폐쇄형 네트워크 기반 LLM 에이전트를 활용한 유한요소해석 모델 자동 생성 시스템
LLM Agent-Based Automatic Generation System for Finite Element Analysis Models in Closed Network Environments
※ 기관로그인 시 무료 이용이 가능합니다.
※ 학술발표대회집, 워크숍 자료집 중 4페이지 이내 논문은 '요약'만 제공되는 경우가 있으니, 구매 전에 간행물명, 페이지 수 확인 부탁 드립니다.
4,000원
원문정보
초록
영어
Finite element analysis is widely used to predict the stress and deformation behavior of structures, but constructing analysis models and assigning boundary conditions require specialized expertise, limiting accessibility for non-experts. Recently, AI agents based on large language models (LLMs) have been actively studied. However, commercial LLMs cannot access confidential corporate data. They also carry the risk of hallucination, where incorrect values may be reflected in the analysis results. In addition, security concerns often prevent their use with proprietary design data. To address these limitations, this study employed open-source LLM that can be operated within a closed network, to automatically extract design conditions from natural language input, and introduced a parsing and validation procedure to prevent hallucination-induced errors. The validated data were reflected in the analysis model by precisely substituting only pre-defined tagged variables within the pre-processing python script, thereby modifying the model without altering the remaining script structure. The proposed system was applied to a case study involving the design modification of robot arms in a multi-joint robot used for ship-building industry; the cross-sectional shape, length, and material of the robot arms specified through natural language input were accurately reflected in the generated script, while unintended parts remained unchanged. These results demonstrate that users without expertise in finite element analysis can modify analysis models and obtain results solely through a conversational interface.
목차
Abstract 1. 서론 2. Proposed model 2.1 Overall Workflow 2.2 Local LLM-Based Interface 2.3 Automatic modification of the script 3. Case study 3.1 Application to multi-joint robot 3.2 Result 4. Discussion 5. Conclusion Acknowledgements References