- Engineering Workflow Automation
- Design Space Exploration
Modern engineering design processes face the challenge of integrating data from diverse sources into consistent predictive models, known as multi-fidelity models. This integration offers advantages like reduced costs and improved design quality. However, a key challenge is developing algorithms that automatically identify the best distribution of design investigations, considering the compromise between sampling cost and desired accuracy.
This case study presents a machine-learning algorithm that addresses the challenge by guiding numerical experiments at different fidelity levels, adaptively selecting sampling locations, and optimizing the design using Optimus.