Abstract

Finding Robust Setpoint for Design Space Using DOE and Monte Carlo Simulations

Nirav Shah, Senior Data Scientist, MKS Data Analytics Solutions (formerly MKS Umetrics)

Design Space can be obtained by using risk analysis to thoroughly investigate and define Critical Quality Attributes (CQAs) and Critical Process Parameters (CPPs), together using design of experiment (DOE) to derive mathematical models relating CQAs with CPPs. Regardless of how a Design Space is developed, it is expected that operation within the Design Space will result in a product meeting the defined quality attributes. The set points selected from the ranges derived by a DOE model may not guarantee the defined quality attributes, as there is a risk of failure considering the uncertainty of the model as well as process variability. This talk will present an application on how to find the robust setpoint for Design Space combining DOE models, Monte Carlo simulations and Design Space concept. Set point analysis will be discussed for Design Space robustness and stability. Keywords: Design of Experiment, design space, robust optimization, process development