Inverse Design of Digital Materials Using Corrected Generative Deep Neural Network and Generative Deep Convolutional Neural Network
Generative networks are effective tools for digital materials (DM) inverse design. However, the optimization performance of generative networks is restricted by the increasing discrepancy between the optimized input and the prescribed input domain as the design loop increases. Herein, a correction t...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2023-01-01
|
Series: | Advanced Intelligent Systems |
Subjects: | |
Online Access: | https://doi.org/10.1002/aisy.202200333 |
_version_ | 1797946331024588800 |
---|---|
author | Zhi Wan Ze Chang Yading Xu Yitao Huang Branko Šavija |
author_facet | Zhi Wan Ze Chang Yading Xu Yitao Huang Branko Šavija |
author_sort | Zhi Wan |
collection | DOAJ |
description | Generative networks are effective tools for digital materials (DM) inverse design. However, the optimization performance of generative networks is restricted by the increasing discrepancy between the optimized input and the prescribed input domain as the design loop increases. Herein, a correction technique is incorporated into generative deep neural network (GDNN) and generative deep convolutional neural network (GDCNN). The correction is performed by pulling the machine learning (ML)‐optimized inputs back to the prescribed domain at certain interval during the optimization process instead of only postprocessing at the end. A DM system with two phases, i.e., the matrix phase and the pore phase, is used for the structural design. The datasets are produced using a numerical model and describe the relationship between the material structure and the elastic modulus and tensile strength. The results show that the optimization effectiveness of corrected GDNN/GDCNN significantly improves given the fact that more structures converge to the best structures and fewer nonrepetitive structures are left after optimization, which helps to search for the best structures and decreases the computational burden when verifying the ML‐recommended structures. The corrected GDNN and GDCNN also manage to find structures with higher tensile strength in the new inverse design. |
first_indexed | 2024-04-10T21:09:19Z |
format | Article |
id | doaj.art-ed0031ace92647019a5f51f6572f5f9e |
institution | Directory Open Access Journal |
issn | 2640-4567 |
language | English |
last_indexed | 2024-04-10T21:09:19Z |
publishDate | 2023-01-01 |
publisher | Wiley |
record_format | Article |
series | Advanced Intelligent Systems |
spelling | doaj.art-ed0031ace92647019a5f51f6572f5f9e2023-01-21T05:53:26ZengWileyAdvanced Intelligent Systems2640-45672023-01-0151n/an/a10.1002/aisy.202200333Inverse Design of Digital Materials Using Corrected Generative Deep Neural Network and Generative Deep Convolutional Neural NetworkZhi Wan0Ze Chang1Yading Xu2Yitao Huang3Branko Šavija4Faculty of Civil Engineering and Geosciences Delft University of Technology 2628 CN Delft The NetherlandsFaculty of Civil Engineering and Geosciences Delft University of Technology 2628 CN Delft The NetherlandsFaculty of Civil Engineering and Geosciences Delft University of Technology 2628 CN Delft The NetherlandsFaculty of Civil Engineering and Geosciences Delft University of Technology 2628 CN Delft The NetherlandsFaculty of Civil Engineering and Geosciences Delft University of Technology 2628 CN Delft The NetherlandsGenerative networks are effective tools for digital materials (DM) inverse design. However, the optimization performance of generative networks is restricted by the increasing discrepancy between the optimized input and the prescribed input domain as the design loop increases. Herein, a correction technique is incorporated into generative deep neural network (GDNN) and generative deep convolutional neural network (GDCNN). The correction is performed by pulling the machine learning (ML)‐optimized inputs back to the prescribed domain at certain interval during the optimization process instead of only postprocessing at the end. A DM system with two phases, i.e., the matrix phase and the pore phase, is used for the structural design. The datasets are produced using a numerical model and describe the relationship between the material structure and the elastic modulus and tensile strength. The results show that the optimization effectiveness of corrected GDNN/GDCNN significantly improves given the fact that more structures converge to the best structures and fewer nonrepetitive structures are left after optimization, which helps to search for the best structures and decreases the computational burden when verifying the ML‐recommended structures. The corrected GDNN and GDCNN also manage to find structures with higher tensile strength in the new inverse design.https://doi.org/10.1002/aisy.202200333convolutional neural networkcorrection techniquedigital materialsinverse designstructure optimization |
spellingShingle | Zhi Wan Ze Chang Yading Xu Yitao Huang Branko Šavija Inverse Design of Digital Materials Using Corrected Generative Deep Neural Network and Generative Deep Convolutional Neural Network Advanced Intelligent Systems convolutional neural network correction technique digital materials inverse design structure optimization |
title | Inverse Design of Digital Materials Using Corrected Generative Deep Neural Network and Generative Deep Convolutional Neural Network |
title_full | Inverse Design of Digital Materials Using Corrected Generative Deep Neural Network and Generative Deep Convolutional Neural Network |
title_fullStr | Inverse Design of Digital Materials Using Corrected Generative Deep Neural Network and Generative Deep Convolutional Neural Network |
title_full_unstemmed | Inverse Design of Digital Materials Using Corrected Generative Deep Neural Network and Generative Deep Convolutional Neural Network |
title_short | Inverse Design of Digital Materials Using Corrected Generative Deep Neural Network and Generative Deep Convolutional Neural Network |
title_sort | inverse design of digital materials using corrected generative deep neural network and generative deep convolutional neural network |
topic | convolutional neural network correction technique digital materials inverse design structure optimization |
url | https://doi.org/10.1002/aisy.202200333 |
work_keys_str_mv | AT zhiwan inversedesignofdigitalmaterialsusingcorrectedgenerativedeepneuralnetworkandgenerativedeepconvolutionalneuralnetwork AT zechang inversedesignofdigitalmaterialsusingcorrectedgenerativedeepneuralnetworkandgenerativedeepconvolutionalneuralnetwork AT yadingxu inversedesignofdigitalmaterialsusingcorrectedgenerativedeepneuralnetworkandgenerativedeepconvolutionalneuralnetwork AT yitaohuang inversedesignofdigitalmaterialsusingcorrectedgenerativedeepneuralnetworkandgenerativedeepconvolutionalneuralnetwork AT brankosavija inversedesignofdigitalmaterialsusingcorrectedgenerativedeepneuralnetworkandgenerativedeepconvolutionalneuralnetwork |