Data-driven topology optimization (DDTO) for three-dimensional continuum structures

Developing appropriate analytic-function-based constitutive models for new materials with nonlinear mechanical behavior is demanding. For such kinds of materials, it more challenging to realize the integrated design from collection material experiment under classical topology optimization framework based on models. The present work proposes a mechanistic-based data-driven (DDTO) three-dimensional continuum structures finite deformation. In DDTO framework, help neural networks and explicit method, optimal deformation implemented only using uniaxial equi-biaxial experimental data. Numerical examples illustrate effectiveness approach, which paves way composed novel without available relations.