1、附录1翻译原文及译文DocNo/P0193-GP-01-1DocName/AnalysisofManufacturingProcessDataUsingQUICKTechnologyTMIssue：1Data：20April，2006Name(Print)SignatureAuthor：D/CliftonReviewer：S/TurnerTableofContents1ExecutiveSummary/41/1Introdution/41/2TechniquesEmployed/41/3SummaryofResults/41/4Observations/52Introdution/62/1Ox
2、fordBioSignalsLimited/63ExternalReferences/74Glossary/75DataDescription/75/1Datatypes/75/2PriorExperimentKnowledge/75/3TestDescription/86Pre-processing/96/1RemovalofStart/StopTransients/96/2RemovalofPowerSupplySignal/96/3FrequencyTransformation/97AnalysisI-Visualisation/127/1VisualisationofHigh-Dime
3、nsionalData/127/2Visualising5-DManufacturingProcessData/错误!未定义书签。7/3AutomaticNoveltyDetection/错误!未定义书签。7/4ConclusionofAnalysisI-Visualisation/错误!未定义书签。8AnalysisII-SignatureAnalysis/错误!未定义书签。8/1ConstructingSignatures/错误!未定义书签。8/2VisualisingSignatures/错误!未定义书签。8/3ConclusionofAnalysisII-SignatureAnalys
4、is/错误!未定义书签。9AnalysisIII-TemplateAnalysis/错误!未定义书签。9/1ConstructingaTemplateofNormality/错误!未定义书签。9/2ResultsofNoveltyDetectionUsingTemplateAnalysis/错误!未定义书签。9/3ConclusionofAnalysisIII-TemplateAnalysis/错误!未定义书签。10AnalysisIV-None-linearPrediction/错误!未定义书签。10/1NeuralNetworksforOn-LinePrediction/错误!未定义书签。
5、10/2ResultsofNoveltyDetectionusingNon-linearPrediction/错误!未定义书签。10/3ConclusionofAnalysisIV-Non-linearPrediction/错误!未定义书签。11OverallConclusion/错误!未定义书签。11/1Methodology/错误!未定义书签。11/2SummaryofTesults/错误!未定义书签。11/3FutureWork/错误!未定义书签。12AppendixA-NeuroScaleVisualisations/错误!未定义书签。TableofFiguresFigure1-Tes
6、t90/Fromtoptobottom/Ax/Ay/Az/AE/SPagainsttimet(s)Figure2-PowerspectraforTest19afterremovalof50Hzpowersupplycontribution/Thetopplotshowsa3-D“landspace”plotofeachspectrum/Thebottomplotshowsa“contour”plotofthesameinformation/withincreasingsignalpowershownasincreasingcolourfromblacktoredFigure3-Powerspe
7、ctraforTest19afterremovalofallspectralcomponentsbeneathpowerthresholdFigure4-Azagainsttime(inseconds)forTest19/beforeremovaloflow-powerfrequencycomponentsFigure5-Azagainsttime(inseconds)forTest19/afterremovaloflow-powerfrequencycomponentsFigure6-SPforanexampletest/showingthreeautomatically-detecrmin
8、edstates/S1-drillingin(showningreen)；S2-drill-bitbreak-throughandremoval(showninred)；S3-retraction(showninblue)Figure7-Examplesignatureofvariableyplottedagainstoperating-pointFigure8-Powerspectrafortest51/frequency(Hz)onthex-axisbetween0fs/2Figure9-AveragesignificantfrequencyfuFigure10-Visualisation
9、ofAEsignaturesforalltestsFigure11-VisualisationofAxbroadbandsignaturesforalltestsFigure12-VisualisationofAxaverage-frequencysignaturesforalltestsFigure13-NoveltydetectionusingatemplatesignatureFigure14-1ExecutiveSummary1/1IntroductionThepurposeofthisinvestigationconductedbyOxfordBioSignalswastoexami
10、neanddeterminethesuitabilityofitstechniquesinanalyzingdatafromanexamplemanufacturingprocess/ThisreporthasbeensubmittedtoRolls-RoycefortheexpressedofassessingOxfordBioSignalstechniqueswithrespecttomonitoringtheexampleprocess/TheanalysisconductedbyOxfordBioSignals(OBS)waslimitedtoafixedtimescale/afixe
11、dsetofchallengedataforasingleprocess(asprovidedbyRolls-RoyceandAachenuniversityofTechnology)/withnopriordomainknowledge/norinformationofsystemfailure/1/2TechniquesEmployedOBSusedanumberofanalysistechniquesgiventhelimitedtimescales/I-Visualisation/andClusterAnalysisThispowerfulmethodallowedtheevoluti
12、onofthesystemstate(fusingallavailabledatatypes)tobevisualisedthroughouttheseriesoftests/Thisshowedseveraldistinctmodesofoperationduringtheseries/highlightingmajoreventsobservedwithinthedata/latercorrelatedwithactualchangestothesystemsoperationbydomainexperts/Clusteranalysisautomaticallydetectswhicho
13、ftheseeventsmaybeconsideredtobe“abnormal”/withrespecttopreviouslyobservedsystembehavior/II-Signaturerepresentseachtestasasinglepointonaplot/allowingchangesbetweenteststobeeasilyidentified/Abnormaltestsareshownasoutlyingpoints/withnormaltestsformingacluster/Modelingthenormalbehaviorofseveralfeaturess
14、electedfromtheprovideddata/thismethodshowedthatadvancewarningofsystemfailurecouldbeautomaticallydetectedusingthesefeatures/aswellashighlightingsignificanteventswithinthelifeofthesystem/III-TemplateAnalysisThismethodallowsinstantaneoussample-bysamplenoveltydetection/suitableforon-lineimplementation/U
15、singacomplementaryapproachtoSignatureAnalysis/thismethodalsomodelsnormalsystembehavior/Resultsconfirmedtheobservationmadeusingpreviousmethods/IV-NeuralnetworkPredictorSimilarlyusefulforon-lineanalysis/thismethodusesanautomatedpredictorofsystembehaviour(aneuralnetworkpredictor)/inwhichpreviouslyidentifiedeventswereconfirmed/andfurthersignificantepisodesweredetected/1/3SummaryofResultsEarlywarningofsystemfailurewasindependentlyidentifiedbythevariousanalysismethodsemployed/Severalsignificanteventsduringthelifeoftheprocesswerecorrelatedwith
免责声明：
1. 《外文翻译--制造分析进程数据使用快速标记技术》内容来源于互联网，版权归原著者或相关公司所有。
2. 若《86561825文库网》收录的文本内容侵犯了您的权益或隐私，请立即通知我们删除。