Skip to main navigation Skip to search Skip to main content

Knowledge Graph Enhanced Large Language Model for Missile Design

  • Northwestern Polytechnical University Xian
  • National Key Laboratory of Aircraft Configuration Design

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Missile technology, central to precision-guided weapons, demands systematic improvements in overall design methods for enhancing intelligence, precision, and cost-efficiency. Traditional empirical design heavily relies on subjective expert knowledge, leading to inconsistencies and high iterative costs. To address these issues, this study proposes an innovative framework integrating knowledge graph (KG) and large language model (LLM) technologies into missile overall design. We construct a multi-level knowledge association fusion model based on missile modular design philosophy and ontological modeling, achieving structured knowledge representation. Leveraging LLM-based open information extraction with chain-of-thought prompting, we systematically organize and fuse missile design experiences and instances. Furthermore, employing retrieval-augmented generation (RAG), we implement an interpretable missile design knowledge Q&A recommendation system. The developed KG encompasses 18,150 entities and 40,017 relations, demonstrating strong connectivity and comprehensive coverage. The resulting recommendation system effectively supports missile design layouts and instance-specific inquiries, significantly advancing missile overall design technology toward agile, cost-effective, and precise development.

Original languageEnglish
Title of host publicationProceedings of The 2025 Asia-Pacific International Symposium on Aerospace Technology - Proceedings of APISAT 2025
EditorsJinyoung Suk, Shinkyu Jeong, Donghun Park
PublisherSpringer Science and Business Media Deutschland GmbH
Pages69-81
Number of pages13
ISBN (Print)9789819213184
DOIs
StatePublished - 2027
EventAsia-Pacific International Symposium on Aerospace Technology, APISAT 2025 - Seoul Olympic Parkte, Korea, Republic of
Duration: 27 Oct 202529 Oct 2025

Publication series

NameLecture Notes in Mechanical Engineering
ISSN (Print)2195-4356
ISSN (Electronic)2195-4364

Conference

ConferenceAsia-Pacific International Symposium on Aerospace Technology, APISAT 2025
Country/TerritoryKorea, Republic of
CitySeoul Olympic Parkte
Period27/10/2529/10/25

Keywords

  • Knowledge graph (KG)
  • Large language model (LLM)
  • Missile design
  • Retrieval augmented generation (RAG)

Fingerprint

Dive into the research topics of 'Knowledge Graph Enhanced Large Language Model for Missile Design'. Together they form a unique fingerprint.

Cite this