Page 47 - IJAMD-1-2

International Journal of AI for
Materials and Design

PERSPECTIVE ARTICLE
A unified industrial large knowledge

model framework in Industry 4.0 and smart
manufacturing

Jay Lee and Hanqi Su*

Center for Industrial Artificial Intelligence, Department of Mechanical Engineering, A. James Clark
School of Engineering, University of Maryland, College Park, Maryland, United States of America

Abstract

The recent emergence of large language models (LLMs) demonstrates the
potential for artificial general intelligence, revealing new opportunities in
Industry 4.0 and smart manufacturing. However, a notable gap exists in applying
these LLMs in industry, primarily due to their training on general knowledge
rather than domain-specific knowledge. Such specialized domain knowledge is
vital for effectively addressing the complex needs of industrial applications. To
bridge this gap, this paper proposes a unified industrial large knowledge model
(ILKM) framework, emphasizing its potential to revolutionize future industries.
In addition, ILKMs and LLMs are compared from eight perspectives. Finally, the
“6S Principle” is proposed as the guideline for ILKM development, and several
potential opportunities are highlighted for ILKM deployment in Industry 4.0 and
smart manufacturing.

Keywords: Industrial large knowledge model; Large language model; Machine learning;
*Corresponding author:
Hanqi Su Industrial artificial intelligence; Industry 4.0; Smart manufacturing
(hanqisu@umd.edu)
Citation: Lee J, Su H. A unified
industrial large knowledge model
framework in Industry 4.0 and 1. Introduction
smart manufacturing. Int J AI Mater
1
Design. 2024;1(2):3681. In the era of Industry 4.0, a paradigm shift is unfolding in the manufacturing sector,
doi: 10.36922/ijamd.3681 driven by the advent of smart manufacturing practices. This revolution has been fueled
2
Received: May 16, 2024 by advancements in industrial big data analytics, industrial artificial intelligence (AI), 3
Accepted: June 4, 2024 machine learning (ML) and deep learning, cyber-physical system, and industrial
6
4,5
Published Online: July 24, 2024
internet of things. These technologies aim to enhance efficiency, productivity, and
7
Copyright: © 2024 Author(s). flexibility in manufacturing processes.
This is an Open-Access article
8,9
distributed under the terms of the Recent advances in large language models (LLMs) have showcased extraordinary
Creative Commons Attribution capabilities in natural language processing, including understanding, interpreting, and
License, permitting distribution,
and reproduction in any medium, generating human language. However, a gap exists in the application of these LLMs
provided the original work is within smart manufacturing, primarily because LLMs are predominantly trained on
properly cited. general knowledge, not domain-specific knowledge, which may not be entirely suitable
Publisher’s Note: AccScience for the specific and complex needs of industrial applications. Therefore, there is an urgent
Publishing remains neutral with need for the development of an advanced foundation model leveraging the powers of
regard to jurisdictional claims in
published maps and institutional LLMs and domain-specific knowledge to address complex challenges in Industry 4.0
affiliations. and smart manufacturing.
Volume 1 Issue 2 (2024) 41 doi: 10.36922/ijamd.3681