Once design point candidates are identified, probabilistic analysis can be used to quantify the reliability or quality of the product statistically. Probabilistic analysis typically involves four areas of statistical variability: geometric shape, material properties, loading, and boundary conditions. For example, the statistical variability of the geometry of a product tries to capture product-to-product differences due to manufacturing imperfections quantified by manufacturing tolerances.
Probabilistic characterization provides a probability of success or failure rather than a simple yes or no evaluation. For instance, a probabilistic analysis could determine that one part in 1 million is likely to fail. Probabilistic analysis can also predict the probability of a product surviving its expected useful life.
To perform a robustness analysis, you insert a Six Sigma Analysis system in the Project Schematic. The process here is very similar to the process for response surfaces. The main difference is in the definition of the parameters. Instead of specifying a minimum and maximum value to define the range for each input parameter, you describe an input parameter in terms of a statistical curve and the curve's associated parameters. Once parameters are defined, you compute a new DOE and corresponding response surfaces and sensitivity charts. The results for the robustness analysis are in the form of probabilities and statistical distributions of the output parameters.