A New Fuzzy Process Capability Index for Asymmetric Tolerance Interval

A New Fuzzy Process Capability Index for Asymmetric Tolerance Interval

Zainab Abbasi Ganji, Bahram Sadeghpour Gildeh
Copyright: © 2017 |Pages: 31
DOI: 10.4018/IJFSA.2017070104
OnDemand:
(Individual Articles)
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

Process capability indices are used to evaluate the performance of the manufacturing process. When the specification limits and the target value are not precise, the authors cannot use the traditional methods to assess the capability of the process. For the processes with asymmetric tolerance intervals, some fuzzy process capability indices have been introduced such as and . In some cases, these indices may fail to account the process performance. To overcome the problem with them, the authors propose two new fuzzy indices in the case that the specification limits and the target value are fuzzy while the data are crisp. Also, the authors present an application example to demonstrate effectiveness and performance of the proposed indices.
Article Preview
Top

1. Introduction

Process capability indices measure how much of the process' products are in accordance with the requirements of the intended construction engineers or customers. A tolerance interval for a product characteristic, X, consists of lower and upper limits, ‎‎LSL‎ and ‎USL,‎‎ together with a target value ‎T‎‎ somewhere between these limits.

A tolerance interval is symmetric if the target value is the midpoint of the tolerance interval. Although the symmetric cases are by far the more common, there are sufficiently many instances in which the target value is not the midpoint of the tolerance limits. In these cases, the tolerance interval is called asymmetric. ‎

For the processes with symmetric tolerance interval, there are several indices to provide measures of Normally-distributed process potential and performance such as IJFSA.2017070104.m03 and IJFSA.2017070104.m04 ‎(see Chan, Cheng & Spiring, 1988; Kane, 1986; Pearn, Kotz & Johnson, 1992).‎ Vannman (1995) introduced a superstructure index IJFSA.2017070104.m05 that contains these for basic indices.

According to Boyles (1994), it is often assumed that asymmetric tolerances are necessarily related in some cases to a skewed process distribution. In some circumstances the customer may allow the manufacturer to set a specification interval in terms of the process distribution. In some situations, asymmetric tolerances are due to transforming data to achieve approximate Normality. In general, asymmetric tolerances are not related to the shape of the supplier's process distribution; instead they simply reflect the customer's attitude that deviation from target value in one direction is less tolerable than the other.

There have been some indices introduced to handle the processes with asymmetric tolerances. Some superstructure indices are IJFSA.2017070104.m06 and IJFSA.2017070104.m07. For more information, one can see Chen & Pearn (2001), Chan, Cheng & Spiring (1988), Franklin & Wasserman (1992); Kane (1986); Kushler & Hurley (1992); Pan & Li (2014); Pan & Wendy (2015).

Suppose product characteristic ‎X‎‎ has Normal distribution with mean IJFSA.2017070104.m08 and standard deviation IJFSA.2017070104.m09. Some well-known indices which is widely used to measure the capability of the processes with asymmetric tolerances are as the following:

IJFSA.2017070104.m10
where:
IJFSA.2017070104.m11
IJFSA.2017070104.m12
IJFSA.2017070104.m13
IJFSA.2017070104.m14
IJFSA.2017070104.m15
and:

Complete Article List

Search this Journal:
Reset
Volume 13: 1 Issue (2024)
Volume 12: 1 Issue (2023)
Volume 11: 4 Issues (2022)
Volume 10: 4 Issues (2021)
Volume 9: 4 Issues (2020)
Volume 8: 4 Issues (2019)
Volume 7: 4 Issues (2018)
Volume 6: 4 Issues (2017)
Volume 5: 4 Issues (2016)
Volume 4: 4 Issues (2015)
Volume 3: 4 Issues (2013)
Volume 2: 4 Issues (2012)
Volume 1: 4 Issues (2011)
View Complete Journal Contents Listing