Neural parametric representations for thin-shell shape optimisation

TL;DR

This paper introduces a neural parametric representation for thin-shell shape optimisation, enabling flexible, differentiable geometry modeling suitable for gradient-based optimisation of complex structures.

Contribution

The paper presents a novel neural network-based geometric representation (NRep) for thin-shell surfaces, facilitating efficient gradient-based shape optimisation with potential for complex lattice-skin structures.

Findings

Benchmark examples validate the effectiveness of NRep.

The approach enables optimisation of complex shell geometries.

NRep offers a compact and expressive shape representation.

Abstract

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.