A NEURAL FUZZY CONTROL CHART FOR DETECTING AND CLASSIFYING PROCESS MEAN SHIFTS

We propose a neural fuzzy (NF) control chart for identifying process m ean shifts. A supervised multi-layer backpropagation neural network is trained off-line to detect various mean shifts in a production proces s. In identifying mean shifts in real-time usage, the neural network's outputs are classified into various decision regions using a fuzzy se t scheme. The approach offers better performance and additional advant ages over conventional control charts. Simulation results show that th e proposed NF control charts are superior to conventional X-bar charts and CUSUM charts in terms of the average run lengths (ARL). The propo sed system also has the ability to identify the magnitude of a mean sh ift, in addition to the Shewhart-type control chart heuristic rules. C orrect classification percentages are studied. Furthermore, general gu idelines are given for the proper use of the proposed NF charts.