Identifying the time of a step change with MEWMA control charts by Artificial Neural Network

Quality control charts have proven to be very effective in detecting out of control signals. it is very importantto practitioners to determine at what point in the past the signal was initiated. if a control chart signals achange in the process parameter, identifying the time of the change will substantially help the signal diagnosticsprocedure since it simplifies the search for special causes. in this paper the researchers have proposed theobservations following multivariate normal distribution. they have used multivariate exponentially weightedmoving average (mewma) control chart to detect signals. this research provides two ways to detect thechange point, first mle, and then neural network is used to identify the time of the change in the parameters(mean) in the past. the researchers intended to assess the performance of two approaches and compare themthrough computer simulation experiments. the results show that neural network performs effectively andequally well for the whole process dimensions while shift magnitudes are considered. thus, the neural networkprovides process engineers with an accurate and useful estimate of the actual time of the change in theprocess mean.