Title :
An optimal bivariate Poisson field chart for monitoring defects
Author :
Aebtarm, Surath ; Bouguila, Nizar
Author_Institution :
CIISE, Concordia Univ., Montreal, QC
Abstract :
In this article, we propose an optimal bivariate field chart to monitor two correlated characteristics of count data. This chart is based on optimization of bivariate Poisson confidence interval and projection of bivariate Poisson data in Poisson field. Both a real case study and simulations present improved performance of our proposed algorithm. Our experimental results show improved rate of average run length and robust detection of means shifts compared with other charts. The proposed chart is an effectively applicable chart, especially, in high quality processes.
Keywords :
control charts; monitoring; statistical process control; stochastic processes; attribute chart; bivariate Poisson confidence interval; bivariate Poisson data projection; control chart; defect monitoring; optimal bivariate Poisson field chart; statistical process control; Control charts; Councils; Data analysis; Data engineering; Gaussian distribution; Monitoring; Probability density function; Process control; Robustness; Poisson distribution; Poisson field; attribute chart; bivariate Poisson; control chart; count data;
Conference_Titel :
Electrical and Computer Engineering, 2009. CCECE '09. Canadian Conference on
Conference_Location :
St. John´s, NL
Print_ISBN :
978-1-4244-3509-8
Electronic_ISBN :
0840-7789
DOI :
10.1109/CCECE.2009.5090218