Neural parametric representations for thin-shell shape optimisation
This work addresses shape optimization for thin-shell structures, which is incremental as it introduces a neural representation for an existing optimization framework.
The paper tackled the problem of shape optimization for thin-shell structures by proposing a neural parametric representation (NRep) based on a neural network with periodic activation functions, which was applied to structural compliance optimization with a volume constraint, and benchmark examples demonstrated its effectiveness.
Shape optimisation of thin-shell structures requires a flexible, differentiable geometric representation suitable for gradient-based optimisation. We propose a neural parametric representation (NRep) for the shell mid-surface based on a neural network with periodic activation functions. The NRep is defined using a multi-layer perceptron (MLP), which maps the parametric coordinates of mid-surface vertices to their physical coordinates. A structural compliance optimisation problem is posed to optimise the shape of a thin-shell parameterised by the NRep subject to a volume constraint, with the network parameters as design variables. The resulting shape optimisation problem is solved using a gradient-based optimisation algorithm. Benchmark examples with classical solutions demonstrate the effectiveness of the proposed NRep. The approach exhibits potential for complex lattice-skin structures, owing to the compact and expressive geometry representation afforded by the NRep.