LLMs reduce simulator calls and speed up engineering redesigns
LLM-Assisted Optimization for Simulation-Based Redesign
Artificial IntelligenceComputational Engineering, Finance, and Science
Summary
When engineers need to update designs because things change, it often takes a lot of computer time to check the new ideas with simulations. The authors study how large language models (LLMs), which understand engineering context and instructions, can help guide the search for better designs and reduce how many times simulations are run. They looked at different ways to combine LLMs with traditional optimization techniques to redesign electric vehicle battery packs and found this hybrid method can find good solutions much faster. How well it works depends on the type of design change and how much control the LLM has.
What this means in practice
- •For automotive design engineers: Accelerate redesign of vehicle components by reducing costly simulation runs with LLM-guided optimization techniques.
- •For manufacturing process planners: Improve adaptation of production setups to cost or material changes by integrating semantic knowledge with numerical optimization.
Authors
Chan-Eui Song, Jeremy J. Michalek, Christopher McComb
Abstract
Engineering design frequently involves redesigning a prior solution to adapt to changes in context, such as material prices or system requirements. Redesign often leverages simulators too complex and/or computationally intensive for traditional numerical solvers, which lack engineering knowledge and context, to ensure global solution quality. Large language models (LLMs) can interpret semantic information, including engineering knowledge about the system and changes in context, to help guide search, and recent studies have shown that incorporating this knowledge into optimization can improve search performance. However, how best to combine LLMs with numerical solvers in redesign remains unclear. We develop and test an integrated LLM-optimization approach for redesign and compare three methods for leveraging LLMs (warm start, variable fixing and ReAct) and four black-box solvers (Bayesian optimization, genetic algorithms, mesh adaptive direct search and random search) on an electric vehicle battery pack cost minimization case study across four types of redesign scenarios. We find that the integrated approach can match feasible design discovery of the numerical-solver baselines with 80% fewer simulator evaluations while tripling the fraction of runs that find near-optimal solutions. We find that the best LLM-solver integration approach and the way the prior solution is leveraged depend on the structure of the design requirement change, and that the benefit of increasing LLM model size grows with the extent to which the LLM controls the search. These results show clear potential for LLMs in redesign tasks for guiding or replacing numerical solvers.