Statistical process control

Abstract

Purpose – In this context, process capability indices (PCI) reveal the process zones base on specification limits (SLs). Most of the research on control charts assumed certain data. However, to measure quality characteristic, practitioners sometimes face with uncertain and linguistic variables. Fuzzy theory is one of the most applicable tools which academia has employed to deal with uncertainty. The paper aims to discuss these issues. Design/methodology/approach – In this investigation, first, fuzzy and S control chart has been developed and second, the fuzzy formulation of the PCIs such as C pm ,C pmu ,C pml , C pmk , P p , P pl , P pu , P pk are constructed when SLs and measurements are at both triangular fuzzy numbers (TFNs) and trapezoidal fuzzy numbers (TrFNs) stages. Findings – The results show that using fuzzy make more flexibility and sense on recognition of out-of-control warnings. Research limitations/implications – For further research, the PCIs for non-normal data can be conducted based on TFN and TrFN. Practical implications – The application case is related to a piston company in Konya’s industry area. Originality/value – In the previous researches, for calculating C p , C pk , C pm and C pmk indices, the base approach was calculate standard deviation for a short term variation. For calculating these indices, the variation between subgroups are being ignored. Therefore, P p and P pk indices solved this fault by mentioning long term and short term variations. Therefore these two indices calculate the actual process capability.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 17 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.