MO-PaDGAN: Generating Diverse Designs with Multivariate Performance Enhancement
This addresses challenges in engineering design automation for generating novel, high-performance designs, but it is incremental as it builds on existing generative models with a new loss function.
The paper tackled the problem of generating diverse and high-performance designs in engineering using deep generative models, proposing MO-PaDGAN to enhance multivariate performance and diversity, and demonstrated that it expands design boundaries and produces designs exceeding training data performance in an airfoil example.
Deep generative models have proven useful for automatic design synthesis and design space exploration. However, they face three challenges when applied to engineering design: 1) generated designs lack diversity, 2) it is difficult to explicitly improve all the performance measures of generated designs, and 3) existing models generally do not generate high-performance novel designs, outside the domain of the training data. To address these challenges, we propose MO-PaDGAN, which contains a new Determinantal Point Processes based loss function for probabilistic modeling of diversity and performances. Through a real-world airfoil design example, we demonstrate that MO-PaDGAN expands the existing boundary of the design space towards high-performance regions and generates new designs with high diversity and performances exceeding training data.