STABILITY AND SENSITIVITY OF AN EWMA CONTROLLER

The performance of a process control algorithm based on the EWMA statistic is analyzed. A simple condition relating the EWMA weight and the estimated process gain is shown to ensure that the control strategy is stable for a first-order multiple-input, single-output process that may be drifting or wandering. A similar condition is shown to guarantee stability far a second-order, single-input process. An expression is derived for the output mean squared deviation from target as a function of the algorithm parameters, how quickly the process drifts or wanders, and the amount of noise. The results are illustrated in the context of an epitaxial growth process.