Robust optimization and uncertainty quantification

Current state-of-the-art Computer-Aided Engineering (CAE) tools can only account for the uncertainties inherent to the processes in a very limited way, making the obtained global optima unreliable. The inclusion of an advanced and reliable uncertainty quantification in the CAE tools, coupled to an efficient methodology, would therefore be a major breakthrough for CAE, allowing industrial partners to design quicker and obtain better, cheaper and more robust (i.e. less uncertainty sensitive) products.

The primary objective of this research topic is to develop an efficient methodology for the optimization of industrial processes under uncertainty.  The methodology will enable to construct/achieve robust designs. The methodology will handle uncertainties in the model parameters, as well as uncertainties in the design variables. Hereby, the emphasis is on a large number of design variables and uncertainties. The inclusion of uncertainty quantification in the design cycle requires combining the exploration of the design space (optimization) with exploration of the stochastic space and the development and use of accurate and efficient surrogate models.

Such methodology offers following major opportunities:

  1. better, more efficient, more performant products or processes
  2. changing know-how from “alchemy” to “science”
  3. resulting in more environmentally friendly processes
  4. savings on R&D time and costs
  5. reduced time-to-market path.