Improvement of the statistical process control through an enhanced test of normality

Abstract

The improvement of quality is based on the continuous monitoring of inputs and products during the processes for the development of different goods or services. When it is possible to measure or compare inputs and outputs, statistical tools such as control charts are useful for evaluating the degree of compliance achieved with respect to specifications. Statistical process control (SPC) assists the quality experts and engineers to raise the quality of the products through the reduction of the process variability. In SPC, statistical techniques are utilized to identify and monitor special cause events. The SPC is a method for error avoidance instead of error detection. A study of a case study of automotive small and medium-sized enterprise (SME) in Portugal in which SPC is applied is made in this paper. At the factory the normality test employed in the SPC chart is the Kolmogorov-Smirnov test (K-S). When the control chart is analysed it shows that the process is centred, thus satisfying the quality compliance requirements. At the same time, the K-S test confirms that the recorded data trail a normal distribution. While the Shapiro-Wilk test is a more accurate normality test it could give a different answer by substituting the K-S test. Thus, a comparison is made between the two and the results are analysed.

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 — 14 citations exist upstream.

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