【摘要】：變壓器是電力系統(tǒng)關(guān)鍵設(shè)備之一,其運(yùn)行狀況對(duì)電網(wǎng)的安全、穩(wěn)定運(yùn)行具有重要影響。變壓器表面振動(dòng)信號(hào)中包含著豐富的變壓器狀態(tài)信息,國(guó)內(nèi)外學(xué)者對(duì)基于振動(dòng)分析的變壓器在線監(jiān)測(cè)和故障診斷技術(shù)做了大量研究,并取得了許多研究成果。變壓器振動(dòng)基頻(100Hz)幅值大小是分析和評(píng)判變壓器運(yùn)行狀態(tài)和故障診斷的重要依據(jù),但由于多種因素的影響,理論分析正常運(yùn)行中變壓器表面振動(dòng)的基頻幅值困難諸多,尚沒有成熟的基于基頻幅值的變壓器狀態(tài)監(jiān)測(cè)方法。本文針對(duì)變壓器表面振動(dòng)信號(hào)采集和分析實(shí)際需求,結(jié)合已有研究結(jié)果,分析探討了傳感器的選型、振動(dòng)測(cè)點(diǎn)的選擇以及采集參數(shù)等問題,設(shè)計(jì)實(shí)現(xiàn)了一套便攜式振動(dòng)信號(hào)采集系統(tǒng),完成了多臺(tái)次運(yùn)行中變壓器表面振動(dòng)數(shù)據(jù)的采集;對(duì)變壓器表面振動(dòng)實(shí)測(cè)數(shù)據(jù)進(jìn)行了頻域分析和能量分析,并結(jié)合運(yùn)行電壓和負(fù)載電流數(shù)據(jù),分析了振動(dòng)信號(hào)基頻幅值與運(yùn)行工況的關(guān)系,結(jié)果表明基頻幅值大小受多重因素復(fù)雜影響,實(shí)測(cè)值與理論計(jì)算值差異顯著;本文給出一種基于廣義回歸神經(jīng)網(wǎng)絡(luò)(GRNN)的基頻幅值預(yù)測(cè)方法,用于正常運(yùn)行狀態(tài)下的變壓器表面振動(dòng)基頻幅值預(yù)測(cè)。根據(jù)變壓器運(yùn)行電壓、負(fù)載電流、油溫等運(yùn)行工況數(shù)據(jù)以及表面振動(dòng)歷史數(shù)據(jù)進(jìn)行網(wǎng)絡(luò)訓(xùn)練,訓(xùn)練后的網(wǎng)絡(luò)可根據(jù)實(shí)時(shí)運(yùn)行數(shù)據(jù)預(yù)測(cè)變壓器表面振動(dòng)基頻幅值。運(yùn)行中變壓器表面振動(dòng)實(shí)測(cè)信號(hào)分析表明,本文方法比原有方法預(yù)測(cè)精度高,可為基于振動(dòng)的變壓器在線監(jiān)測(cè)提供參考。最后本文給出一種典型樣本篩選方法,首先基于模糊熵理論計(jì)算特征權(quán)重,然后根據(jù)運(yùn)行工況數(shù)據(jù)間的加權(quán)歐氏距離對(duì)訓(xùn)練樣本進(jìn)行篩選,實(shí)測(cè)數(shù)據(jù)分析表明該方法可以顯著壓縮訓(xùn)練數(shù)據(jù),降低數(shù)據(jù)冗余,提高網(wǎng)絡(luò)訓(xùn)練速度和計(jì)算速度。
[Abstract]:Transformer is one of the key equipments in power system. The vibration signal of transformer surface contains abundant transformer state information. Many researches have been done on on-line monitoring and fault diagnosis of transformer based on vibration analysis, and many research results have been achieved. The amplitude of transformer vibration base frequency (100Hz) is an important basis for analyzing and judging transformer operation state and fault diagnosis. However, due to the influence of many factors, it is difficult to analyze the fundamental frequency amplitude of transformer surface vibration in normal operation. There is no mature transformer condition monitoring method based on fundamental frequency amplitude. In this paper, according to the actual demand of vibration signal acquisition and analysis on transformer surface, combined with the existing research results, the selection of sensor, the selection of vibration measuring points and the acquisition parameters are analyzed and discussed. A portable vibration signal acquisition system is designed and implemented. The frequency domain analysis and energy analysis of the measured data of transformer surface vibration are carried out, and the relationship between the fundamental frequency amplitude of vibration signal and the operating condition is analyzed by combining the data of operating voltage and load current. The results show that the amplitude of the fundamental frequency is affected by many complex factors, and there is a significant difference between the measured value and the theoretical value. In this paper, a prediction method of fundamental frequency amplitude based on generalized regression neural network (GRNN) is presented, which can be used to predict the fundamental frequency amplitude of transformer surface vibration under normal operation. Network training is carried out according to the operating condition data of transformer operating voltage, load current, oil temperature and history data of surface vibration. The trained network can predict the fundamental frequency amplitude of transformer surface vibration based on real-time operation data. The analysis of the measured signals of transformer surface vibration in operation shows that the proposed method is more accurate than the original method and can be used as a reference for on-line monitoring of transformers based on vibration. Finally, a typical sample selection method is presented. Firstly, the feature weights are calculated based on the fuzzy entropy theory, and then the training samples are screened according to the weighted Euclidean distance between the operating condition data. The analysis of measured data shows that this method can significantly compress the training data, reduce the data redundancy, and improve the training speed and computing speed of the network.
【學(xué)位授予單位】：華北電力大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TM41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 王廣庭;李陽海;楊濤;蘇世瑋;趙家毅;;基于振動(dòng)信號(hào)分析的變壓器故障診斷研究進(jìn)展[J];噪聲與振動(dòng)控制;2016年05期

2 陳偉根;萬福;顧朝亮;鄒經(jīng)鑫;漆薇;王品一;;變壓器油中溶解氣體拉曼剖析及定量檢測(cè)優(yōu)化研究[J];電工技術(shù)學(xué)報(bào);2016年02期

3 周科峰;葉婷;;南京電網(wǎng)變壓器油色譜在線監(jiān)測(cè)的應(yīng)用探討[J];電工技術(shù);2016年01期

4 王春寧;耿志慧;馬宏忠;金基平;李凱;;基于振動(dòng)的電力變壓器鐵心松動(dòng)故障診斷研究[J];高壓電器;2015年12期

5 陳東超;徐婧;洪瑞新;顧煜炯;何成兵;;基于廣義回歸神經(jīng)網(wǎng)絡(luò)的旋轉(zhuǎn)機(jī)械振動(dòng)特征預(yù)測(cè)[J];汽輪機(jī)技術(shù);2015年05期

6 馬宏忠;周宇;李凱;許洪華;王濤云;;基于振動(dòng)的變壓器繞組壓緊狀態(tài)評(píng)估方法[J];電力系統(tǒng)自動(dòng)化;2015年18期

7 朱葉葉;汲勝昌;張凡;劉勇;董鴻魁;崔志剛;吳佳瑋;;電力變壓器振動(dòng)產(chǎn)生機(jī)理及影響因素研究[J];西安交通大學(xué)學(xué)報(bào);2015年06期

8 林U，

本文編號(hào)：2412247