Design of the statistical control of low fraction nonconforming processes restricted to small samples

We present the non-conventional design of no charts used for the surveillance of processes characterized by a very low fraction nonconforming, with a costly and/or time-consuming inspection procedure. which makes the inspection of large samples prohibitive. Under these circumstances, the trade-off b...

Descripción completa

Detalles Bibliográficos
Autores: Leiras, Adriana, Epprecht, Eugenio Kahn, Costa, Antonio Fernando Branco [UNESP]
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2007
País:Brasil
Institución:Universidade Estadual Paulista (UNESP)
Repositorio:Repositório Institucional da UNESP
Idioma:portugués
OAI Identifier:oai:repositorio.unesp.br:11449/231046
Acceso en línea:http://hdl.handle.net/11449/231046
Access Level:acceso abierto
Palabra clave:Control by attributes
Design of control charts
Np charts
Statistical process control
Descripción
Sumario:We present the non-conventional design of no charts used for the surveillance of processes characterized by a very low fraction nonconforming, with a costly and/or time-consuming inspection procedure. which makes the inspection of large samples prohibitive. Under these circumstances, the trade-off between the false-alarm rate and the speed with which the chart signals process deteriorations is the basis to design the control chart, once [depending on the sample size) the conventional np chart with three-sigma limits offers little protection against false alarms or is slow in detecting process disturbances. The study was motivated by the real case of a newspapers packaging process. The nominal number of newspapers in the package depends on the newspaper's breadth, and packages with a number of newspapers different from nominal are considered nonconforming.