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

TL;DR

This paper introduces a CNN-based metamodeling approach that effectively handles highly nonlinear, high-dimensional problems in complex product design, demonstrating superior efficiency and accuracy over traditional methods.

Contribution

It proposes a novel CNN-based metamodeling technique tailored for high-dimensional, nonlinear problems, validated through extensive testing and application in IGA-based optimization.

Findings

CNN outperforms traditional metamodels in high-dimensional nonlinear problems.

The CNN metamodel is efficient with limited training samples.

Successful application to IGA-based optimization.

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.