【摘要】：高壓斷路器在電力系統(tǒng)中起著極為重要的作用,它承擔著系統(tǒng)的控制和保護工作。在正常運行情況下,高壓斷路器控制線路和設(shè)備的投切操作;當發(fā)生故障時,則快速切斷故障線路,以防止故障的進一步擴大。因此一旦高壓斷路器發(fā)生故障,將直接危害系統(tǒng)的運行可靠性,并可能引起重大的停電損失。國內(nèi)外相關(guān)調(diào)查表明,斷路器大部分故障都是由機械原因造成的,因此開展高壓斷路器機械故障診斷的研究具有重要的現(xiàn)實意義。高壓斷路器分合閘動作期間產(chǎn)生的振動信號包含了重要的狀態(tài)信息,本文通過對斷路器振動信號進行處理和分析,來獲取高壓斷路器的機械狀態(tài)情況。其主要研究內(nèi)容包括信號采集、特征提取和狀態(tài)識別三個部分。首先,選擇合理的振動傳感器和信號采集設(shè)備,設(shè)計并搭建斷路器振動信號采集系統(tǒng)平臺,采集高壓斷路器在不同機械狀態(tài)下振動信號。其次,針對高壓斷路器振動信號的非平穩(wěn)、非線性特點,采用變分模態(tài)分解對斷路器振動信號進行時-頻分解處理,得到相應(yīng)的本征模態(tài)函數(shù),然后將得到的模態(tài)函數(shù)矩陣劃分為若干子矩陣以計算矩陣局部奇異值,并選擇各個子矩陣的最大奇異值作為故障診斷的特征向量。最后,構(gòu)建單類分類器和多類分類器聯(lián)合的多層分類器,采用兩層獨立的單類支持向量機分別用于準確區(qū)分高壓斷路器正常與故障狀態(tài)、已知故障類型和未知故障類型,在此基礎(chǔ)上,進一步采用支持向量機識別已知故障的具體故障類型。對SF6高壓斷路器在正常和三種典型故障下開展實例診斷測試,實驗結(jié)果表明,采用變分模態(tài)分解和局部奇異值分解方法能夠準確提取斷路器故障特征,而將單類分類器應(yīng)用到高壓斷路器機械故障診斷中能夠有效提高故障識別的準確率,從而提高了故障診斷的可靠性,具有較高的工程應(yīng)用價值。
[Abstract]:High-voltage circuit breaker plays an important role in the power system, it is responsible for the control and protection of the system. Under the normal operation condition, the high voltage circuit breaker controls the switching operation of the circuit and equipment; when the fault occurs, the fault line is cut off quickly to prevent the further expansion of the fault. Therefore, once the high voltage circuit breaker breaks down, it will directly endanger the reliability of the system, and may cause significant loss of power. The investigation at home and abroad shows that most of the faults of circuit breakers are caused by mechanical reasons, so it is of great practical significance to study the mechanical fault diagnosis of high voltage circuit breakers. The vibration signal generated during the switching operation of high voltage circuit breakers contains important state information. In this paper, the mechanical state of high voltage circuit breakers is obtained by processing and analyzing the vibration signals of circuit breakers. The main research contents include three parts: signal acquisition, feature extraction and state recognition. First of all, select reasonable vibration sensor and signal acquisition equipment, design and build the circuit breaker vibration signal acquisition system platform, collect high-voltage circuit breaker vibration signals in different mechanical states. Secondly, in view of the non-stationary and nonlinear characteristics of the vibration signals of high voltage circuit breakers, the variational mode decomposition is used to process the vibration signals of the circuit breakers by time-frequency decomposition, and the corresponding eigenmode functions are obtained. Then the modal function matrix is divided into several submatrices to calculate the local singular value of the matrix and the maximum singular value of each submatrix is selected as the eigenvector of fault diagnosis. Finally, a multi-layer classifier combined with single-class classifier and multi-class classifier is constructed. Two independent single-class support vector machines are used to accurately distinguish the normal and fault states of HV circuit breakers, known fault types and unknown fault types, respectively. On this basis, support vector machine (SVM) is used to identify the specific fault types of known faults. An example diagnosis test of SF6 high voltage circuit breaker under normal and three typical faults is carried out. The experimental results show that variational mode decomposition and local singular value decomposition can accurately extract the fault characteristics of the circuit breaker. The application of single-class classifier to mechanical fault diagnosis of high voltage circuit breakers can effectively improve the accuracy of fault identification, thus improving the reliability of fault diagnosis, and has a higher engineering application value.
【學位授予單位】：東北電力大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：TM561

【參考文獻】

相關(guān)期刊論文 前10條

1 武英杰;甄成剛;劉長良;;變分模態(tài)分解在風電機組故障診斷中的應(yīng)用[J];機械傳動;2015年10期

2 劉長良;武英杰;甄成剛;;基于變分模態(tài)分解和模糊C均值聚類的滾動軸承故障診斷[J];中國電機工程學報;2015年13期

3 唐貴基;王曉龍;;參數(shù)優(yōu)化變分模態(tài)分解方法在滾動軸承早期故障診斷中的應(yīng)用[J];西安交通大學學報;2015年05期

4 繆希仁;吳曉梅;石敦義;郭謀發(fā);王吳雨;;采用HHT振動分析的低壓斷路器合閘同期辨識[J];電工技術(shù)學報;2014年11期

5 郭謀發(fā);徐麗蘭;繆希仁;陳立純;;采用時頻矩陣奇異值分解的配電開關(guān)振動信號特征量提取方法[J];中國電機工程學報;2014年28期

6 孫一航;武建文;廉世軍;張路明;;結(jié)合經(jīng)驗?zāi)B(tài)分解能量總量法的斷路器振動信號特征向量提取[J];電工技術(shù)學報;2014年03期

7 梅飛;梅軍;鄭建勇;張思宇;朱克東;;粒子群優(yōu)化的KFCM及SVM診斷模型在斷路器故障診斷中的應(yīng)用[J];中國電機工程學報;2013年36期

8 常廣;王毅;王瑋;;采用振動信號零相位濾波時頻熵的高壓斷路器機械故障診斷[J];中國電機工程學報;2013年03期

9 徐建源;張彬;林莘;李斌;騰云;;能譜熵向量法及粒子群優(yōu)化的RBF神經(jīng)網(wǎng)絡(luò)在高壓斷路器機械故障診斷中的應(yīng)用[J];高電壓技術(shù);2012年06期

10 黃南天;徐殿國;劉曉勝;林琳;;基于模式相似性測度的電能質(zhì)量數(shù)據(jù)壓縮方法[J];電工技術(shù)學報;2011年10期

相關(guān)博士學位論文 前1條

1 董越;SF_6高壓斷路器在線監(jiān)測及振動信號的分析[D];上海交通大學;2008年

相關(guān)碩士學位論文 前1條

1 張佩;高壓斷路器機械故障診斷方法的研究[D];華北電力大學;2014年

，

本文編號：2339466