Akademik Veri Yönetim Sistemi
INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH, cilt.37, sa.10, ss.2191-2200, 1999 (SCI-Expanded)
Control charts are tools commonly used in production environments to determine whether a process is in control or not. In this study, in addition to traditional Shewhart control charts, artificial neural networks which attempt to emulate the massively parallel and distributed processing of the brain are being examined for use in statistical process control. It is vital for quality and cost to detect variability (shift in mean and/or variance) in a process. If the time between the occurrence of a variation and its detection and cost are considered, the determination of the variation correctly and quickly is very important for production processes. This study has scope for the determination of mean and/or variance shifts in a process. One model is developed for detection of the shifts in a process. The model includes two neural networks: one determines shifts in process mean and the other determines shifts in variance. The results of these networks are combined to decide which shift has occurred. The performance of the model was compared with that of control charts by evaluating Type II error.