Neural Network Material Models Determined From Structural Tests

157 p.Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 1997.A nested modular neural network structure is introduced in this study and applied to model uniaxial concrete behavior under cyclic loading and biaxial concrete behavior under monotonic loading and unloading. The results show that the nested modular neural network structure is more flexible and efficient to model path-dependent material behavior than the fully-connected internal neural network structure.U of I OnlyRestricted to the U of I community idenfinitely during batch ingest of legacy ETD