Neural Network Control Chart Architecture for Monitoring Non-Conformities in a Poisson Process

摘要

The uses of Neural Network (NN) models have recently been recommended as statistical quality control (SQC)tools. The advantages of NNs, particularly the robustness of the nonlinear modeling abilities, are appealing to qualitycontrol practitioners for use in process monitoring. Advances in computing power have also made the Neural NetworkControl Charts (NNCC) an alternative SQC technique.The systematic Design of Experiment (DOE) methodology isemployed to fnd near optimal NN topology for NNCC for Poisson data. A (2k) full factorial design is implemented andsupplemented as needed to investigate NN topologies. The effect of the following factors were investigated through asimulation study: the number of the inputs “n”, the number of nodes in the hidden layer(s), the training data size, andin-control mean for shift range 0-3σ . The guidelines and steps of constructing the DOE study for the NNCC is given,along with an example