7168

6674

كارشناسي ارشد

سيستم هاي اقتصادي - اجتماعي

اصفهان: دانشگاه صنعتي اصفهان، دانشكده صنايع و سيستم ها

1390

چهارده، 116ص.: مصور، جدول، نمودار

ص.ع. به فارسي و انگليسي

غلامعلي رئيسي اردلي

رضا حجازي

7/8/91

علي زينل همداني، ناصر ملاوردي

1396/09/20

كتابنامه

صنايع و سيستم ها

مهندسي صنايع و سيستم ها

ID6674

به فارسي و انگليسي: قابل رويت در نسخه ديجيتالي

Using T2 Hotelling multivariate Control Charts in Poly Acryle Plant by Inaccurate Data Mina Maleki m maleki@in iut ac ir Date of Submission 11 3 2012 Department of Industrial and Systems Engineering Isfahan University of Technology Isfahan 84156 83111 Iran Degree M Sc Language Farsi Supervisor gholam ali raissi raissi@cc iut ac ir Abstract Nowadays in industry there are many situations in which the simultaneous monitoring or control oftwo or more related quality process characteristics is necessary Monitoring these quality characteristicsindependently can be very misleading Process monitoring of problems in which several related variablesare of interest are collectively known as multivariate statistical process control The most useful tool ofmultivariate statistical process control is the quality control chart Multivariate process control techniqueswere established by Hotelling in his 1947 pioneering paper Statistical process control SPC is anapproach that uses statistical techniques to monitor Although many different multivariate controlprocedures exist it is belief that a control procedure built on T2 statistic possesses all the characteristics thatis necessary Like many multivariate charting statistics the T2 is a univariate statistic This is true regardlessthe number of process variables used in computing it However because of its similarity to a univariateShewhart chart the T2 control chart is sometimes referred to as a multivariate Shewhart chart Thisrelationship to common univariate charting procedures facilitates the understanding of this charting method Signal interpretation requires a procedure for isolating the contribution of each variable and or a particulargroup of variables As with univariate control out of control situations can be attributed to individualvariables being outside their allowable operational range The signal interpretation procedure covered inthis text is capable of separating a T2 value into independent components One type of componentdetermines the contribution of the individual variables to a signaling observation while the othercomponents check the relationships among groups of variables This procedure is global in nature and notisolated to a particular data set or type of industry The T2 statistics is one of the more flexible multivariatestatistics It gives excellent performance when used to monitor independent observation from a steady statecontinuous process It also can be based on either a single observation or the mean of a subgroup of nobservation Many industrial processes produce observations containing time dependency The T2 statisticcan be readily adapted to these situations and can be used to produce a time adjusted statistic For manyproblems control limits could not be so precise Uncertainty comes from the measurement system includingoperators and gauges and environmental conditions In this context fuzzy set theory is a useful tool tohandle this uncertainty Numeric control limits can be transformed to fuzzy control limits by usingmembership functions If a sample mean is too close to the control limits and the used measurement systemis not so sensitive the decision may be faulty Fuzzy control limits provide a more accurate and flexibleevaluation Key words multivariate statistical process control T2 Hotelling charts time dependency fuzzy settheory

غلامعلي رئيسي اردلي

رضا حجازي

علي زينل همداني، ناصر ملاوردي