An AI-Assisted Design Method for Topology Optimization without Pre-Optimized Training Data

  title={An AI-Assisted Design Method for Topology Optimization without Pre-Optimized Training Data},
  author={A. von Halle and Lucio Flavio Dr.-Ing. Campanile and Alexander Hasse},
  journal={Proceedings of the Design Society},
  pages={1589 - 1598}
Abstract Engineers widely use topology optimization during the initial process of product development to obtain a first possible geometry design. The state-of-the-art method is iterative calculation, which requires both time and computational power. This paper proposes an AI-assisted design method for topology optimization, which does not require any optimized data. The presented AI-assisted design procedure generates geometries that are similar to those of conventional topology optimizers, but… 

Topology Optimisation under Uncertainties with Neural Networks

Two neural network architectures (NN) are developed that are capable of predicting the gradient step of the optimisation procedure and are observed to outperforms the classical optimisation method since larger iteration steps become viable.

Intelligent Generation Method of Innovative Structures Based on Topology Optimization and Deep Learning

The research results showed that the proposed approach of structural generation based on topology optimization and deep learning is feasible, and can not only generate innovative structures but also optimize the material consumption and mechanical performance further.

On the use of artificial neural networks in topology optimisation

The question of how methods from the field of artificial intelligence can help improve the conventional frameworks for topology optimisation has received increasing attention over the last few years.



Accelerating gradient-based topology optimization design with dual-model artificial neural networks

Dual-model artificial neural networks that are trained with both forward and sensitivity data are constructed and integrated into the Solid Isotropic Material with Penalization (SIMP) method to replace the FEA.

3D Topology Optimization using Convolutional Neural Networks

A data-driven approach based on a 3D encoder-decoder Convolutional Neural Network architecture for accelerating 3D topology optimization and to determine the optimal computational strategy for its deployment is proposed.

A Systematic Study of Deep Generative Models for Rapid Topology Optimization

Four distinctive models were successfully developed, trained, and evaluated to generate rapid designs with comparable results to that of conventional algorithms, highlighting the effectiveness of the novel design problem representation and proposed generative models in rapid topology optimization.

Universal machine learning for topology optimization

Accelerated topology optimization by means of deep learning

The representation capabilities and the computational advantages offered by the proposed DBN-based methodology coupled with the SIMP approach are investigated in several benchmark topology optimization test examples where it is observed more than one order of magnitude reduction on the iterations that were originally required by SIMP.

TOuNN: Topology Optimization using Neural Networks

This paper demonstrates that one can directly execute topology optimization (TO) using neural networks (NN) and uses the NN’s activation functions to represent the popular Solid Isotropic Material with Penalization (SIMP) density field.

Topology Optimization Using Convolutional Neural Network

Four types of input images and two encoder–decoder architectures are developed, and their performance is studied using identity mapping to obtain the optimized structure of a cantilever beam which is fixed at one end and a constant load is applied at the other end.

A Novel Topology Optimization Approach using Conditional Deep Learning

In this study, a novel topology optimization approach based on conditional Wasserstein generative adversarial networks (CWGAN) is developed to replicate the conventional topology optimization