Abstract: The exponentially weighted moving average chart (EWMA) is widely employed in quality control to monitor a process or to evaluate historic data. EWMA charts are designed to exhibit acceptable average run lengths both when the process is in and out of control. This paper introduces a functional technique for generating the parameters λ and Δ for such a chart that will have specified average run lengths. The parameters are estimated using regression plus an artificial neural network.
Keywords: ARL, average run length, EWMA chart, Exponentially Weighted Moving Average chart, neural network, parameter estimation, SPC, statistical process control
Recieved: 20.01.2010 Accepted: 15.06.2010 UDC: 005.642.2