ارسل ملاحظاتك

ارسل ملاحظاتك لنا







Multivariate Statistical Process Control Based on Principal Component Analysis : MSPC-PCA

المصدر: المجلة المصرية للدراسات التجارية
الناشر: جامعة المنصورة - كلية التجارة
المؤلف الرئيسي: S., Hanaa M. (Author)
مؤلفين آخرين: B Ashraf A. (Co-Author), El Bayomy, A. T. (Co-Author)
المجلد/العدد: مج37, ع1
محكمة: نعم
الدولة: مصر
التاريخ الميلادي: 2013
الصفحات: 57 - 82
رقم MD: 660235
نوع المحتوى: بحوث ومقالات
قواعد المعلومات: EcoLink
مواضيع:
رابط المحتوى:
صورة الغلاف QR قانون

عدد مرات التحميل

13

حفظ في:
المستخلص: Tracking batch to batch variation and detecting abnormal events at early stages of a batch run is of critical importance in chemical process and many other industries which employ batch-wise operations. Multivariate quality control chart (MQC) Hotelling’s T2 ,the multivariate exponentially weighted moving average (MEWMA) chart, multivariate cumulative sum (MCUSUM) chart, and the multivariate process variability control chart have been a key technique for this purpose. A significant step forward in recent years in multivariate statistical process control (MSPC) for operational condition monitoring and fault diagnosis has been the introduction of principal component analysis (PCA) for compression of process data / significant progress has been made since Kresta ,et al introduced the idea of using principal component analysis (PCA) to pre - processing the process variables. PCA provides a smaller number of latent variables that can be used to replace the original observed variables in calculating the T2 and other charts. Each principal component (PC) is the linear combination of the original variables with the first PC captures the majority of variation in the data, and the second PC captures the majority of remaining variation and is orthogonal to the first PC, and so forth. There has been a wealth of publications in this area over the last ten years, and the work has been reviewed by a number of researchers.

عناصر مشابهة