터널구조물 해석을 위한 인공신경망 기반 비선형 유한요소해석 기법의 개발

Development of Neural Network Based Nonlinear Finite Element Procedure for Tunnel Structures

This paper describes a new concept of finite element analysis, which is based on neural network based material models (NNCMs) without invoking any pre-chosen mathematical framework. NNCMs have several advantages over conventional constitutive models (CCMs) and once plugged in a finite element (FE) engine, can be used for FE analysis in a manner similar to CCMs. The paper demonstrates a FE framework in which NNCMs are incorporated and also proposes a strategy for data enhancement by invoking the assumption of isotropy of the material. It is shown through some illustrative examples that this provides a better training environment for a generalized NNCM in which stress and strain components are used as effects and cause. Form this study, it appears that there is a prima facia case for developing NNCMs for materials for which mathematical theories become too complex and a large number of material parameters and constants have to be identified or determined.