On artificial neural networking-based process monitoring under bootstrapping using runs rules schemes

Abstract

Control charts are popular tools in statistical pro- cess control (SPC) and artificial neural network (ANN) tech- nique is an attractive alternative for efficient monitoring of process parameters. This study uses the artificial neural net- work technique with back propagation method to process control system for dispersion parameter. We have trained an artificial neural network to be used in statistical control charts using varying runs rules schemes. By investigating the per- formanceoftrainedartificialneuralnetworkundernormaland bootstrapping environments we have made comparisons of the usual ANN and three runs rules-based schemes for ANN to gain the precision of process. We have used average run length (ARL), extra quadratic loss (EQL), relative ARL (RARL), and performance comparison index (PCI) measures and explored the said structures of trained artificial neural network under bootstrapping by implementing runs rules schemes. We havealso suggested a modificationinthe trained ANN for variance change detection. An example with real data is also given for practical considerations.