The traditional use of control charts assumes the independence of data. It is widely recognized that many processes are autocorrelated thus violating the main assumption of independence. As a result, there is a need for a broader approach to quality monitoring when data are time-dependent or autocorrelated. The aim of this work is to present a new procedure for manufacturing process quality control in the case of serially correlated data. In particular, a recurrent neural network is introduced for quality control problem. Performance comparisons between the neural-based algorithm and control charts are also presented in the paper in order to validate the proposed approach. The simulation results indicate that the neural-based procedure is quite effective as it achieves improved performance over control charts.
Detecting Changes in Autoregressive Processes with a Recurrent Neural Network for Manufacturing Quality Monitoring
Pacella, M.;Semeraro, Q.;
2005-01-01
Abstract
The traditional use of control charts assumes the independence of data. It is widely recognized that many processes are autocorrelated thus violating the main assumption of independence. As a result, there is a need for a broader approach to quality monitoring when data are time-dependent or autocorrelated. The aim of this work is to present a new procedure for manufacturing process quality control in the case of serially correlated data. In particular, a recurrent neural network is introduced for quality control problem. Performance comparisons between the neural-based algorithm and control charts are also presented in the paper in order to validate the proposed approach. The simulation results indicate that the neural-based procedure is quite effective as it achieves improved performance over control charts.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.