본문 바로가기 주메뉴 바로가기
국회도서관 홈으로 정보검색 소장정보 검색

결과 내 검색

동의어 포함

초록보기

This study develops and evaluates a prompt-driven large language model (LLM) agent for section design of doubly reinforced concrete (RC) beams. Using Google Gemini (Gems), an engineering “expert” that operates without fine-tuning by uploading ACI-318 provisions, sample design documents, and a database of prior beam designs was developed. The agent interprets code clauses, formulas, and constraints from these materials and retrieves similar design cases to propose an initial solution. It then incorporates user-specified natural-language constraints—most notably a strength-ratio cap (design strength ≤ 105% of required strength)—to iteratively refine toward safe and economical designs. Beyond reporting member size and reinforcement details, the agent provides step-by-step computational justifications for moment and shear checks, increasing verifiability and instructional value. We benchmark the LLM-generated designs against results from the commercial program MIDAS/Design+ and observe close agreement. In several scenarios, the constraint-guided LLM solutions are more material-efficient while remaining code-compliant. The workflow also supports batch processing from spreadsheet inputs, enabling practical automation across multiple beams. The approach requires no additional model training or coding making it accessible to non-developer practitioners. Results indicate that a general-purpose LLM, properly grounded with code documents and examples, can achieve practice-level performance with transparent reasoning. This demonstrates a viable approach to AI-assisted structural design that is explainable, interactive, and readily integrated with engineering workflows.

권호기사

권호기사 목록 테이블로 기사명, 저자명, 페이지, 원문, 기사목차 순으로 되어있습니다.
기사명 저자명 페이지 원문 목차
고층 건물에서 수평-수직 집풍 시스템의 냉난방 부하 감당률 평가 연구 = Load coverage ratio of a horizontal-vertical wind generation system integrated in high-rise buildings 여태훈, 박정빈, 유현택, 조재완 p. 19-28
기계학습 모델을 활용한 경년열화에 의한 원전구조물 지진취약도 변화 분석 = Investigation of seismic fragility curve of NPP structure due to aging deteriorations using machine learning model 김현수, 안시현, 조혜윤 p. 29-36
래티스 리브형 골 데크 플레이트의 구조 성능 = Structural performance of the lattice integrated rib-type deck plate 오명호, 박성진, 김영호 p. 37-44
길이 조절형 나사식 원형강관 접합부를 적용한 각형강관 보의 휨 성능 평가 = Experimental evaluation of the flexural performance of rectangular steel beams connected by a length-adjustable threaded circular tube 강주화, 김민숙, 이영학 p. 45-52
LLM을 이용한 RC 복근보 단면설계 에이전트 개발 = Development of structural design agent for doubly reinforced beams using LLM 김기철, 김현수 p. 53-60
부식된 철근콘크리트 기둥의 매크로 해석모델 = Macro analytical model of reinforced concrete columns with corroded bars 음영채, 강성훈, 한선진, 신동현 p. 61-69
철계 형상기억합금 및 탄소섬유시트 스트립을 활용한 콘크리트 보의 전단 보강 실험 연구 = Experimental study on shear retrofitting of concrete beams using Fe-SMA and CFRP strips 김채원, 정동혁 p. 71-81
변형률 기반 손상 이미지를 활용한 철근콘크리트 기둥의 CNN 기반 층간변위비 예측 방법 = CNN-based inter-story drift ratio prediction method for reinforced concrete columns using strain-derived damage images 박민석, 최인섭 p. 83-91
Vectran 섬유 고성능 시멘트복합체 보의 휨 성능 = Bending performances of beams reinforced with Vectran fiber-reinforced high-performance cementitious composites 문형주, 양일승, 조창근 p. 93-100
건축적 내러티브 공간개념을 적용한 숭례문 역사공원 계획에 관한 연구 = A study on the application of architectural narrative spatial concepts in the planning of the Sungnyemun Historical Park 김태원 p. 101-113