Deep Generative Model for Mechanical System Configuration Design

TL;DR

This paper introduces GearFormer, a deep generative Transformer model that efficiently predicts optimal mechanical system configurations, significantly accelerating and improving the design process compared to traditional search methods.

Contribution

The paper presents GearFormer, a novel Transformer-based generative model trained on synthetic data to optimize mechanical system configurations, enhancing speed and solution quality.

Findings

GearFormer outperforms standalone search methods in satisfying design requirements.

Hybrid approaches combining GearFormer and search methods yield even better solutions.

GearFormer generates solutions orders of magnitude faster than traditional search algorithms.

Abstract

Generative AI has made remarkable progress in addressing various design challenges. One prominent area where generative AI could bring significant value is in engineering design. In particular, selecting an optimal set of components and their interfaces to create a mechanical system that meets design requirements is one of the most challenging and time-consuming tasks for engineers. This configuration design task is inherently challenging due to its categorical nature, multiple design requirements a solution must satisfy, and the reliance on physics simulations for evaluating potential solutions. These characteristics entail solving a combinatorial optimization problem with multiple constraints involving black-box functions. To address this challenge, we propose a deep generative model to predict the optimal combination of components and interfaces for a given design problem. To demonstrate our approach, we solve a gear train synthesis problem by first creating a synthetic dataset using a grammar, a parts catalogue, and a physics simulator. We then train a Transformer using this dataset, named GearFormer, which can not only generate quality solutions on its own, but also augment search methods such as an evolutionary algorithm and Monte Carlo tree search. We show that GearFormer outperforms such search methods on their own in terms of satisfying the specified design requirements with orders of magnitude faster generation time. Additionally, we showcase the benefit of hybrid methods that leverage both GearFormer and search methods, which further improve the quality of the solutions.