A Novel Self‐Updating Design Method for Complex 3D Structures Using Combined Convolutional Neuron and Deep Convolutional Generative Adversarial Networks
Mechanical design is one of the essential disciplines in engineering applications, while inspirations of design ideas highly depend on the ability and prior knowledge of engineers or designers. With the rapid development of machine learning (ML) techniques, artificial intelligence (AI)‐based design...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-06-01
|
| Series: | Advanced Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/aisy.202100186 |
| _version_ | 1811239441831821312 |
|---|---|
| author | Zewen Gu Xiaonan Hou Mohamed Saafi Jianqiao Ye |
| author_facet | Zewen Gu Xiaonan Hou Mohamed Saafi Jianqiao Ye |
| author_sort | Zewen Gu |
| collection | DOAJ |
| description | Mechanical design is one of the essential disciplines in engineering applications, while inspirations of design ideas highly depend on the ability and prior knowledge of engineers or designers. With the rapid development of machine learning (ML) techniques, artificial intelligence (AI)‐based design methods are promising tools for the design of advanced engineering systems. So far, there have been some studies of 2D patterns and structural designs based on ML techniques. However, a particular challenge remains in allowing complex 3D mechanical designs using ML techniques. Herein, a novel and experience‐free method to equip ML models with 3D design capabilities by combining a convolutional neuron network (CNN) with a deep convolutional generative adversarial network (DCGAN) is developed. The model directly receives 2D image‐based training data that define the complex 3D structures of a specific machine part. After the training process, an infinite number of new 3D designs can be generated by the proposed model, with their geometric and mechanical properties being accurately predicted at the same time. Moreover, the generated new designs can be fed back to expand the original input datasets for further ML model training and updating. |
| first_indexed | 2024-04-12T13:01:28Z |
| format | Article |
| id | doaj.art-39bd8e7224d94d94b107520c508f1951 |
| institution | Directory Open Access Journal |
| issn | 2640-4567 |
| language | English |
| last_indexed | 2024-04-12T13:01:28Z |
| publishDate | 2022-06-01 |
| publisher | Wiley |
| record_format | Article |
| series | Advanced Intelligent Systems |
| spelling | doaj.art-39bd8e7224d94d94b107520c508f19512022-12-22T03:32:10ZengWileyAdvanced Intelligent Systems2640-45672022-06-0146n/an/a10.1002/aisy.202100186A Novel Self‐Updating Design Method for Complex 3D Structures Using Combined Convolutional Neuron and Deep Convolutional Generative Adversarial NetworksZewen Gu0Xiaonan Hou1Mohamed Saafi2Jianqiao Ye3Department of Engineering Engineering Building Lancaster University Lancaster LA1 4YW UKDepartment of Engineering Engineering Building Lancaster University Lancaster LA1 4YW UKDepartment of Engineering Engineering Building Lancaster University Lancaster LA1 4YW UKDepartment of Engineering Engineering Building Lancaster University Lancaster LA1 4YW UKMechanical design is one of the essential disciplines in engineering applications, while inspirations of design ideas highly depend on the ability and prior knowledge of engineers or designers. With the rapid development of machine learning (ML) techniques, artificial intelligence (AI)‐based design methods are promising tools for the design of advanced engineering systems. So far, there have been some studies of 2D patterns and structural designs based on ML techniques. However, a particular challenge remains in allowing complex 3D mechanical designs using ML techniques. Herein, a novel and experience‐free method to equip ML models with 3D design capabilities by combining a convolutional neuron network (CNN) with a deep convolutional generative adversarial network (DCGAN) is developed. The model directly receives 2D image‐based training data that define the complex 3D structures of a specific machine part. After the training process, an infinite number of new 3D designs can be generated by the proposed model, with their geometric and mechanical properties being accurately predicted at the same time. Moreover, the generated new designs can be fed back to expand the original input datasets for further ML model training and updating.https://doi.org/10.1002/aisy.202100186convolutional neuron networksdeep convolutional generative adversarial networksengineering designshelical structuresmachine learning |
| spellingShingle | Zewen Gu Xiaonan Hou Mohamed Saafi Jianqiao Ye A Novel Self‐Updating Design Method for Complex 3D Structures Using Combined Convolutional Neuron and Deep Convolutional Generative Adversarial Networks Advanced Intelligent Systems convolutional neuron networks deep convolutional generative adversarial networks engineering designs helical structures machine learning |
| title | A Novel Self‐Updating Design Method for Complex 3D Structures Using Combined Convolutional Neuron and Deep Convolutional Generative Adversarial Networks |
| title_full | A Novel Self‐Updating Design Method for Complex 3D Structures Using Combined Convolutional Neuron and Deep Convolutional Generative Adversarial Networks |
| title_fullStr | A Novel Self‐Updating Design Method for Complex 3D Structures Using Combined Convolutional Neuron and Deep Convolutional Generative Adversarial Networks |
| title_full_unstemmed | A Novel Self‐Updating Design Method for Complex 3D Structures Using Combined Convolutional Neuron and Deep Convolutional Generative Adversarial Networks |
| title_short | A Novel Self‐Updating Design Method for Complex 3D Structures Using Combined Convolutional Neuron and Deep Convolutional Generative Adversarial Networks |
| title_sort | novel self updating design method for complex 3d structures using combined convolutional neuron and deep convolutional generative adversarial networks |
| topic | convolutional neuron networks deep convolutional generative adversarial networks engineering designs helical structures machine learning |
| url | https://doi.org/10.1002/aisy.202100186 |
| work_keys_str_mv | AT zewengu anovelselfupdatingdesignmethodforcomplex3dstructuresusingcombinedconvolutionalneuronanddeepconvolutionalgenerativeadversarialnetworks AT xiaonanhou anovelselfupdatingdesignmethodforcomplex3dstructuresusingcombinedconvolutionalneuronanddeepconvolutionalgenerativeadversarialnetworks AT mohamedsaafi anovelselfupdatingdesignmethodforcomplex3dstructuresusingcombinedconvolutionalneuronanddeepconvolutionalgenerativeadversarialnetworks AT jianqiaoye anovelselfupdatingdesignmethodforcomplex3dstructuresusingcombinedconvolutionalneuronanddeepconvolutionalgenerativeadversarialnetworks AT zewengu novelselfupdatingdesignmethodforcomplex3dstructuresusingcombinedconvolutionalneuronanddeepconvolutionalgenerativeadversarialnetworks AT xiaonanhou novelselfupdatingdesignmethodforcomplex3dstructuresusingcombinedconvolutionalneuronanddeepconvolutionalgenerativeadversarialnetworks AT mohamedsaafi novelselfupdatingdesignmethodforcomplex3dstructuresusingcombinedconvolutionalneuronanddeepconvolutionalgenerativeadversarialnetworks AT jianqiaoye novelselfupdatingdesignmethodforcomplex3dstructuresusingcombinedconvolutionalneuronanddeepconvolutionalgenerativeadversarialnetworks |