预览加载中，请您耐心等待几秒...

基于局部PLS的多输出过程自适应软测量建模方法(英文).docx

预览
1/2
2/2

在线预览结束，喜欢就下载吧，查找使用更方便

下载提示 文本预览

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

基于局部PLS的多输出过程自适应软测量建模方法(英文) BasicIntroductiontotheTopic: Theconceptofsoftsensingorsoftmeasurementiswidelyusedintheprocessindustry.Itisanon-invasivemethodofmeasuringvariousprocessvariableswhicharedifficulttomeasurewithconventionalsensors.Softsensingisachievedbymodelingtherelationshipbetweentheinputandoutputvariables.Theoutputvariableisestimatedbasedontherelationshipwiththeinputvariables. Thefocusofthispaperistopresentanewmethodofsoftsensing,whichisbasedonLocalPartialLeastSquares(PLS)regression.Thismethodisappliedtoamulti-outputprocess.TheproposedmethodcombinesthebenefitsofLocalPLSregressionwithaprocessvariableselectionmethodcalledRecursiveFeatureElimination(RFE).Theaimistodevelopanadaptivesoftsensingmodelthatcancopewithprocesschanges. Methodology: Theproposedmethodconsistsofthefollowingsteps: 1.DataCollection:Thefirststepistocollecttheprocessdata.Thedataconsistsofbothinputandoutputvariables.Theinputvariablesarethosevariableswhichinfluencetheoutputvariables.Theoutputvariablesarethosevariableswhichneedtobepredicted. 2.DataPre-processing:Thesecondstepistopre-processthedata.Thisinvolvesnormalization,medianfiltering,andremovingoutliers. 3.FeatureSelection:Thethirdstepistoselecttherelevantfeatures.Inthispaper,wehaveusedtheRecursiveFeatureElimination(RFE)method.RFEisabackwardeliminationmethodwherefeaturesareeliminatedonebyoneuntilthedesirednumberoffeaturesisobtained. 4.LocalPLSRegression:ThefourthstepistobuildalocalPLSregressionmodel.Theinputvariablesareusedtopredicttheoutputvariables.ThelocalPLSregressionmodelisbuiltusingasetofinputandoutputvariablesthatareselectedusingtheRFEmethod. 5.ModelValidation:Thefinalstepistovalidatethemodel.ThemodelisvalidatedusingtheRootMeanSquareError(RMSE)andtheCoefficientofDetermination(R2). ResultsandDiscussion: Theproposedmethodhasbeentestedonamulti-outputprocess.Theresultsshowthattheproposedmethodisabletomodeltheprocessaccurately.IthasbeenobservedthattheLocalPLSregressionmodelwiththeRFEfeatureselectionmethodperformsbetterthanthestandardPLSr