Data-driven Topology Optimization of Channel Flow Problems

TL;DR

This paper introduces a neural network approach for fluid topology optimization that significantly reduces computation time and demonstrates high accuracy in channel flow problems, outperforming traditional iterative methods.

Contribution

The study adapts and tests CNN, cGAN, and DDIM neural networks for fluid topology optimization, achieving fast, accurate results without iterative calculations.

Findings

663 times faster than conventional methods

High pixel accuracy in topology results

Effective generalization for Stokes flow problems

Abstract

Typical topology optimization methods require complex iterative calculations, which cannot meet the requirements of fast computing applications. The neural network is studied to reduce the time of computing the optimization result, however, the data-driven method for fluid topology optimization is less of discussion. This paper intends to introduce a neural network architecture that avoids time-consuming iterative processes and has a strong generalization ability for topology optimization for Stokes flow. Different neural network methods including Convolution Neural Networks (CNN), conditional Generative Adversarial Networks (cGAN), and Denoising Diffusion Implicit Models (DDIM) which have been already successfully used in solid structure optimization problems are mutated and examined for fluid topology optimization cases. The presented neural network method is tested on the channel flow topology optimization problems for Stokes flow. The results have shown that our presented method has high pixel accuracy and gains a 663 times decrease on average in execution time compared with the conventional method.