





摘"要:變壓器狀態(tài)對(duì)于智能配電房的安全穩(wěn)定運(yùn)行具有重要意義。為實(shí)現(xiàn)對(duì)變壓器故障的準(zhǔn)確診斷,在變壓器油中溶解氣體分析(DGA)的基礎(chǔ)上,提出了一種聯(lián)合使用支持向量數(shù)據(jù)描述(SVDD)和改進(jìn)KMeans聚類的變壓器故障診斷方法。首先利用SVDD構(gòu)造閉合分類曲面實(shí)現(xiàn)“正?!焙汀肮收稀眱深惻袛啵缓髮?duì)“故障”類樣本進(jìn)行K-Means聚類分析,自動(dòng)將其劃分為低能放電、中低溫過熱、高能放電、高溫過熱和局部放電5種故障類型,同時(shí)針對(duì)KMeans初始聚類中心選取難題,提出局部密度概念自動(dòng)確定KMeans初始聚類中心,提升聚類性能。最后利用變壓器故障真實(shí)數(shù)據(jù)開展實(shí)驗(yàn),結(jié)果表明,相較于支持向量機(jī)(SVM)和BP神經(jīng)網(wǎng)絡(luò)模型,所提方法的故障診斷準(zhǔn)確率分別提升9.8%和8%。
關(guān)鍵詞:智能配電房;變壓器故障診斷;油中溶解氣體分析;支持向量數(shù)據(jù)描述;多分類器聯(lián)合
中圖分類號(hào):TM41""""""文獻(xiàn)標(biāo)識(shí)碼:A
Transformer"Fault"Diagnosis"Model"Based"
on"SVDD"and"Improved"KMeans
XIE"Xuqin,"LIU"Quanhui,"ZHAO"Xiangwen,"ZHANG"Qingsong,"LIN"Jianxiong,"ZHANG"Fan"
(Guangzhou"Zengcheng"Power"Supply"Burea,China"Southern"Power"Grid"Co.,"Ltd.,Guangzhou,"Guangdong"510000,"China)
Abstract:The"operation"status"of"transformer"is"of"great"significance"to"the"stability"and"reliability"of"intelligent"distribution"room."In"order"to"realize"the"accurate"diagnosis"of"transformer"faults,"based"on"the"analysis"of"dissolved"gases"in"transformer"oil,"a"multiclassifier"joint"fault"diagnosis"method"based"on"the"combined"use"of"support"vector"data"description"(SVDD)"and"improved"KMeans"clustering"is"proposed."First,"SVDD"is"used"to"construct"a"closed"classification"surface"to"realize"“normal”"and"“fault”"judgments."Then"KMeans"clustering"analysis"is"carried"out"on"the"“fault”"samples,"which"are"automatically"divided"into"five"types:"low"energy"discharge,"medium"and"low"temperature"overheat,"high"energy"discharge,"high"temperature"overheat"and"partial"discharge."At"the"same"time,"the"concept"of"local"density"is"proposed"to"automatically"determine"the"initial"clustering"center"of"KMeans"to"improve"the"clustering"performance."Finally,"the"transformer"fault"data"of"the"intelligent"distribution"room"is"used"to"carry"out"the"verification"experiment."The"results"show"that"compared"with"the"traditional"support"vector"machine"(SVM)"and"BP"neural"network"model,"the"fault"diagnosis"accuracy"of"the"proposed"method"is"improved"by"9.8%"and"8%,respectively.
Key"words:"intelligent"distribution"room;"transformer"fault"diagnosis;"analysis"of"dissolved"gas"in"oil;"support"vector"data"description;"multiclassifier"association
電力變壓器是智能配電房進(jìn)行能量轉(zhuǎn)換和傳輸?shù)暮诵脑O(shè)備,其運(yùn)行狀態(tài)對(duì)于智能配電房至關(guān)重要,是決定智能配電房安全、可靠和穩(wěn)定運(yùn)行的關(guān)鍵[1]。然而變壓器運(yùn)行工況和運(yùn)行環(huán)境較為復(fù)雜,長(zhǎng)時(shí)間運(yùn)行導(dǎo)致的繞組變形和絕緣老化等原因都可能會(huì)引發(fā)變壓器故障,給人民群眾的生命財(cái)產(chǎn)安全帶來隱患。因此,建立變壓器故障診斷模型,從而實(shí)現(xiàn)對(duì)變壓器運(yùn)行狀態(tài)的實(shí)時(shí)準(zhǔn)確監(jiān)控對(duì)于智能配電房具有重要意義[2]。
目前絕大多數(shù)變壓器都采用油紙組成的絕緣結(jié)構(gòu),當(dāng)變壓器發(fā)生故障時(shí),絕緣材料會(huì)產(chǎn)生各種氣體,且不同故障產(chǎn)生的氣體成分和濃度不同,因此通過油中溶解氣體分析(dissolved"gas"analysis,"DGA)可以實(shí)現(xiàn)對(duì)變壓器不同故障類型的診斷[3]?!?br>