All news

LLM and GraphRAG-Driven DSM Generation for Cyber-Physical Systems

The study explores LLMs and retrieval-augmented generation, including graph-based, for generating design structure matrices. Methods are tested on a power screwdriver and a CubeSat, covering component relationship detection and component identification, with code released for reproducibility.

Why it matters

It shows how to automate architectural dependency mapping of complex technical systems, useful for their digital models.

Relevant to DT products

Original headline
Retrieval Augmented (Knowledge Graph), and Large Language Model-Driven Design Structure Matrix (DSM) Generation of Cyber-Physical Systems
Read the original: arXiv — Systems and Control (eess.SY)

Translation and summary are machine-generated from the source. The full article is not republished; its rights belong to the source.