資源描述:
《基于Markov特征的油氣管道泄漏檢測與定位方法.pdf》由會員上傳分享,免費在線閱讀,更多相關(guān)內(nèi)容在行業(yè)資料-天天文庫。
1、第38卷第4期儀器儀表學報Vol38No42017年4月ChineseJournalofScientificInstrumentApr.2017基于Markov特征的油氣管道泄漏檢測與定位方法劉金海,臧東,汪剛(東北大學信息科學與工程學院沈陽110004)摘要:針對傳統(tǒng)的基于壓力信號的管道泄漏檢測方法誤報率和漏報率偏高,同時定位誤差較大的缺點,設(shè)計了一種基于Markov特征的管道泄漏檢測與定位方法。首先,將管道壓力數(shù)據(jù)構(gòu)造為Markov鏈的形式,并提取其動態(tài)特征;然后,將所提取的特征應用于NeymanPearson異常檢測方法之中,檢測全部壓力數(shù)據(jù)樣本的狀態(tài),并對檢測
2、到的異常樣本進行同源信號匹配,修正檢測結(jié)果;最后,將相似性定位方法與連續(xù)小波定位方法結(jié)合,確定管道首末兩端響應壓力變化的時間差,并根據(jù)管道長度和壓力波傳輸速度等信息,對泄漏源定位。所提方法能應用于小泄漏和緩慢泄漏的檢測與定位,易于實現(xiàn),誤報率與漏報率顯著降低,定位精度提高。通過對歷史數(shù)據(jù)的分析,驗證了所提方法的可行性和有效性。關(guān)鍵詞:油氣管道;Markov鏈;NeymanPearson異常檢測;相似性定位;連續(xù)小波定位中圖分類號:TH878TH865TE832TE88文獻標識碼:A國家標準學科分類代碼:440.55Leakagedetectionandlocationmet
3、hodofoilandgaspipelinesbasedonMarkovfeaturesLiuJinhai,ZangDong,WangGang(SchoolofInformationScienceandEngineering,NortheasternUniversity,Shenyang110004,China)Abstract:Aimingatshortcomingsoftraditionalleakagedetectionmethodsbasedonpressuresignal,suchashighfalsepositiverateandfalsenegativerate
4、,andlargelocationerror,aleakagedetectionandlocationmethodofoilandgaspipelinebasedonMarkovfeatureisdesigned.Firstofall,aMarkovchainisbuiltfromthepipelinepressuredata,atthesametime,thedynamicfeaturesareextracted;then,inordertodetectallpressuredatasamplestates,theNeymanPearsonanomalydetection
5、methodisappliedtothedynamicfeatures;meanwhile,thedetectionresultsarecorrectedthroughcheckingwhetherthedetectedabnormalsamplesarematchingwiththesamesourcesignal;last,similaritylocationmethodandcontinuouswaveletlocationmethodarecombinedtodeterminethetimedifferenceofthepressurechangesatbothend
6、softhepipe,andtheleakageislocatedaccordingtheinformationofpipelinelengthandpressurewavetransmissionspeed.Themethodpresentedinthispapercanbeusedinthedetectionandlocalizationoflittleleakageandslowleakage,iseasytoimplement;moreover,thefalsepositiverateandfalsenegativeratearesignificantlydecrea
7、sed,thepositioningaccuracyisimproved.Thehistoricaldataanalysisverifiestheeffectivenessandfeasibilityoftheproposedmethod.Keywords:oilandgaspipeline;Markovchain;NeymanPearsonanomalydetection;similaritylocation;continuouswaveletlocation氣管道故障的有效檢測和及時處理已迫在眉睫