Comparative Traditional Methods of Attributes with Fuzzy Quality Control Charts for Improving the Quality of a Product

Abstract

The problems motivating the study, as a result of sudden changes in production quality levels, which affect the production process. Control charts are a major tool in statistical quality control. The aim of the study is to monitor the production quality of a product that is an engine used in the application of a hair dryer. The methodology followed, the hair dryer model was chosen to verify the possibility of improving the product quality using fuzzy logic and comparing the traditional Shewhart control charts (p-chart) with the fuzzy p-chart in the context of manufacturing, and the collected data were processed using Minitab 21 Statistical Software. The performance of a control chart using fuzzy logic was measured for the proposed industrial product type with specifications for 300 samples of the constant size and a production period of 25 days to identify the product quality. The basic criterion for drawing the chart using fuzzy logic depends on the fuzzy ordering function for each of w, λ and its values are within the limits of (0 < λ or w ≤ 1) is a weighting parameter. The necessary tests were conducted to monitor the product quality using (w = 0.1, 0.2) and (λ = 0.1, 0.2) when the fuzzy ordering function is used. Results, it was found that the fuzzy p-chart was more sensitive to process changes and could detect shifts in defect ratio faster and more accurately, the production process was under statistical control and within quality control limits, and the conventional deviation from nominal control charts showed a false alarm for the observation as out of control. Recommendations, the present method can be used to improve product quality and reduce defects for the motor department.

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 — 5 citations exist upstream.

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