Application of global sensitivity analysis for identification of probabilistic design spaces

The design space (DS) is defined as the combination of materials and process conditions, which provides assurance of quality for a pharmaceutical product. A model-based approach to identify a probability-based DS requires costly simulations across the entire process parameter space (certain) and the uncertain model parameter space. We demonstrate that application of global sensitivity analysis (GSA) can significantly reduce model complexity and reduce computational time for identifying and quantifying DS by screening out non-important uncertain parameters. The novelty of this approach in that the usage of an indicator function which takes only binary values as a model function allows to apply a straightforward GSA based on Sobol’ sensitivity indices and to avoid using more costly Monte Carlo filtering or GSA for constrained problems. We consider an application from the chemical industry to illustrate how this formulation results in model reduction and dramatic reduction of the number of required model runs.