Page 125 - 2025年第56卷第2期
P. 125

culttoachieveintelligentwaterdistributiontasksincanalsystems.Therefore,asetofmeasurement - controlgatee
                  quipmentthatcanaccuratelymeasuretheoutletflowofthefinalchannelisdeveloped.Toachieveaccuratemonito
                  ringoftheflowthroughthegatestructure ,thispaperanalyzesthehydrauliccharacteristicsofthemeasurement -
                  controlgateandidentifiestheflowpatternatdifferentopenings (e)ofthegate.Then,basedontheBuckingham
                  theorem andtheleastsquaremethod ,theflowmeasurementmodelofthegatestructureisestablished.Finally,the
                  accuracyofthemodelisanalyzedandevaluated.Theresultsshowthatwhentherelativeopeningofthemeasure
                  ment - controlgateisrelativelyhigh,theflowthroughthegateisweirflow,andviceversa,itisorificeflow.The
                  criticalrelativeopening(e?H) c ofthecriticalrelativeopeningofthetwoflowpatternsis1.033.Theaveragerelative
                  errorofthedischargecalculationmodelconstructedfordifferentgateopeningsis4.7%,whichis26.3% moreaccu
                  ratethantheflowmeasurementequationforrectangularthin - plateweirs.Theerroroftheorificeflowmodelisless
                  than2.9%.Whene?H c >0.14,theflowisclassifiedasalargeorificeflowwithadischargecoefficientof0.7,oth
                  erwise,itisasmallorificeflowwithadischargecoefficientof0.846.Theresearchresultscanprovideareference
                  fortheaccuracyimprovementoftheintelligentgateflowmonitoringtechnologyoftheirrigationchannel.
                  Keywords:measurement - controlsluicegate;dischargecoefficient;dimensionalanalysis;precisionevaluation;
                  terminalirrigationchannelflowmeasurement


                                                                                    (责任编辑:王 婧)


              (上接第 252页)
                             Researchonstreamflowintervalpredictionbasedondeeplearning
                                               ensembleoptimizationmodel
                                              1
                                                                          2
                                                              1
                                HUANGJinghan,WANGZhaocai,WUJunhao,YAOZhiyuan             1
                                 (1.CollegeofInformation,ShanghaiOceanUniversity,Shanghai 201306,China;
                        2.StateKeyLaboratoryofEstuarineCoastalScience,EastChinaNormalUniversity,Shanghai 200241,China)

                  Abstract:Duetotheincreasingoccurrenceofextremeweathereventsandthecomplexityofstreamflowvaria
                  tions ,itischallengingtorealizeaccuratestreamflowprediction,andpreviousstudiesaremostlybasedonpoint
                  predictionofdeterminatevalues,whichishardtotakeintoaccounttheeffectofuncertaintyandleadtothelack
                  ofpracticalapplicabilityofthepredictionresults.Inthisstudy ,adeeplearningensemblemodelforstreamflow
                  intervalpredictionbasedonmeteorologicalandhydrologicalvariablesisdeveloped.Themodelfirstfiltersoutthe
                  keydrivingvariablesaffectingstreamflowthroughthePearsoncorrelationcoefficient (PCC).Thentherawdata
                  aredecomposedintointrinsicmodefunctions(IMFs)byvariationalmodaldecomposition(VMD).Thecompo
                  nentsare then quadratically decomposed using complementary ensemble empiricalmodaldecomposition
                  (CEEMD)tocapturemoredetailsofthedata.Thepointpredictionresultsofstreamflowareobtainedbyagated
                  recurrentunit (GRU)incorporatinganattentionmechanism (AM),andanimprovedsparrowsearchalgorithm
                  (ISSA)isusedtooptimizehyperparameterssuchasthelearningrateoftheGRUandthenumberofhiddenlayer
                  dimensionstoenhancethemodelperformance.Finally,nonparametrickerneldensityestimation(NKDE)isin
                  troducedforintervalprediction.ThecombinedmodelVMD - CEEMD - ISSA - AM- GRU(VCIAG)constructedin
                  thisstudyperformsadvancemulti - periodpredictionforninehydrologicalstationsintheJialingRiverbasin.The
                  resultsofthestudyshowedthatthemodelperformswellintheshortterm,withNashefficiencycoefficients
                  (NSE)closeto1forseveralstations.Forfloodforecasting,themodel’sNSEforDongjintuo,Wusheng,and
                  Jinxistationsare0.73,0.92,and0.92,respectively.Inaddition,theeffectsoftheinputvariablesonrunoff
                  arequantifiedbytheShapleyvaluemethod(Shapley).TheVCIAGmodelproposedinthisstudynotonlyper
                  formswellinstreamflowpredictionaccuracy,butalsohassignificantadvantagesinintervalpredictionofuncer
                  tainty ,whichcanprovidemanagerswithmoreaccurateandreliablerunoffinformation,andthusbettersupport
                  runoffriskassessmentandscientificdecision - makingprogramsinpractice.
                  Keywords:deeplearningensemblemodels;streamflow intervalprediction;modaldecomposition; improved
                  sparrowsearchalgorithm;attentionmechanism

                                                                                    (责任编辑:韩 昆)

                                                                                                —  2 6 5 —
   120   121   122   123   124   125   126   127   128   129   130