AICLDec 7, 2023

Using a Large Language Model to generate a Design Structure Matrix

arXiv:2312.04134v15 citationsh-index: 1Nat Lang Process J
Originality Incremental advance
AI Analysis

This work addresses productivity improvements for engineers and researchers in complex system design, though it is incremental as it builds on existing DSM methods with LLM automation.

The paper tackled the time-consuming and costly manual generation of Design Structure Matrices (DSM) by using a Large Language Model (LLM) to automate the process, achieving a 77.3% accuracy in reproducing entries from a published diesel engine DSM.

The Design Structure Matrix (DSM) is an established method used in dependency modelling, especially in the design of complex engineering systems. The generation of DSM is traditionally carried out through manual means and can involve interviewing experts to elicit critical system elements and the relationships between them. Such manual approaches can be time-consuming and costly. This paper presents a workflow that uses a Large Language Model (LLM) to support the generation of DSM and improve productivity. A prototype of the workflow was developed in this work and applied on a diesel engine DSM published previously. It was found that the prototype could reproduce 357 out of 462 DSM entries published (i.e. 77.3%), suggesting that the work can aid DSM generation. A no-code version of the prototype is made available online to support future research.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes