Analisis Diagram Kontrol MCUSUM dan MEWMA Berbasis Model Time Series untuk Pengendalian Kualitas di PG Rejo Agung Baru Madiun

Fairuz, Maulida Ihza (2022) Analisis Diagram Kontrol MCUSUM dan MEWMA Berbasis Model Time Series untuk Pengendalian Kualitas di PG Rejo Agung Baru Madiun. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.

Text 06111440000047-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 April 2024. Download (1MB) | Request a copy

Abstract

Dalam proses pengendalian kualitas secara statistik, terdapat asumsi dasar yang harus dipenuhi, yaitu data berdistribusi normal dan independen. Data yang digunakan tidak selalu memenuhi kedua asumsi tersebut. Hal ini disebabkan oleh adanya autokorelasi pada data. Pada penelitian ini, pendekatan residual time series digunakan untuk mengatasi kondisi tersebut. Proses pengendalian kualitas dilakukan menggunakan metode MCUSUM dan MEWMA, dengan data karakteristik kualitas dari Gula Kristal Putih (GKP). Data yang digunakan tidak memenuhi asumsi distribusi normal. Namun, proses pengendalian kualitas tetap dilakukan karena diagram kontrol MEWMA diketahui cukup kuat untuk menangani data yang tidak berdistribusi normal, sedangkan pengendalian kualitas dengan diagram kontrol MCUSUM tetap dilakukan untuk mengetahui kinerjanya. Uji ARL dilakukan untuk mendapatkan diagram kontrol dengan kinerja terbaik, dimana semakin besar nilai ARL maka semakin baik pula kinerja diagram kontrol yang dinilai. Secara umum, diagram kontrol MEWMA memiliki kinerja lebih baik dibanding diagram kontrol MCUSUM. Kinerja terbaik didapatkan dari diagram kontrol MCUSUM dengan nilai k=0,5 dan h=6.
================================================================================================
In statistical quality control process, there are two basic assumptions that must be met, that the data must follow normal distribution and independent. The data used do not always meet these two assumptions. This is caused by autocorrelation in the data. In this study, the residual time series approach was used to overcome this condition. The quality control process was carried out using the MCUSUM and MEWMA methods, using data of quality characteristic from White Crystal Sugar (GKP). The data used did not meet the assumption of a normal distribution. However, the quality control process was still carried out because the MEWMA control chart is known to be robust enough to handle data that is not normally distributed, while the quality control using the MCUSUM control chart was still carried out to determine its performance. The ARL test was carried out to obtain the control chart with the best performance, where the greater the ARL value, the better the performance of control chart that was assessed. In general, MEWMA control chart has better performance than MCUSUM control chart. The best performance was obtained from the MCUSUM control chart with a value of k=0,5 and h=6.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Besar Jenis Butir, Kadar Air, MCUSUM, MEWMA, Warna Larutan, Color of Solution, Grain, Moisture
Subjects:	Q Science > QA Mathematics > QA276 Mathematical statistics. Time-series analysis. Failure time data analysis. Survival analysis (Biometry)
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Mathematics > 44201-(S1) Undergraduate Thesis
Depositing User:	Maulida Ihza Fairuz
Date Deposited:	16 Feb 2022 05:46
Last Modified:	16 Feb 2022 05:46
URI:	http://repository.its.ac.id/id/eprint/94116

Actions (login required)

View Item