Length Scale Control in Topology Optimization using Fourier Enhanced Neural Networks
arXiv:2109.01861
Abstract
Length scale control is imposed in topology optimization (TO) to make designs amenable to manufacturing and other functional requirements. Broadly, there are two types of length-scale control in TO: \emph {exact} and \emph {approximate}. While the former is desirable, its implementation can be difficult, and is computationally expensive. Approximate length scale control is therefore preferred, and is often sufficient for early stages of design. In this paper we propose an approximate length scale control strategy for TO, by extending a recently proposed density-based TO formulation using neural networks (TOuNN). Specifically, we enhance TOuNN with a Fourier space projection, to control the minimum and/or maximum length scales. The proposed method does not involve additional constraints, and the sensitivity computations are automated by expressing the computations in an end-end differentiable fashion using the neural net's library. The proposed method is illustrated through several numerical experiments for single and multi-material designs.
arXiv commentSubmitted to Computer Aided Design, 2021
References in corpus (8)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Infill Optimization for Additive Manufacturing -- Approaching Bone-like Porous Structures
- NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
- On the Spectral Bias of Neural Networks
- Imposing minimum and maximum member size, minimum cavity size, and minimum separation distance between solid members in topology optimization
- Multi-constrained topology optimization via the topological sensitivity
- Descending through a Crowded Valley - Benchmarking Deep Learning Optimizers