Introduction to the Deep Neural Network Direct Stiffness Method (DNN-DSM)
This blog post briefly presents a novel approach for carrying out a computationally economical beam-element analysis that accounts for the nonlinear load-displacement and moment-rotation behavior of RHS/SHS (rectangular and squared hollow sections) of various local slenderness: the “DNN-DSM”, which makes use of machine learning techniques (deep neural networks – DNN) to predict the nonlinear stiffness matrix terms in a beam-element formulation for implementation in the Direct Stiffness Method (DSM). The whole idea is grounded on trained DNN models from an extensive pool of shell-based simulations including linear buckling analysis (LBA) and geometrically and materially nonlinear analysis with imperfections (GMNIA).
Read more