Using Large Language Models for Parametric Shape Optimization

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Xinxin, Xu, Zhuoqun, Zhu, Guangpu, Tay, Chien Ming Jonathan, Cui, Yongdong, Khoo, Boo Cheong, Zhu, Lailai
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916518108856320
author Zhang, Xinxin
Xu, Zhuoqun
Zhu, Guangpu
Tay, Chien Ming Jonathan
Cui, Yongdong
Khoo, Boo Cheong
Zhu, Lailai
author_facet Zhang, Xinxin
Xu, Zhuoqun
Zhu, Guangpu
Tay, Chien Ming Jonathan
Cui, Yongdong
Khoo, Boo Cheong
Zhu, Lailai
contents Recent advanced large language models (LLMs) have showcased their emergent capability of in-context learning, facilitating intelligent decision-making through natural language prompts without retraining. This new machine learning paradigm has shown promise in various fields, including general control and optimization problems. Inspired by these advancements, we explore the potential of LLMs for a specific and essential engineering task: parametric shape optimization (PSO). We develop an optimization framework, LLM-PSO, that leverages an LLM to determine the optimal shape of parameterized engineering designs in the spirit of evolutionary strategies. Utilizing the ``Claude 3.5 Sonnet'' LLM, we evaluate LLM-PSO on two benchmark flow optimization problems, specifically aiming to identify drag-minimizing profiles for 1) a two-dimensional airfoil in laminar flow, and 2) a three-dimensional axisymmetric body in Stokes flow. In both cases, LLM-PSO successfully identifies optimal shapes in agreement with benchmark solutions. Besides, it generally converges faster than other classical optimization algorithms. Our preliminary exploration may inspire further investigations into harnessing LLMs for shape optimization and engineering design more broadly.
format Preprint
id arxiv_https___arxiv_org_abs_2412_08072
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Using Large Language Models for Parametric Shape Optimization
Zhang, Xinxin
Xu, Zhuoqun
Zhu, Guangpu
Tay, Chien Ming Jonathan
Cui, Yongdong
Khoo, Boo Cheong
Zhu, Lailai
Computational Engineering, Finance, and Science
Artificial Intelligence
Machine Learning
Recent advanced large language models (LLMs) have showcased their emergent capability of in-context learning, facilitating intelligent decision-making through natural language prompts without retraining. This new machine learning paradigm has shown promise in various fields, including general control and optimization problems. Inspired by these advancements, we explore the potential of LLMs for a specific and essential engineering task: parametric shape optimization (PSO). We develop an optimization framework, LLM-PSO, that leverages an LLM to determine the optimal shape of parameterized engineering designs in the spirit of evolutionary strategies. Utilizing the ``Claude 3.5 Sonnet'' LLM, we evaluate LLM-PSO on two benchmark flow optimization problems, specifically aiming to identify drag-minimizing profiles for 1) a two-dimensional airfoil in laminar flow, and 2) a three-dimensional axisymmetric body in Stokes flow. In both cases, LLM-PSO successfully identifies optimal shapes in agreement with benchmark solutions. Besides, it generally converges faster than other classical optimization algorithms. Our preliminary exploration may inspire further investigations into harnessing LLMs for shape optimization and engineering design more broadly.
title Using Large Language Models for Parametric Shape Optimization
topic Computational Engineering, Finance, and Science
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2412.08072