The effects of measurement errors on estimating and assessing the multivariate process capability with imprecise characteristic. (October 2022)

• Record Type: Journal Article
• Authors: Afshari, Robab; Ahmadi Nadi, Adel; Johannssen, Arne; Chukhrova, Nataliya; Tran, Kim Phuc
• Is Part Of: Computers & industrial engineering. Volume 172:Part A(2022)
• Publication Date: 2022-10
• Subjects: Process capability indices -- Hypothesis testing -- Linear covariate model -- Fuzzy number arithmetic; Engineering -- Data processing -- Periodicals; Industrial engineering -- Periodicals; 620.00285
• DOI: 10.1016/j.cie.2022.108563
• Languages: English
• ISSNs: 0360-8352

Abstract

Abstract: In industrial environments, process capability indices are daily employed as numerical metrics to summarize the performance of a process according to a predefined set of specification limits. Neglecting gauge measurement errors is a common phenomenon in process capability evaluations by researchers in laboratory investigations and by practitioners in daily operations. However, this common negligence is far from reality regardless of the employment of highly modern measuring tools, and may notably influence the efficiency of the measuring method for assessing the performance of a manufacturing process. In this paper, a linear covariate error model is applied to investigate the effects of gauge measurement errors on the classical and fuzzy estimation approaches of the multivariate process capability index S p k T for univariate and multivariate normally distributed quality characteristics with precise specification limits. Moreover, lower confidence bounds are also derived for the yield index S p k T in the presence of measurement errors and based on a fuzzy approach. In addition to the theoretical results, extensive simulations have been conducted to analyze how the behavior of the test statistic and lower confidence bound (LCB) for assessing the performance of the process is affected by different sources of the measurement errors. The obtained results indicate that a serious underestimation of the process capability occurs when the data is contaminated with measurement errors. It is also shown that the underestimation problem is somewhat solved by taking multiple measurements from the identical item. Moreover, comparative analyses show that the proposed method is superior to Scagliarini's method and Wang's way such that the negative effects of errors on underestimating the LCB are reduced in the proposed plan. This paper also extends the application of the introduced method to correlated variables. Finally, three practical examples are discussed to demonstrate the use of the proposed method in industrial applications. Highlights: The paper investigates effects of measurement errors on assessing process capability. A linear covariate error model is considered in fuzzy and non-fuzzy PCI estimation. Simulation study is conducted to show error impacts on estimators of PCI. A comparative study is done and the most informative method is introduced. Real data examples are studied to handle the introduced method in real situations.