Economic-statistical design of fully adaptive multivariate control charts under effects of multiple assignable causes. (November 2022)

• Record Type: Journal Article
• Authors: Taji, Jalal; Farughi, Hiwa; Rasay, Hasan
• Is Part Of: Computers & industrial engineering. Volume 173(2022)
• Publication Date: 2022-11
• Subjects: Economic-statistical design -- Variable-parameter -- Control chart -- Markov chain -- Assignable cause; Engineering -- Data processing -- Periodicals; Industrial engineering -- Periodicals; 620.00285
• DOI: 10.1016/j.cie.2022.108676
• Languages: English
• ISSNs: 0360-8352

Abstract

Highlights: Using a proper Markov chain approach, Economic-statistical design of a fully adaptive multivariate control chart is proposed. Effects of multiple assignable causes are considered. A comparison between variable parameter control chart and fixed parameter control chart has been done. A robust parameter design is done using Taguchi Method and comprehensive sensitivity analysis is conducted. Abstract: Fully adaptive multivariate control charts are efficient to monitor several quality characteristics simultaneously. Charts with assuming a single assignable cause (AC) have been investigated in many studies. However, due to the usual complexity of production processes, the assumption of single AC is not close to real-world conditions. In this paper, by a proper Markov chain approach, we develop an economic-statistical design of a variable-parameter (VP) multivariate control chart to monitor the process mean subject to multiple assignable causes. Numerical examples based on the Taguchi method have been provided and for some parameters, sensitivity analysis is given. Moreover, a comparison between proposed model and fix-parameter (FP) model is done to evaluate the savings of using the adaptive control chart. The results indicate that the proposed VP control charts outperform FP control charts.