Browse > Article

System for Preliminary Structural Design using Multi-Level Neural Networks  

김남희 (서울대학교 지구환경시스템공학부)
장승필 (서울대학교 지구환경시스템공학부)
이승철 (서울대학교 토목공학과 대학원 석사졸업)
Publication Information
Journal of the Computational Structural Engineering Institute of Korea / v.15, no.2, 2002 , pp. 261-270 More about this Journal
Abstract
The use of ANN is appropriate to computerize the information and knowledge used in the preliminary design stage where it lacks of formality of representation of designers' experience and intuition. Considering that there exists very little design information in preliminary design stage to start with, the ANN model for this stage must be designed to have input much less than output. However, this situation usually causes various problems such as in teaming time, convergence and reliability of solutions. To address this problem, this paper proposes multi-level neural networks lot progressive structural design considering that all the design information can not be obtained at a time but we growing gradually. The use of multi-level networks developed in this paper has been proved its validity by applying it to the preliminary design of cable-stayed bridges.
Keywords
multi-level neural networks; preliminary structural design; cable-stayed bridges;
Citations & Related Records
연도 인용수 순위
  • Reference
1 장대교량의 설계 및 시공에 관한 연구, 건기연 95- SE-112-2, 한국건설기술연구원, 1995
2 Abhijit Mukherjee and Jayant M. Deshpande, 'Modeling Initial Design Process Using Artificial Neural Network', Journal of Computing in Civil Engineering, ASCE, Vol. 9, No. 3, 1995, pp.194-200   DOI   ScienceOn
3 김남희, 이승철, 장승필, '인공신경망을 이용한 사장교 초기 구조설계시스템 개발', 한국전산구조공학회 학술발표회 논문집, 1999, pp.421-428
4 Namhee Kim Hong and Sung-Gul Hong, 'Application of Entity-Based Approach for Unified Representation of Design Alternatives for Structural Design', Advances in Engineering Software, Vol. 32, No. 8, 2001, pp.599-610   DOI   ScienceOn
5 Namhee Kim Hong and Sung-Gul Hong, 'Entity-Based Product and Process Models for Structural Design', Journal of Computing in Civil Engineering, ASCE, Vol. 9, No. 3, 1998, pp.194-200   DOI   ScienceOn
6 Martin T. Hagan, Howard B. Demuth and Mark Beale, Neural Network Design, PWS Publishing Company, 1996