Robust Design course
Course Overview
This training course is designed to help modeFRONTIER users to expand their knowledge of Robust Design Optimization. Robust optimization problems arise where there are uncertainties involved in the data or in the model. The presence of uncertainty is due to errors in measuring, or difficulties in sampling, or moreover can depend on events and effects in the future that cannot be known with certainty. The uncertainty makes the traditional deterministic optimization approaches especially insufficient because these methods do not consider the impact such variations. These uncertainties should be included in the optimization procedures, so that prescribed robustness can be achieved in the optimal designs. In this training, the attendee will learn how to use modeFRONTIER and its tools to prudent decision-making under uncertainty.
Prerequisites
Getting started with modeFRONTIER or modeFRONTIER Fundamentals are recommended to get the best from this course.
Audience
The primary audience for this course includes modeFRONTIER user who wants to have a comprehensive introduction to Robust Design Optimization problems.
Topics
- Introduction to robust design optimization
- Monte Carlo and Latin Hypercube sampling technique
- Problems of decision-making under uncertainty
- Robust Design Optimization Examples
- Propagating and analyzing the effects
- Sensitivity analysis
- Assess outcomes from robust design optimization
At the end of the course, the attendees will be able to
- Set up modeFRONTIER stochastic projects
- Define distributions upon variables
- Use Monte Carlo and Latin Hypercube sampling
- Compute the Sensitivity Analysis
- Run robust design optimization projects and assess results