Selecting an appropriate supplier can substantially reduce purchasing costs, decrease production lead time, increase customer satisfaction, and strengthen corporate competitiveness. Thus, an effective approach to alleviate the problem of supplier selection is essential. Numerous studies have indicated that quality is the most critical and fundamental factor for supplier selection and evaluation, among various criteria. This study provides several methods for selecting the superior supplier based on the commonly used quality criterion, process yield. Four tests for comparing two yield-measure indices, based on the normal approximation and generalised confidence intervals method, are presented and compared. This paper provides recommendations for selecting efficient methods, based on the simulation results of test size and selection power. An example is also presented to illustrate the applicability of these methods.
In the manufacturing industry, many product characteristics are of one-sided specifications. The well-known process capability indices C PU and C PL are often used to measure process performance. Most capability research works have assumed no measurement errors. Unfortunately, such an assumption is not realistic even if the measurement is conducted using highly sophisticated advanced measuring instruments. Therefore, conclusions drawn regarding process capability are not reliable. In this paper, we consider the estimation and testing of C PU and C PL with the presence of measurement errors, to obtain adjusted lower confidence bounds and critical values for true process capability, which can be used to determine whether the factory processes meet the capability requirement when the measurement errors are unavoidable.
An important issue for design engineers is how to assign tolerance limits economically. Most work related to tolerance design is for nominal-is-best (N-type) quality characteristics and restricted by a normality assumption. However, smaller-is-better (S-type) quality characteristics and larger-is-better (L-type) quality characteristics are common in real applications. The practical distributions for S-type data or L-type data are typically skewed, and the normality assumption is violated. Determining tolerance with non-normal data using methodologies based on a normality assumption is not appropriate. This study considers the case in which measurements are recorded without their algebraic signs. The folded normal distribution works well to fit these absolute data. Based on the statistical properties of the folded normal distribution, this study develops an economic model encompassing quality loss, manufacturing costs, and re-work costs to determine tolerances. By minimising total costs, a procedure based on the Newton-Raphson method is utilised to obtain the optimal solution. Finally, a welding machine experiment is carried out to demonstrate the applicability of the proposed model.
The process capability index has become an efficient tool for measuring a supplier’s process performance.
C
pk
(
WSD
)
is one popularly used index for assessing non-normal process capability when the process violates the normality assumption. Unfortunately, this index cannot accurately reflect the process yield, so it may produce a serious result if the practitioner compares the calculated
C
pk
(
WSD
)
value with the capability requirement to determine whether the process meets that requirement. Hence, this study modifies
C
pk
(
WSD
)
to provide an adequate measure of lognormal process capability. In addition, an estimator of this modified index is also provided. Simulations show that the bias of this estimator is slight, and the coverage probability of capability testing is close to the nominal confidence. This means that our proposed method is adaptable for use.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.