The generalized linear model‐based exponentially weighted moving average and cumulative sum charts for the monitoring of high‐quality processes

2021 ◽  
Author(s):  
Tahir Mahmood ◽  
Narayanaswamy Balakrishnan ◽  
Min Xie
Keyword(s):  
Linear Model ◽  
Generalized Linear Model ◽  
Moving Average ◽  
Exponentially Weighted Moving Average ◽  
Cumulative Sum ◽  
High Quality ◽  
Model Based ◽  
Cumulative Sum Charts ◽  
Weighted Moving Average ◽  
Exponentially Weighted

scholarly journals PERBANDINGAN KINERJA PETA KENDALI CUMULATIVE SUM DAN PETA KENDALI EXPONENTIALLY WEIGHTED MOVING AVERAGE

2020 ◽  
Vol 9 (4) ◽  
Author(s):  
Dhea Trinandya Wijayanti, Helmi, Nurfitri Imro’ah
Keyword(s):  
Average Run Length ◽  
Moving Average ◽  
Exponentially Weighted Moving Average ◽  
Cumulative Sum ◽  
Run Length ◽  
Weighted Moving Average ◽  
Exponentially Weighted

 Pada umumnya peta kendali yang sering digunakan dalam pengendalian kualitas statistik adalah peta kendali Shewhart. Peta kendali ini bekerja hanya dengan menggunakan informasi yang terkandung dalam titik sampel terakhir dan mengabaikan informasi dari seluruh barisan titik sampel sebelumnya. Hal ini membuat peta kendali Shewhart kurang efektif dalam mendeteksi pergeseran rata-rata yang relatif kecil pada proses produksi. Sebagai alternatif, dikembangkan peta kendali Cumulative Sum (Cusum) dan peta kendali Exponentially Weighted Moving Average (EWMA). Penelitian ini menerapkan peta kendali Cusum dan peta kendali EWMA serta membandingkan kinerjanya dalam mendeteksi pergeseran rata-rata yang relatif kecil pada data produksi. Tahapan pengerjaan dimulai dari melakukan analisis peta kendali Cusum dan peta kendali EWMA dengan menghitung nilai statistik, batas kendali, dan membentuk grafik setiap peta kendali. Selanjutnya, dihitung nilai Average Run Length (ARL) sebagai acuan untuk membandingkan kinerja kedua peta kendali. Berdasarkan hasil penerapannya pada produksi wajan nomor 18 di CV. XYZ, pada peta kendali Cusum tidak terdapat titik-titik yang berada di luar batas kendali. Namun, pada peta kendali EWMA mampu mendeteksi adanya 9 titik yang berada di luar batas kendali sehingga proses produksi tidak terkendali secara statistik. Selain itu berdasarkan perolehan nilai ARL, diketahui nilai ARL peta kendali EWMA menunjukkan hasil yang lebih kecil yaitu sebesar 45,832 dibandingkan dengan nilai ARL peta kendali Cusum yang sebesar 69,108. Dari hasil analisis didapat kesimpulan bahwa peta kendali EWMA lebih efektif daripada peta kendali Cusum dalam mendeteksi adanya pergeseran rata-rata yang relatif kecil pada produksi wajan nomor 18 di CV. XYZ. Kata Kunci: Cusum, EWMA, ARL                                       

scholarly journals Performance of Joint Quality Monitoring Schemes under Gaussian distribution

2020 ◽  
Vol 9 (2) ◽  
pp. 335-340
Keyword(s):  
Moving Average ◽  
Statistical Quality Control ◽  
Exponentially Weighted Moving Average ◽  
Cumulative Sum ◽  
Monitoring Scheme ◽  
Mean And Variance ◽  
Joint Monitoring ◽  
Mean Variance ◽  
Weighted Moving Average ◽  
Exponentially Weighted

Jointly monitoring the process mean and variance has become a well-known topic in statistical quality control literature after it is considered as a bivariate problem. Many joint monitoring schemes have been proposed by using the Shewhart, cumulative sum and exponentially weighted moving average techniques. In this paper, best performing schemes from each technique has been selected and compared for their performance using average run length properties. It was found that selection of better joint monitoring scheme based on the shift in mean and variance to be detected quickly. In particular, the Shewhart distance joint monitoring scheme performs well when there is larger shifts in mean, variance or in both. In addition, the Shewhart distance joint monitoring scheme performs specific when there is no shift in mean and decrease in variance. For the smaller shifts in mean, variance or in both, cumulative sum and exponentially weighted moving average joint monitoring schemes can be recommended. At this scenario exponentially weighted moving average joint monitoring scheme performs marginally better than the cumulative sum scheme.

scholarly journals GRAFIK PENGENDALI MIXED EXPONENTIALLY WEIGHTED MOVING AVERAGE – CUMULATIVE SUM (MEC) DALAM ANALISIS PENGAWASAN PROSES PRODUKSI (Studi Kasus : Wingko Babat Cap “Moel”)

2021 ◽  
Vol 10 (1) ◽  
pp. 114-124
Author(s):  
Aulia Resti ◽  
Tatik Widiharih ◽  
Rukun Santoso
Keyword(s):  
Control Chart ◽  
Control Charts ◽  
Average Run Length ◽  
Moving Average ◽  
Exponentially Weighted Moving Average ◽  
Cumulative Sum ◽  
Statistical Process ◽  
Cusum Charts ◽  
Weighted Moving Average ◽  
Exponentially Weighted

Quality control is an important role in industry for maintain quality stability.  Statistical process control can quickly investigate the occurrence of unforeseen causes or process shifts using control charts. Mixed Exponentially Weighted Moving Average - Cumulative Sum (MEC) control chart is a tool used to monitor and evaluate whether the production process is in control or not. The MEC control chart method is a combination of the Exponentially Weighted Moving Average (EWMA) and Cumulative Sum (CUSUM) charts. Combining the two charts aims to increase the sensitivity of the control chart in detecting out of control. To compare the sensitivity level of the EWMA, CUSUM, and MEC methods, the Average Run Length (ARL) was used. From the comparison of ARL values, the MEC chart is the most sensitive control chart in detecting out of control compared to EWMA and CUSUM charts for small shifts. Keywords: Grafik Pengendali, Exponentially Weighted Moving Average, Cumulative Sum, Mixed EWMA-CUSUM, Average Run Lenght, EWMA, CUSUM, MEC, ARL

scholarly journals حول خصائص طول التشغيل للوحتي سيطرة ( المجموع المتراكم (Cusum) و المتوسط المتحرك الموزون اسيا (EWMA) ) لتوزيع بواسون

2019 ◽  
Vol 25 (114) ◽  
pp. 475-497
Author(s):  
جنان عباس ناصر
Keyword(s):  
Moving Average ◽  
Exponentially Weighted Moving Average ◽  
Cumulative Sum ◽  
Weighted Moving Average ◽  
Exponentially Weighted

في هذا البحث نتحرى حول خصائص طول التشغيل للوحتي سيطرة المجموع المتراكم (cumulative sum (Cusum)) والمتوسط المتحرك الموزون اسيا (Exponentially Weighted Moving Average (EWMA)) للكشف عن الانحرافات الموجبة في متوسط العملية عندما تكون العملية تتبع توزيع بواسون بمتوسط غير معلوم. وقد استعمل اسلوب سلسلة ماركوف لحساب المتوسط والانحراف المعياري لطول التشغيل للوحتي سيطرة المجموع المتراكم (Cusum) والمتوسط المتحرك الموزون اسيا (EWMA) عندما يكون المتغير تحت السيطرة يتبع توزيع بواسون. استعملت لوحتي سيطرة الـ Cusum والـ EWMA أيضا لمراقبة متوسط العملية عندما المشاهدات (منتجات اختيرت من مصنع المأمون) تكون مستقلة ومتطابقة التوزيع (iid) من توزيع بواسون بعملية تصنيع مستمرة. اذ افترضنا عدة قيم لمعلمات للوحتي سيطرة الـ poisson Cusum والـ EWMA poisson ولعدد حالات لسلسلة ماركوف. وقد استحصلت نتائج البحث باستعمال برامج مكتوبة ببرنامج Matlab -R2018a . تبين نتائج البحث بان لوحاتي سيطرة الـ poisson Cusum والـ EWMA  poisson كانت حساسة أكثر عند قيم معينة لمعلمات لوحتي  سيطرة الـ  poisson Cusum والـ EWMA  poisson. ولعدد الحالات في سلسلة ماركوف.  

Sign in / Sign up

Export Citation Format

Share Document