘要】：電接觸是指電氣設(shè)備和電氣線路中一切導(dǎo)電的連接部位,它具有數(shù)量龐大、類型繁多、故障高發(fā)等特點(diǎn)。因此,電接觸的狀態(tài)檢測與故障診斷對整個(gè)電力系統(tǒng)的安全穩(wěn)定運(yùn)行至關(guān)重要。本文研究了基于紅外熱像特征與概率神經(jīng)網(wǎng)絡(luò)的電接觸故障檢測的新方法。主要針對高壓隔離開關(guān)、液壓式耐張線夾、高壓套管將軍帽三類電接觸進(jìn)行故障研究與分析,在綜合考慮空氣污染指數(shù)、環(huán)境溫度對檢測結(jié)果準(zhǔn)確性影響的基礎(chǔ)上,從理論、實(shí)驗(yàn)等方面系統(tǒng)地驗(yàn)證了該方法的準(zhǔn)確性和有效性。本文采用高分辨率紅外熱像儀采集電接觸圖像。針對電接觸紅外熱像對比度低、噪聲大的特點(diǎn),提出了一種基于總體最小二乘法(Total Least Squares,TLS)估計(jì)的遺傳小波紅外熱像去噪方法。該方法采用總體最小二乘法獲得圖像的小波系數(shù)估計(jì),小波逆變后得到的去噪圖像作為父本,然后與通過維納濾波后得到母本進(jìn)行遺傳運(yùn)算,最終得到的子代作為去噪后圖像。該方法充分利用兩個(gè)親本的優(yōu)勢,逐代進(jìn)化產(chǎn)生優(yōu)良個(gè)體,使去噪后圖像同時(shí)具有以上兩種方法的去噪優(yōu)勢。仿真結(jié)果表明,去噪后的紅外圖像相比于常規(guī)的去噪方法結(jié)果具有更高的信噪比和更小的最小均方誤差。針對現(xiàn)場所拍攝的紅外圖像所包含的信息繁多,為了能從復(fù)雜的背景中提取目標(biāo)物,本文提出了一種改進(jìn)的自適應(yīng)遺傳算法對電接觸紅外熱像進(jìn)行分割。該方法綜合考慮了適應(yīng)值與相似度的適應(yīng)度選擇,引入進(jìn)化因子,根據(jù)個(gè)體適應(yīng)度和進(jìn)化代數(shù)自動(dòng)調(diào)整交叉概率和變異概率。把圖像分割最佳閾值選取轉(zhuǎn)換成最優(yōu)問題,利用改進(jìn)算法的尋優(yōu)高效性求解最優(yōu)閾值實(shí)現(xiàn)圖像分割。仿真結(jié)果表明,新算法比常規(guī)的閾值分割算法更能清晰、完整地分割出目標(biāo)區(qū)域,并縮短了最佳閾值尋優(yōu)時(shí)間,提高圖像分割的質(zhì)量和速度。針對電接觸熱故障等級判別,本文設(shè)計(jì)了概率神經(jīng)網(wǎng)絡(luò)分類器。在綜合考慮了空氣污染指數(shù)、環(huán)境溫度以及紅外熱像的溫度信息基礎(chǔ)上,利用概率神經(jīng)網(wǎng)絡(luò)分類器建立了三類不同電接觸在不同空氣污染等級和不同環(huán)境溫度下與故障等級的映射關(guān)系。利用概率神經(jīng)網(wǎng)絡(luò)具有較強(qiáng)的容錯(cuò)能力和結(jié)構(gòu)自適應(yīng)性,實(shí)現(xiàn)了多個(gè)故障等級的準(zhǔn)確快速識別。
[Abstract]:Electrical contact refers to the electrical equipment and electrical circuit in all conductive connection parts, it has a large number, various types, high frequency of faults and so on. The state detection and fault diagnosis of electric contact is very important for the safe and stable operation of the whole power system. In this paper, a new method of electrical contact fault detection based on infrared thermal image feature and probabilistic neural network is studied. Three kinds of electric contact of hydraulic tension clamp and high pressure bushing general cap are studied and analyzed. On the basis of considering the influence of air pollution index and ambient temperature on the accuracy of the test results, the theory is presented. The experimental results show that the method is accurate and effective. In this paper, the high resolution infrared thermal imager is used to collect electrical contact images. In this paper, a genetic wavelet infrared thermal image denoising method based on Total Least SquaresTLS) estimation is proposed, in which the wavelet coefficients of the image are estimated by the total least square method, and the denoised image obtained by the wavelet inversion is used as the parent. Then genetic operation is carried out with the female parent obtained by Wiener filter, and the final offspring is used as the denoised image. This method makes full use of the advantages of the two parents and evolves to produce good individuals from generation to generation. The de-noised image has the advantages of the above two methods simultaneously. The simulation results show that, Compared with the conventional denoising method, the denoised infrared image has higher SNR and smaller minimum mean square error. The infrared image taken in the field contains a great deal of information, in order to extract the object from the complex background. In this paper, an improved adaptive genetic algorithm is proposed to segment the infrared thermal image of electric contact. The crossover probability and mutation probability are automatically adjusted according to individual fitness and evolutionary algebra. The optimal threshold selection of image segmentation is transformed into an optimal problem, and the optimal threshold is solved by the improved algorithm. The simulation results show that, Compared with the conventional threshold segmentation algorithm, the new algorithm can segment the target area more clearly and completely, shorten the optimal threshold searching time, and improve the quality and speed of image segmentation. In this paper, a probabilistic neural network classifier is designed. On the basis of considering the air pollution index, ambient temperature and the temperature information of infrared thermal image, Using probabilistic neural network classifier, the mapping relationship between three kinds of electrical contact and fault level under different air pollution levels and different ambient temperatures is established. The probabilistic neural network has strong fault tolerance and structural adaptability. The accurate and fast identification of multiple fault levels is realized.
【學(xué)位授予單位】：湖南大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2015
【分類號】：TM501.3

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 吳迎昌;羅滇生;何洪英;;基于TLS估計(jì)的遺傳小波紅外圖像去噪方法[J];計(jì)算機(jī)科學(xué);2015年04期

2 莫朝霞;陳沅江;;我國紅外熱像檢測技術(shù)的研究及發(fā)展展望[J];激光與紅外;2014年12期

3 周孝信;魯宗相;劉應(yīng)梅;陳樹勇;;中國未來電網(wǎng)的發(fā)展模式和關(guān)鍵技術(shù)[J];中國電機(jī)工程學(xué)報(bào);2014年29期

4 劉小平;;牽引變電所紅外熱成像溫度智能預(yù)警系統(tǒng)[J];工業(yè)控制計(jì)算機(jī);2014年04期

5 王國剛;;輸變電設(shè)備電接觸過熱及劣化機(jī)理研究進(jìn)展[J];電力建設(shè);2013年10期

6 吳濤;余海濤;戴永正;王鵬;張光來;;550kV高壓隔離開關(guān)熱穩(wěn)定性分析[J];高壓電器;2013年09期

7 張力娜;李小林;;一種基于小波變換的偏微分方程圖像去噪方法[J];激光與紅外;2013年08期

8 陳允;徐偉東;袁偉群;趙瑩;嚴(yán)萍;蘭國峰;;電磁發(fā)射中鋁電樞與不同材料導(dǎo)軌間的滑動(dòng)電接觸特性[J];高電壓技術(shù);2013年04期

9 崔玉勝;;國際電接觸會(huì)議的起源和發(fā)展[J];電工材料;2012年04期

10 鄧建鋼;郭濤;徐秋元;聶德鑫;程藻;程林;;變壓器繞組測溫光纖光柵傳感器設(shè)計(jì)及性能測試[J];高電壓技術(shù);2012年06期

，

本文編號：1518805