Alternative methods for the simultaneous monitoring of simple linear profile parameters

Tahir Mahmood*, Muhammad Riaz, M. Hafidz Omar, Min Xie

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

In many industrial processes, the quality characteristic of interest has a relation (linear or non-linear) with other supporting variable(s). Simple linear profile is a well-known term used for the quality characteristic, which is linearly associated with another descriptive variable, and the monitoring of simple linear profile parameters (i.e., slope, intercept, and error variance) is known as linear profiling. In the literature, a well-known approach named as EWMA_3 chart is used for the simultaneous monitoring of intercept, slope, and error variance. This approach is very efficient as compared to EWMA/R, Hotelling T2, and Shewhart_3 charts but it is a tedious method, since distinct pair of control limits require individual charting constant for each parameter. In this study, new methods are designed for the simultaneous monitoring of simple linear profile parameters, which requires single charting constant and have several advantages such as simplicity, efficiency, and ease of applicability. The findings of this study reveal that newly designed control charts such as the Max − EWMA − 3 and SS − EWMA − 3 have almost similar performance with EWMA_3 chart. Specifically, Max − EWMA − 3 − C chart shows superiority among all other control charts. Further, importance of the stated proposals is highlighted by the real example from the field of chemical engineering.
Original languageEnglish
Pages (from-to)2851-2871
Number of pages21
JournalInternational Journal of Advanced Manufacturing Technology
Volume97
DOIs
Publication statusPublished - Jul 2018
Externally publishedYes

Keywords

  • control chart
  • linear profiling
  • max statistic
  • MOX sensor
  • simultaneous monitoring

Fingerprint

Dive into the research topics of 'Alternative methods for the simultaneous monitoring of simple linear profile parameters'. Together they form a unique fingerprint.

Cite this