☆ 4.7 Article

Deep learning driven real time topology optimisation based on initial stress learning

ADVANCED ENGINEERING INFORMATICS (2022)

Journal

ADVANCED ENGINEERING INFORMATICS

Volume 51, Issue -, Pages -

Publisher

ELSEVIER SCI LTD

DOI: 10.1016/j.aei.2021.101472

Keywords

Topology optimisation; Deep learning based optimisation; Convolutional neural networks; Major principal stress matrix

Funding

National Natural Science Foundation of China, China [U1906-233, 11732004]
National Key R&D Program of China, China [2017YFC0307201]
Key R&D Program of Shandong Province, China [2019JZZY01-0801]
Fundamental Research Funds for the Central Universities, China [DUT20ZD213, DUT-20LAB308]

Ask authors/readers for more resources

Protocol

Community support

Reagent

Community support

Automated Summary New
Abstract

The paper introduces a deep learning approximate algorithm based on convolutional neural networks for real-time topology optimization, which can produce high-precision topological prediction results with a relatively small number of samples and has higher real-time performance compared to traditional topology optimization methods.

Topology optimisation can facilitate engineers in proposing efficient and novel conceptual design schemes, but the traditional FEM based optimization demands significant computing power and makes the real time optimization impossible. Based on the convolutional neural network (CNN) method, a new deep learning approximate algorithm for real time topology optimisation is proposed. The algorithm learns from the initial stress (LIS), which is defined as the major principal stress matrix obtained from finite element analysis in the first iteration of classical topology optimisation. The initial major principal stress matrix of the structure is used to replace the load cases and boundary conditions of the structure as independent variables, which can produce topological prediction results with high accuracy based on a relatively small number of samples. Compared with the traditional topology optimisation method, the new method can produce a similar result in real time without repeated iterations. A classic short cantilever problem was used as an example, and the optimized topology of the cantilever structure is predicted successfully by the established approximate algorithm. By comparing the prediction results to the structural optimisation results obtained by the classical topology optimisation method, it is discovered that the two results are highly approximate, which verifies the validity of the established algorithm. Furthermore, a new algorithm evaluation method is proposed to evaluate the effects of using different methods to select samples on the prediction performance of the optimized topology, and the results were promising and concluded in the end.

Authors

I am an author on this paper

Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7

Not enough ratings

Secondary Ratings

Novelty

Significance

Scientific rigor

Rate this paper

Soil texture prediction with automated deep convolutional neural networks and population-based learning

Osayande Pascal Omondiagbe, Linda Lilburne, Sherlock A. Licorish, Stephen G. MacDonell

Summary: The performance of convolutional neural networks (CNNs) in soil spectroscopy requires tuning of network architectures which is time-consuming and requires machine learning expertise. This study proposes an approach that combines the design of CNN components with tuning the hyperparameters for soil spectroscopy modeling. The results show that the proposed approach achieves improved model performance compared to previous studies, indicating its potential for advancing the use of CNNs in soil spectroscopy modeling.

GEODERMA (2023)