Monitoring high-yields processes with defects count in nonconforming items by artificial neural network

In high-yields process monitoring, the Geometric distribution is particularly useful to control the cumulative counts of conforming (CCC) items. However, in some instances the number of defects on a nonconforming observation is also of important application and must be monitored. For the latter case, the use of the generalized Poisson distribution and hence simultaneously implementation of two control charts (CCC & C charts) is recommended in the literature. In this paper, we propose an artificial neural network approach to monitor high-yields processes in which not only the cumulative counts of conforming items but also the number of defects on nonconforming items is monitored. In order to demonstrate the application of the proposed network and to evaluate the performance of the proposed methodology we present two numerical examples and compare the results with the ones obtained from the application of two separate control charts (CCC & C charts).