Toward Knowledge-Guided AI for Inverse Design in Manufacturing: A Perspective on Domain, Physics, and Human-AI Synergy

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Hugon, Moon, Hyeonbin, Lee, Junhyeong, RYu, Seunghwa
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912550989332480
author Lee, Hugon
Moon, Hyeonbin
Lee, Junhyeong
RYu, Seunghwa
author_facet Lee, Hugon
Moon, Hyeonbin
Lee, Junhyeong
RYu, Seunghwa
contents Artificial intelligence (AI) is reshaping inverse design in manufacturing, enabling high-performance discovery in materials, products, and processes. However, purely data-driven approaches often struggle in realistic manufacturing settings characterized by sparse data, high-dimensional design spaces, and complex constraints. This perspective proposes an integrated framework built on three complementary pillars: domain knowledge to establish physically meaningful objectives and constraints while removing variables with limited relevance, physics-informed machine learning to enhance generalization under limited or biased data, and large language model-based interfaces to support intuitive, human-centered interaction. Using injection molding as an illustrative example, we demonstrate how these components can operate in practice and conclude by highlighting key challenges for applying such approaches in realistic manufacturing environments.
format Preprint
id arxiv_https___arxiv_org_abs_2506_00056
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Toward Knowledge-Guided AI for Inverse Design in Manufacturing: A Perspective on Domain, Physics, and Human-AI Synergy
Lee, Hugon
Moon, Hyeonbin
Lee, Junhyeong
RYu, Seunghwa
Artificial Intelligence
Computational Physics
Artificial intelligence (AI) is reshaping inverse design in manufacturing, enabling high-performance discovery in materials, products, and processes. However, purely data-driven approaches often struggle in realistic manufacturing settings characterized by sparse data, high-dimensional design spaces, and complex constraints. This perspective proposes an integrated framework built on three complementary pillars: domain knowledge to establish physically meaningful objectives and constraints while removing variables with limited relevance, physics-informed machine learning to enhance generalization under limited or biased data, and large language model-based interfaces to support intuitive, human-centered interaction. Using injection molding as an illustrative example, we demonstrate how these components can operate in practice and conclude by highlighting key challenges for applying such approaches in realistic manufacturing environments.
title Toward Knowledge-Guided AI for Inverse Design in Manufacturing: A Perspective on Domain, Physics, and Human-AI Synergy
topic Artificial Intelligence
Computational Physics
url https://arxiv.org/abs/2506.00056