Towards Seamless Data Translation Based on Data Models: A Hybrid AI Framework for Smart Transportation and Manufacturing

Interoperability between different data standards is essential for advancing digital technologies in smart manufacturing and transportation. This paper presents a hybrid AI framework that integrates Ontology Learning (OL), Knowledge Graphs (KGs), and Large Language Models (LLMs) to improve data translation across these standards. Focusing on IEEE 1451, ISO 15926, and IEC 61499, we address the challenges posed by these data models' unique structures and semantics. Our comparative analysis evaluates the strengths and limitations of OL, KGs, and LLMs across key metrics like accuracy, scalability, efficiency, robustness, and flexibility. The proposed framework leverages OL for systematic structuring, KGs for relational modeling, and LLMs for linguistic processing, enhancing translation accuracy and adaptability. However, integrating these approaches introduces scalability and processing efficiency trade-offs, particularly in resource-constrained environments. This study contributes to developing more sophisticated and scalable data translation models tailored for heterogeneous data environments, with practical implications for smart manufacturing and transportation.