Published on Wed Nov 15 2017

Can CNN Construct Highly Accurate Models Efficiently for High-Dimensional Problems in Complex Product Designs?

Yu Li, Hu Wang, Juanjuan Liu

Convolutional Neural Network (CNN) is introduced to construct a highly accurate metamodel efficiently. CNN is a potential modeling tool to handle highly nonlinear and dimensional problems (hundreds-dimensional problems) with the limited training samples.

0
0
0
Abstract

With the increase of the nonlinearity and dimension, it is difficult for the present popular metamodeling techniques to construct reliable metamodels. To address this problem, Convolutional Neural Network (CNN) is introduced to construct a highly accurate metamodel efficiently. Considering the inherent characteristics of the CNN, it is a potential modeling tool to handle highly nonlinear and dimensional problems (hundreds-dimensional problems) with the limited training samples. In order to evaluate the proposed CNN metamodel for hundreds-dimensional and strong nonlinear problems, CNN is compared with other metamodeling techniques. Furthermore, several high-dimensional analytical functions are also employed to test the CNN metamodel. Testing and comparisons confirm the efficiency and capability of the CNN metamodel for hundreds-dimensional and strong nonlinear problems. Moreover, the proposed CNN metamodel is also applied to IsoGeometric Analysis (IGA)-based optimization successfully.

Sat Jul 17 2021
Artificial Intelligence
Data-informed Deep Optimization
Complex design problems are common in the scientific and industrial fields. In practice, objective functions or constraints of these problems often do not have explicit formulas. Such optimization problems are especially difficult when design parameters are high-dimensional.
2
0
0
Fri Jun 25 2021
Machine Learning
A mechanistic-based data-driven approach to accelerate structural topology optimization through finite element convolutional neural network (FE-CNN)
A mechanistic data-driven approach is proposed to accelerate structural topology optimization. It uses an in-house developed finite element convolutional neural network (FE-CNN) The approach can be divided into two stages: offline training, and online optimization.
1
0
0
Mon Sep 14 2020
Artificial Intelligence
Accelerating gradient-based topology optimization design with dual-model neural networks
Topology optimization (TO) is a common technique used in free-form designs. To improve the accuracy of sensitivity analyses, dual-model neural networks are constructed. They are integrated into the Solid Isotropic Material with Penalization (SIMP) method to replace FEA.
0
0
0
Sat Jul 04 2020
Machine Learning
Understanding the effect of hyperparameter optimization on machine learning models for structure design problems
Machine learning algorithms (MLAs) have been widely applied in computer-aided engineering design. HOpt leads to few improvements in the MLAs accuracy and robustness for high-dimensional mixed-variable design problems. The HOpt is recommended for the design problems with intermediate complexity.
0
0
0
Thu Feb 11 2021
Artificial Intelligence
Real-Time Topology Optimization in 3D via Deep Transfer Learning
The literature on topology optimization has exploded over the last two decades. We introduce a transfer learning method based on a convolutional neural network. The method is multiple orders of magnitude more efficient than the established gradient-based methods, such as SIMP.
0
0
0
Sat Dec 15 2018
Computer Vision
ABC: A Big CAD Model Dataset For Geometric Deep Learning
ABC-Dataset is a collection of one million Computer-Aided Design(CAD) models for research of geometric deep learning methods and applications. The models are parametrized curves and surfaces.
1
1
2