Highest Posterior Distribution (HPD) Control Chart for Individual Observation

AbstractThe most widely used of control chart in multivariate control processing is control chart T2 Hotelling. There are 2 kinds of control chart T2 Hotelling, namely T2 Hotelling for group observation and T2 Hotelling for individual observation. In this paper, discuss the control chart T2 Hotelling for individual observation. This control chart is used for monitoring of mean vector and sample of covariance matrix. Mean vector and sample of covariance matrix are very sensitive with respect to extreme point (outliers). Therefore, it is needed an estimator of mean vector and has a stocky population covariance matrix to the outliers data. One method that can be used to detect data that contains outliers is Minimum Covariance Determinant (MCD). From the calculation results, obtained that control chart T2 Hotelling by using Fast-MCD algorithm is more sensitive to detect outliers data than T2 Hotelling classically.Keyword: T2 Hotelling, Minimum Covariance Determinant (MCD), robust, outlier AbstrakBagan kendali yang paling banyak digunakan dalam pengendalian proses secara multivariat adalah bagan kendali T2 Hotelling. Ada 2 jenis dari bagan kendali Hotelling yaitu bagan kendali Hotelling untuk pengamatan kelompok dan individual. Pada tulisan ini membahas bagan kendali Hotelling untuk pengamatan individual. Bagan kendali ini digunakan untuk memonitor vektor rata-rata dan matriks kovariansi sampel. Vektor rata-rata dan matriks kovariansi sampel sangat sensitif terhadap titik ekstrim (outliers). Oleh karena itu dibutuhkan estimator vektor rata-rata dan matriks kovariansi populasi yang kekar terhadap data outliers. Salah satu metode yang dapat digunakan untuk mendeteksi data yang mengandung outliers adalah Minimum Covariance Determinant (MCD). Dari hasil perhitungan diperoleh bahwa bagan kendali T2 Hotelling dengan algoritma Fast-MCD lebih sensitif mendeteksi data outliers daripada T2 Hotelling klasik.Kata Kunci: T2 Hotelling, Minimum Covariance Determinant (MCD), robust, outlier.

Download Full-text

Performance Evaluation of VSI Attribute Control Chart for On-line Process Control

Productivity Review ◽

10.15843/kpapr.27.4.201312.151 ◽

2013 ◽

Vol 27 (4) ◽

pp. 151-185

Author(s):

Hong-Seok Bae

Keyword(s):

Performance Evaluation ◽

Process Control ◽

Control Chart ◽

On Line ◽

Line Process

Download Full-text

Sensitivity improvement method of CV control chart

Advanced Control, Automation and Robotics ◽

10.2495/acar140011 ◽

2015 ◽

Author(s):

J.H. Lee ◽

E.P. Hong ◽

W. Lee

Keyword(s):

Control Chart ◽

Improvement Method ◽

Sensitivity Improvement

Download Full-text

Construction of New Standardized Attribute Control Chart based on defects per million opportunities

Qalaai Zanist Scientific Journal ◽

10.25212/lfu.qzj.3.3.32 ◽

2018 ◽

Vol 3 (3) ◽

Keyword(s):

Control Chart

Download Full-text

Statistical Management of Food Production Processes

Economy of agricultural and processing enterprises ◽

10.31442/0235-2494-2020-0-11-30-35 ◽

2020 ◽

pp. 30-35

Author(s):

N.A. Jurk ◽

Keyword(s):

Production Process ◽

Control Chart ◽

Food Production ◽

Time Interval ◽

Bakery Products ◽

Shewhart Control ◽

Manufactured Products ◽

Mnemonic Technique ◽

The Stability

The article presents scientific research in the field of statistical controllability of the food production process using the example of bakery products for a certain time interval using statistical methods of quality management. During quality control of finished products, defects in bakery products were identified, while the initial data were recorded in the developed form of a checklist for registering defects. It has been established that the most common defect is packaging leakage. For the subsequent statistical assessment of the stability of the production process and further analysis of the causes of the identified defect, a Shewhart control chart (p-card by an alternative feature) was used, which allows you to control the quality of manufactured products by the number of defects detected. Analyzing the control chart, it was concluded that studied process is conditionally stable, and the emerging defects are random. At the last stage of the research, the Ishikawa causal diagram was used, developed using the 6M mnemonic technique, in order to identify the most significant causes that affect the occurrence of the considered defect in bakery products. A more detailed study will allow the enterprise to produce food products that meet the established requirements.

Download Full-text