ebook img

Statistical robust design : an industrial perspective PDF

246 Pages·2014·12.695 MB·English
by  ArnerMagnus
Save to my drive
Quick download
Download
Most books are stored in the elastic cloud where traffic is expensive. For this reason, we have a limit on daily download.

Preview Statistical robust design : an industrial perspective

RED BOX RULES ARE FOR PROOF STAGE ONLY. DELETE BEFORE FINAL PRINTING. STATISTICAL ROBUST Arnér DESIGN S An Industrial Perspective T A Magnus Arnér, Tetra Pak Packaging Solutions, Sweden T I S A UNIQUELY PRACTICAL APPROACH TO ROBUST DESIGN T FROM A STATISTICAL AND ENGINEERING PERSPECTIVE I Variation in environment, usage conditions, and the manufacturing process has C long presented a challenge in product engineering, and reducing variation is A universally recognized as a key to improving reliability and productivity. One key and cost-effective way to achieve this is by robust design – making the product as L insensitive as possible to variation. With Design for Six Sigma training programs primarily in mind, the author of this R Magnus Arnér book offers practical examples that will help to guide product engineers through O every stage of experimental design: formulating problems, planning experiments, and analysing data. He discusses both physical and virtual techniques, and B includes numerous exercises and solutions that make the book an ideal resource for teaching or self-study. U STATISTICAL • Presents a practical approach to robust design through design of experiments. S • Offers a balance between statistical and industrial aspects of robust design. T • Includes practical exercises, making the book useful for teaching. ROBUST D • Covers both physical and virtual approaches to robust design. • Supported by an accompanying website (www.wiley/com/go/robust) E featuring MATLAB® scripts and solutions to exercises. S • Written by an experienced industrial design practitioner. I DESIGN G This book’s state of the art perspective will be of benefi t to practitioners of robust N design in industry, consultants providing training in Design for Six Sigma, and quality engineers. It will also be a valuable resource for specialized university courses in statistics or quality engineering. An Industrial Perspective www.wiley/com/go/robust Statistical Robust Design Statistical Robust Design An Industrial Perspective Magnus Arne´r TetraPakPackagingSolutions, Sweden Thiseditionfirstpublished2014 ©2014JohnWiley&Sons,Ltd Registeredoffice JohnWiley&SonsLtd,TheAtrium,SouthernGate,Chichester,WestSussex,PO198SQ,United Kingdom Fordetailsofourglobaleditorialoffices,forcustomerservicesandforinformationabouthowtoapply forpermissiontoreusethecopyrightmaterialinthisbookpleaseseeourwebsiteatwww.wiley.com. Therightoftheauthortobeidentifiedastheauthorofthisworkhasbeenassertedinaccordancewiththe Copyright,DesignsandPatentsAct1988. Allrightsreserved.Nopartofthispublicationmaybereproduced,storedinaretrievalsystem,or transmitted,inanyformorbyanymeans,electronic,mechanical,photocopying,recordingorotherwise, exceptaspermittedbytheUKCopyright,DesignsandPatentsAct1988,withoutthepriorpermissionof thepublisher. Wileyalsopublishesitsbooksinavarietyofelectronicformats.Somecontentthatappearsinprintmay notbeavailableinelectronicbooks. Designationsusedbycompaniestodistinguishtheirproductsareoftenclaimedastrademarks.Allbrand namesandproductnamesusedinthisbookaretradenames,servicemarks,trademarksorregistered trademarksoftheirrespectiveowners.Thepublisherisnotassociatedwithanyproductorvendor mentionedinthisbook. LimitofLiability/DisclaimerofWarranty:Whilethepublisherandauthorhaveusedtheirbesteffortsin preparingthisbook,theymakenorepresentationsorwarrantieswithrespecttotheaccuracyor completenessofthecontentsofthisbookandspecificallydisclaimanyimpliedwarrantiesof merchantabilityorfitnessforaparticularpurpose.Itissoldontheunderstandingthatthepublisherisnot engagedinrenderingprofessionalservicesandneitherthepublishernortheauthorshallbeliablefor damagesarisingherefrom.Ifprofessionaladviceorotherexpertassistanceisrequired,theservicesofa competentprofessionalshouldbesought. LibraryofCongressCataloging-in-PublicationData Arner,Magnus,author. Statisticalrobustdesign:anindustrialperspective/MagnusArner. pagescm Includesbibliographicalreferencesandindex. ISBN978-1-118-62503-3(cloth) 1.Industrialdesign–Statisticalmethods. 2.Robuststatistics. I.Title. TS171.9.A762014 745.2–dc23 2013046030 AcataloguerecordforthisbookisavailablefromtheBritishLibrary. ISBN:978-1-118-62503-3 Setin10/12ptTimesbyAptaraInc.,NewDelhi,India 1 2014 Contents Preface ix 1 Whatisrobustdesign? 1 1.1 Theimportanceofsmallvariation 1 1.2 Variancereduction 2 1.3 Variationpropagation 4 1.4 Discussion 5 1.4.1 Limitations 6 1.4.2 Theoutlineofthisbook 7 Exercises 8 2 DOEforrobustdesign,part1 11 2.1 Introduction 11 2.1.1 Noisefactors 11 2.1.2 Controlfactors 12 2.1.3 Control-by-noiseinteractions 12 2.2 Combinedarrays:Anexamplefromthepackagingindustry 13 2.2.1 Theexperimentalarray 15 2.2.2 Factoreffectplots 15 2.2.3 Analyticalanalysisandstatisticalsignificance 17 2.2.4 Someadditionalcommentsontheplotting 20 2.3 Dispersioneffects 21 Exercises 23 Reference 25 3 Noiseandcontrolfactors 27 3.1 Introductiontonoisefactors 27 3.1.1 Categoriesofnoise 28 3.2 Findingtheimportantnoisefactors 33 3.2.1 Relatingnoisetofailuremodes 33 3.2.2 Reducingthenumberofnoisefactors 34 3.3 Howtoincludenoiseinadesignedexperiment 40 3.3.1 Compoundingofnoisefactors 40 vi CONTENTS 3.3.2 Howtoincludenoiseinexperimentation 45 3.3.3 Processparameters 48 3.4 Controlfactors 48 Exercises 49 References 51 4 Response,signal,andPdiagrams 53 4.1 Theideaofsignalandresponse 53 4.1.1 Twosituations 54 4.2 IdealfunctionsandPdiagrams 55 4.2.1 Noiseorsignalfactor 56 4.2.2 Controlorsignalfactor 56 4.2.3 Thescope 58 4.3 Thesignal 63 4.3.1 Includingasignalinadesignedexperiment 64 Exercises 65 5 DOEforrobustdesign,part2 69 5.1 Combinedandcrossedarrays 69 5.1.1 ClassicalDOEversusDOEforrobustdesign 69 5.1.2 Thestructureofinnerandouterarrays 70 5.2 Includingasignalinadesignedexperiment 74 5.2.1 Combinedarrayswithasignal 74 5.2.2 Innerandouterarrayswithasignal 81 5.3 Crossedarraysversuscombinedarrays 89 5.3.1 Differencesinfactoraliasing 91 5.4 Crossedarraysandsplit-plotdesigns 94 5.4.1 Limitsofrandomization 94 5.4.2 Split-plotdesigns 95 Exercises 98 References 99 6 Smaller-the-betterandlarger-the-better 101 6.1 Differenttypesofresponses 101 6.2 Failuremodesandsmaller-the-better 102 6.2.1 Failuremodes 102 6.2.2 STBwithinnerandouterarrays 103 6.2.3 STBwithcombinedarrays 106 6.3 Larger-the-better 106 6.4 Operatingwindow 108 6.4.1 Thewindowwidth 110 Exercises 113 References 115 CONTENTS vii 7 Regressionforrobustdesign 117 7.1 Graphicaltechniques 117 ( ) 7.2 Analyticalminimizationof g′(z) 2 120 7.3 Regressionandcrossedarrays 121 7.3.1 Regressiontermsintheinnerarray 127 Exercises 128 8 Mathematicsofrobustdesign 131 8.1 Notationalsystem 131 8.2 Theobjectivefunction 132 8.2.1 Multidimensionalproblems 136 8.2.2 Optimizationinthepresenceofasignal 138 8.2.3 Matrixformulation 139 8.2.4 Paretooptimality 141 8.3 ANOVAforrobustdesign 144 8.3.1 TraditionalANOVA 144 8.3.2 FunctionalANOVA 146 8.3.3 Sensitivityindices 149 Exercises 152 References 153 9 Designandanalysisofcomputerexperiments 155 9.1 Overviewofcomputerexperiments 156 9.1.1 Robustdesign 157 9.2 Experimentalarraysforcomputerexperiments 161 9.2.1 Screeningdesigns 161 9.2.2 Spacefillingdesigns 163 9.2.3 Latinhypercubes 165 9.2.4 Latinhypercubedesignsandalphabetical optimalitycriteria 166 9.3 Responsesurfaces 167 9.3.1 Localleastsquares 168 9.3.2 Kriging 169 9.4 Optimization 171 9.4.1 Theobjectivefunction 171 9.4.2 AnalyticaltechniquesorMonteCarlo 173 Exercises 175 References 176 10 MonteCarlomethodsforrobustdesign 177 10.1 Geometryvariation 177 10.1.1 Electroniccircuits 179 10.2 Geometryvariationintwodimensions 179 10.3 Crossedarrays 192 viii CONTENTS 11 Taguchiandhisideasonrobustdesign 195 11.1 Historyandorigin 195 11.2 Theexperimentalarrays 197 11.2.1 Thenatureofinnerarrays 197 11.2.2 Interactionsandenergythinking 199 11.2.3 Crossingthearrays 200 11.3 Signal-to-noiseratios 200 11.4 Someotherideas 203 11.4.1 Randomization 203 11.4.2 Scienceversusengineering 204 11.4.3 Linefittingfordynamicmodels 204 11.4.4 Anaspectonthenoise 206 11.4.5 Dynamicmodels 207 Exercises 208 References 208 AppendixA Lossfunctions 209 A.1 WhyAmericansdonotbuyAmericantelevisionsets 209 A.2 Taguchi’sviewonlossfunction 211 A.3 Theaveragelossanditselements 211 A.4 Lossfunctionsinrobustdesign 214 Exercises 215 References 217 AppendixB Dataforchapter2 219 AppendixC Dataforchapter5 223 AppendixD Dataforchapter6 231 Index 233

See more

The list of books you might like

Most books are stored in the elastic cloud where traffic is expensive. For this reason, we have a limit on daily download.