TARGETING IN MULTI-CLASS SCREENING UNDER ERROR AND ERROR-FREE MEASUREMENT SYSTEMS

Recently, the economics of Quality Control has received a lot of interest from researchers. The Economics of Quality Control can be divided into three areas. These areas are “Eco-nomics of Control Charts”, “Economic Design of Inspection Plans” and “Economic Selection of Process Parameters”. The last...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Siddiqui, Atiq (author)
مؤلفون آخرون: unknown (author)
التنسيق: masterThesis
منشور في: 2001
الموضوعات:
الوصول للمادة أونلاين:https://eprints.kfupm.edu.sa/id/eprint/1638/1/Atiq_Siddiqui_MS_Thesis.pdf
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
الوصف
الملخص:Recently, the economics of Quality Control has received a lot of interest from researchers. The Economics of Quality Control can be divided into three areas. These areas are “Eco-nomics of Control Charts”, “Economic Design of Inspection Plans” and “Economic Selection of Process Parameters”. The last problem is known as “Process Targeting”. The objectives of the thesis were to develop three Process Targeting models. The first model was developed for the case of multi-class screening situation when the measurement system is considered error prone. The results showed nullifying effect of measurement error by optimally adjusting the process mean and the cut off points. In the second model, product uniformity was introduced via a Taguchi type quadratic loss function when the measurement system is considered error free. The results showed gains in profit in most of the cases if the new model is used. In the third model, a generalized model was presented in which both the product uniformity and the measurement error were incorporated. Results showed great deal of benefits over all other models if this integrated model is used. Sensitivity analysis has been performed to study the effect of measurement error and other parameters like production cost etc. Moreover, an analytic comparison of the models was performed and relationships between the models has been investigated. A numerical comparison has also been conducted to study the profit gain if a more realistic model is used. The thesis concluded by suggesting a number of extensions to be considered in future research.