Page 184 - 《水资源与水工程学报》2023年第2期
P. 184

!34 " ! 2 #                       & ' ( ) & * + , -                               Vol.34No.2
               2023 $ 4 %               JournalofWaterResources&WaterEngineering                 Apr.,2023

            DOI:10.11705/j.issn.1672-643X.2023.02.23


              'Ö EEMDLSTMARIMAhY3ëd>cå÷˜AB



                                                ö÷ø, 0ù, —jú
                                           ( €Á\& 010É&`, äÐ LÊ 210098)
                 C D: ŒÔ•u~]œFŒ/êZLMˆ4‰Ëá¢.。ۛŒÔ Œílý7ëìˆ34, u5ˆŒÔè±
                 £wlúúX'Ÿ”—¸、 ¶h›Ä,¹5, Gf'›“ ³" 4Ý ¢˜” ˆRzÝtÀ]œFŒÔtuˆ EEMD
                 LSTMARIMA­®。mò÷f̘Íx­o³"(EEMD) $±£wl¹º•–®Ž, Ük®ä*þã-ÍEI
                 (LSTM) $®Ž‘ˆ¹º³Ÿ•–tu, ڱǘµ³#–sTF”¬E7(ARIMA) •–¥µ/{, ¢˜ LSTMÓ
                 ARIMAˆtuÇÈ, 4ݏŒE•tu­®。Ðe‰‰uvO“ˆ]œF23Gû, ݎ-€:F›†Œ±Õ 2
                 Â^®u5ˆwuŒÔèwlG6C$‡•–Îfx¼。ÇÈÉÊ: (m›ê.ˆ LSTM­®Ó ARIMA­®, E
                 •­®ˆ”¬Ž$[µ MAE、 ¬E[µ MSE、 ¬EÜ[µ RMSE¬G 3 ½­®iˆÔ9è, tuuÊà`›·ý
                2 ½­®, ¿­®G]œFŒÔˆu;tu³¿®¯À*{ñ。
                 >EF: ]œF; ŒÔtu; ̘Íx­o³"; ®ä*þã-ÍEI; µ³#–sTF”¬
                 GHIJK:TV641   LMNOP:A    LQRK:1672643X(2023)02018006

                       Seepageporewaterpressurepredictionmodelofearth-rock
                                     damsbasedonEEMDLSTMARIMA

                                      CENWeijun,WANGXiaoxin,JIANGMinghuan
                       (CollegeofWaterConservancyandHydropowerEngineering,HohaiUniversity,Nanjing210098,China)

                 Abstract:Seepagemonitoringisoneoftheimportantcontentsofseepagesafetyevaluationofearth-rock
                 dams.Theseepageporewaterpressureisaffectedbymultipleexternalfactors ,sothetimeseriesofseep
                 ageporewaterpressureatmeasuringpointsisoftencharacterizedbynonstationarityandlocalabrupt
                 changes.Regardingtothis ,theEEMDLSTMARIMAmodelforseepageporewaterpressureprediction
                 ofearth-rockdamsisconstructedaccordingtotheconceptofdecomposition-reconstruction-combina
                 tion.Firstly ,thetimeseriesfeaturesaredecomposedbytheensembleempiricalmodedecomposition
                 (EEMD),andtheextractedfeaturecomponentsarepredictedbythelongshorttermmemory(LSTM)
                 neuralnetwork.Atthesametime,theresidualerroriscorrectedbytheautoregressiveintegratedmoving
                 average (ARIMA),andtheimprovedpredictionmodelisreconstructedbycombiningthepredictionre
                 sultsofLSTMandARIMA.Takinganearth-rockdamonadeepoverburdenasanexample,themeas
                 uredseepageporewaterpressureseriesoftwotypicalmeasuringpointsbehindthecutoffwallofthemain
                 riverbeddamareselectedastheresearchobjectsforapplicationverification.Theresultsshowthat ,com
                 paredwiththesingleLSTM modelandARIMAmodel ,themeanabsoluteerror,themeansquareerror
                 andtherootmeansquareerroroftheproposedpredictionmodelarethesmallest,andthepredictionac
                 curacyoftheproposedmodelisobviouslysuperiortotheothertwomodels.Therefore ,theproposedmod
                 elcanprovideanewapproachforaccuratepredictionandanalysisofseepageporewaterpressureof
                 earth-rockdams.
                 Keywords:earth-rockdam;porewaterpressureprediction;ensembleempiricalmodedecomposition(EE
                 MD);longshorttermmemory(LSTM)neuralnetwork;autoregressiveintegratedmovingaverage(ARIMA)


                !"#$:20220722; %&#$:20220914
                '()*: uv#$%&'()*(51979089、51679073)
                +,-.: á$—(1977—), ë, ^äâL@, AB, PQ, ABDST, 6CEFG]œFù_23Œ/êZ。
   179   180   181   182   183   184   185   186   187   188   189