<dd id="mimiw"><samp id="mimiw"></samp></dd>

<address id="mimiw"><nav id="mimiw"><delect id="mimiw"></delect></nav></address>

    Suzhou Electric Appliance Research Institute
    期刊號: CN32-1800/TM| ISSN1007-3175

    Article retrieval

    文章檢索

    首頁 >> 文章檢索 >> 往年索引

    基于多源數(shù)據(jù)融合的變壓器典型故障診斷模型研究

    來源:電工電氣發(fā)布時間:2023-07-27 12:27 瀏覽次數(shù):308

    基于多源數(shù)據(jù)融合的變壓器典型故障診斷模型研究

    胡晨1,尹恩韜1,樂健2
    (1 國網(wǎng)江西省電力有限公司吉安供電公司,江西 吉安 343000;
    2 武漢大學 電氣與自動化學院,湖北 武漢 430072)
     
        摘 要:準確評估輸變電設備運行狀態(tài)是電力企業(yè)生產(chǎn)技術(shù)工作的核心內(nèi)容。為提高電力變壓器故障診斷精度,對典型變壓器故障特征理論進行研究,建立了區(qū)內(nèi)和區(qū)外的故障仿真模型,在此基礎上提出了基于多源數(shù)據(jù)融合的變壓器典型故障診斷模型。模型采用小波包分析法提取故障特征量,并進行特征融合。實驗結(jié)果表明,所提的變壓器故障判別策略判斷結(jié)果更加精確且診斷時間較快。
        關(guān)鍵詞: 變壓器;故障診斷;數(shù)據(jù)特征;數(shù)據(jù)融合
        中圖分類號:TM407     文獻標識碼:A     文章編號:1007-3175(2023)07-0041-05
     
    Research on Typical Fault Diagnosis Model of
    Transformers Based on Multi-Source Data Fusion
     
    HU Chen1, YIN En-tao1, LE Jian2
    (1 Ji’an Power Supply Company of Jiangxi Electric Power Co., Ltd, Ji’an 343000, China;
    2 School of Electrical Engineering and Automation, Wuhan University, Wuhan 430072, China)
     
        Abstract: Accurate evaluation of operation status of power transmission and transformation equipments is the core of production technology for electric power enterprises. In order to improve the accuracy of power transformer fault diagnosis, the paper makes research on typical transformer fault characteristics theories, builds fault simulation models in and out of the region, and then puts forward a typical faults diagnosis model of transformers based on multi-source data fusion. This model adopts the wavelet packet analysis method to extract fault characteristic quantity and makes them fused. According to the experimental results, this transformer fault diagnosis strategy is more accurate with less diagnosis time.
        Key words: transformer; fault diagnosis; data characteristics; data fusion
     
    參考文獻
    [1] 劉云鵬,和家慧,許自強,等.基于 SVM SMOTE 的電力變壓器故障樣本均衡化方法[J].高電壓技術(shù),2020,46(7):2522-2529.
    [2] 方健,楊帆,童銳,等. 基于紅外圖像處理和半監(jiān)督學習的變壓器故障診斷方法[J] . 全球能源互聯(lián)網(wǎng)(英文版),2021,4(6):596-607.
    [3] 李兵,韓睿,何怡剛,等.改進隨機森林算法在電機軸承故障診斷中的應用[J].中國電機工程學報,2020,40(4):1310-1319.
    [4] 唐文虎,牛哲文,趙柏寧,等. 數(shù)據(jù)驅(qū)動的人工智能技術(shù)在電力設備狀態(tài)分析中的研究與應用[J] .高電壓技術(shù),2020,46(9):2985-2999.
    [5] ZHANG C , TAN K C , LI H , et a1. Acost-sensitive deep belief network for imbalanced classification[J].IEEE Transactions on Neural Networks and Learning Systems,2019,30(1):109-122.
    [6] 陳顥,王伏亮,李澄,等. 基于 KPCA-LSSVM 的智能斷路器故障診斷方法研究[J] . 自動化儀表,2021,42(12):19-22.
    [7] 陳如清,李嘉春,尚濤,等. 改進煙花算法和概率神經(jīng)網(wǎng)絡智能診斷齒輪箱故障[J] . 農(nóng)業(yè)工程學報,2018,34(17):192-198.
    [8] 畢建權(quán),鹿鳴明,郭創(chuàng)新,等. 一種基于多分類概率輸出的變壓器故障診斷方法[J].電力系統(tǒng)自動化,2015,39(5):88-93.
    [9] 蘇磊,陳璐,徐鵬,等. 基于 GRNN 和 KPCA 組合模型的變壓器油中氣體體積分數(shù)短期預測[J] . 高壓電器,2021,57(1):82-88.
    [10] 陳鐵,呂長欽,張欣,等. 基于 KPCA-WPA-SVM 的變壓器故障診斷模型[J] . 電測與儀表,2021,58(4):158-164.
    [11] 吳君,丁歡歡,馬星河,等. 改進自適應蜂群優(yōu)化算法在變壓器故障診斷中的應用[J] . 電力系統(tǒng)保護與控制,2020,48(9):174-180.
    [12] 吳杰康,覃煒梅,梁浩浩,等. 基于自適應極限學習機的變壓器故障識別方法[J] . 電力自動化設備,2019,39(10):181-186.
    [13] HEIDARI A A, MIRJALILI S, FARIS H,et al.Harris hawks optimization:Algorithm and applications[J].Future Generation Computer Systems,2019,97:849-872.
    [14] SAHRI Z B , YUSOF R B . Support vector machine-based fault diagnosis of power transformer using k nearest-neighbor imputed DGA dataset [J] . Journal of Computer & Communications,2014,2(9):22-31.
    [15] 楊凌霄,朱亞麗. 基于概率神經(jīng)網(wǎng)絡的高壓斷路器故障診斷[J] . 電力系統(tǒng)保護與控制,2015,43(10):62-67.

     

    亚洲无码av成人在线,亚洲影院AV无码一区二区,亚洲无码第二页,成人无码AV网站在线观看不卡 (function(){ var bp = document.createElement('script'); var curProtocol = window.location.protocol.split(':')[0]; if (curProtocol === 'https') { bp.src = 'https://zz.bdstatic.com/linksubmit/push.js'; } else { bp.src = 'http://push.zhanzhang.baidu.com/push.js'; } var s = document.getElementsByTagName("script")[0]; s.parentNode.insertBefore(bp, s); })();