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NRS的GWO-SVM變壓器故障診斷方法研究

來源:電工電氣發(fā)布時間:2022-02-28 11:28 瀏覽次數(shù):621

基于NRS的GWO-SVM變壓器故障診斷方法研究

徐偉進1,徐煒彬1,張煒華1,李想1,吳振2
(1 國網(wǎng)吉林省電力有限公司長春供電公司,吉林 長春 130000;
2 長春工業(yè)大學 電氣與電子工程學院,吉林 長春 130012)
 
    摘 要:針對油中溶解氣體分析法 (DGA) 不能有效反映變壓器的不同故障且診斷準確率低的問題,通過鄰域粗糙集 (NRS) 對變壓器故障數(shù)據(jù)比值進行約簡,得出一組新比值作為診斷樣本,進而利用灰狼算法 (GWO) 與支持向量機 (SVM) 結合的模型進行故障診斷。實驗分析表明,利用 NRS 對變壓器故障數(shù)據(jù)約簡能夠有效提高變壓器故障準確率,同時驗證了 GWO-SVM 模型對于變壓器故障診斷的良好適用性。
    關鍵詞:變壓器;故障診斷;鄰域粗糙集;支持向量機;灰狼算法
    中圖分類號:TM407     文獻標識碼:A     文章編號:1007-3175(2022)02-0009-05
 
Research on GWO-SVM Transformer Fault
Diagnosis Method Based on NRS
 
XU Wei-jin1, XU Wei-bin1, ZHANG Wei-hua1, LI Xiang1, WU Zhen2
(1 Changchun Power Supply Company, State Grid Jilin Electric Power Co., Ltd, Changchun 130000, China;
2 School of Electrical and Electronic Engineering, Changchun University of Technology, Changchun 130012, China)
 
    Abstract: Dissolved gas analysis (DGA) in oil cannot reflect the different faults of the transformer effectively, and the diagnosis accuracy is low. This paper simplified the ratio of transformer fault data by using neighborhood rough set (NRS) to solve this problem. It derived a new set of ratios as a diagnostic sample from the simplified data.Furthermore, it used the gray wolf optimize (GWO) combined with the support vector machine (SVM) model for fault diagnosis.The experiment analysis shows that the use of NRS to simplify transformer fault data could effectively improve the accuracy of transformer faults. At the same time, it verifies the applicability of the GWO-SVM model for transformer fault diagnosis.
    Key words: transformer; fault diagnosis; neighborhood rough set; support vector machine; gray wolf optimize
 
參考文獻
[1] 陳小玉. 改進的神經(jīng)網(wǎng)絡在變壓器故障診斷中的應用[J]. 計算機仿真,2012,29(8) :318-321.
[2] DUVAL M, DEPABLA A.Interpretation of gas-inoil analysis using new IEC publication 60599 and IEC TC 10 databases[J].IEEE Electrical Insulation Magazine,2001,17(2) :31-41.
[3] 汪可,李金忠,張書琦,等. 變壓器故障診斷用油中溶解氣體新特征參量[J] . 中國電機工程學報,2016,36(23) :6570-6578.
[4] ROGERS R R.IEEE and IEC codes to interpret incipient faults in transformers, using gas in oil analysis[J].IEEE Transactions on Electrical Insulation,2007,13(5) :349-354.
[5] International Electrotechnical Commission.Mineral oil-impregnated electrical equipment in service—Guide to the interpretation of dissolved and free gases analysis :IEC 60599-1999[S].Geneva :International Electrotechnical Commission Publication,1999 :1-25.
[6] 電力行業(yè)電力變壓器標準化技術委員會. 變壓器油中溶解氣體分析和判斷導則:DL/T 722—2014[S] .北京:中國電力出版社,2007 :3-9.
[7] 楊志超,張成龍,吳奕,等. 基于粗糙集和 RBF 神經(jīng)網(wǎng)絡的變壓器故障診斷方法研究[J] . 電測與儀表,2014,51(21) :34-39.
[8] 陳歡,彭輝,舒乃秋,等. 基于蝙蝠算法優(yōu)化最小二乘雙支持向量機的變壓器故障診斷[J] . 高電壓技術,2018,44(11) :3664-3671.
[9] 鄭蕊蕊,趙繼印,趙婷婷,等. 基于遺傳支持向量機和灰色人工免疫算法的電力變壓器故障診斷[J].中國電機工程學報,2011,31(7) :56-63.
[10] 樊浩,李興文,蘇海博,等. 基于主成分分析-支持向量機優(yōu)化模型的斷路器故障診斷方法研究[J].高壓電器,2020,56(6) :143-151.
[11] 吳廣寧,袁海滿,宋臻杰,等. 基于粗糙集與多類支持向量機的電力變壓器故障診斷[J] . 高電壓技術,2017,43(11) :3668-3674.
[12] 周光宇,馬松齡. 基于機器學習與 DGA 的變壓器故障診斷及定位研究[J] . 高壓電器,2020,56(6) :262-268.
[13] 胡清華,趙輝,于達仁. 基于鄰域粗糙集的符號與數(shù)值屬性快速約簡算法[J] . 模式識別與人工智能,2008,21(6) :732-738.
[14] 胡清華,于達仁,謝宗霞. 基于鄰域?;痛植诒平臄?shù)值屬性約簡[J] . 軟件學報,2008,19(3) :640-649.
[15] 張鐿議,焦健,汪可,等. 基于帝國殖民競爭算法優(yōu)化支持向量機的電力變壓器故障診斷模型[J] .電力自動化設備,2018,38(1) :99-104.
[16] 李春茂,周妺末,劉亞婕,等. 基于鄰域粗糙集與多核支持向量機的變壓器多級故障診斷[J] . 高電壓技術,2018,44(11) :3474-3482.
[17] MIRJALILI S, MIRJALILI S M, LEWIS A.Grey wolf optimizer[J].Advances in Engineering Software,2014,69(3) :46-61.
[18] 趙洛印,李忠誠,王丹,等. 基于 GWO-SVM 的電壓暫降擾動源識別[J]. 電測與儀表,2019,56(23) :76-85.