基于BP神经网络的潜浮式无人船水动力性能分析及阻力预测（英文）-豆柴文库

您所在位置：网站首页 / 基于BP神经网络的潜浮式无人船水动力性能分析及阻力预测（英文）.docx / 文档详情

在线预览结束，喜欢就下载吧，查找使用更方便

5 金币

下载文档

/ 2

下载提示

如果您无法下载资料，请参考说明：

1、部分资料下载需要金币，请确保您的账户上有足够的金币

2、已购买过的文档，再次下载不重复扣费

3、资料包下载后请先用软件解压，在使用对应软件打开

文本预览

基于BP神经网络的潜浮式无人船水动力性能分析及阻力预测（英文）
Title:AnalysisofHydrodynamicPerformanceandResistancePredictionofaSubmarine-likeUnmannedSurfaceVesselbasedonBPNeuralNetwork
Abstract:
Thispaperpresentsananalysisofthehydrodynamicperformanceandresistancepredictionofasubmarine-likeunmannedsurfacevessel(USV).ThepaperproposestheuseofaBackpropagation(BP)neuralnetworkformodelingthehydrodynamicforcesandpredictingtheresistanceoftheUSVindifferentworkingconditions.Themainfocusliesonthedeterminationofthehydrodynamiccoefficientsandthedevelopmentofareliableresistancepredictionmodel.
1.Introduction:
Withtheincreasingdemandforautonomousmaritimemissions,unmannedsurfacevesselshavegainedsignificantattention.However,thehydrodynamiccharacteristicsandresistancepredictionofsubmarine-likeUSVs,whichoperatepartiallysubmerged,havenotbeenthoroughlystudied.ThisresearchaimstofillthisgapbyutilizingBPneuralnetworks.
2.LiteratureReview:
ThissectionpresentsacomprehensivereviewoftheexistingliteratureonhydrodynamicsofUSVsandtheapplicationofBPneuralnetworksinshipresistanceprediction.Ithighlightsthelimitationsandchallengesinexistingresearch,motivatingtheproposedapproachinthispaper.
3.Methodology:
Theproposedmethodologyconsistsofthreemainsteps:datacollection,modeltraining,andresistanceprediction.Inthefirststep,comprehensivedataontheUSV'sgeometricandenvironmentalparametersarecollected.ThesecondstepinvolvestrainingaBPneuralnetworkusingthecollecteddata,withvariousinputparametersrelatingtotheUSV'sgeometricdimensions,speed,submersionratio,andwaterdepth.Finally,thetrainedneuralnetworkisusedtopredicttheresistanceoftheUSV,consideringdifferentoperatingconditions.
4.HydrodynamicForceModeling:
ThissectiondetailsthedeterminationofhydrodynamiccoefficientsfortheUSV.Throughexperimentationandnumericalanalysis,thehydrodynamiccoefficientsforlift,drag,andmomentarecalculated.ThecalculatedcoefficientsarethenusedasinputparametersfortheBPneuralnetwork.
5.ResultsandAnalysis:
ThetrainedBPneuralnetworkisappliedtopredicttheresistanceoftheUSVforvario