DADO -- Low-Cost Query Strategies for Deep Active Design Optimization

TL;DR

This paper introduces low-cost query strategies using deep active learning to efficiently reduce the number of expensive simulations in multi-objective design optimization, especially in structural and fluid dynamics applications.

Contribution

It proposes two novel selection strategies for self-optimization that improve efficiency without requiring uncertainty estimation, applicable to various design optimization problems.

Findings

Strategies significantly reduce computational costs.

Method outperforms random sampling approaches.

Introduces new metrics for evaluating model performance.

Abstract

In this experience report, we apply deep active learning to the field of design optimization to reduce the number of computationally expensive numerical simulations. We are interested in optimizing the design of structural components, where the shape is described by a set of parameters. If we can predict the performance based on these parameters and consider only the promising candidates for simulation, there is an enormous potential for saving computing power. We present two selection strategies for self-optimization to reduce the computational cost in multi-objective design optimization problems. Our proposed methodology provides an intuitive approach that is easy to apply, offers significant improvements over random sampling, and circumvents the need for uncertainty estimation. We evaluate our strategies on a large dataset from the domain of fluid dynamics and introduce two new evaluation metrics to determine the model's performance. Findings from our evaluation highlights the effectiveness of our selection strategies in accelerating design optimization. We believe that the introduced method is easily transferable to other self-optimization problems.