IF-TONIR: iteration-free topology optimization based on implicit neural representations
Topology optimization holds great significance as a research topic in the field of mechanical engineering, aiming to design and optimize structures to achieve desired performance while adhering to specific constraints. However, its high computational complexity and iterative optimization process sev...
| Main Authors: | , , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/173270 |
| _version_ | 1811690235294121984 |
|---|---|
| author | Hu, Jiangbei He, Ying Xu, Baixin Wang, Shengfa Lei, Na Luo, Zhongxuan |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Hu, Jiangbei He, Ying Xu, Baixin Wang, Shengfa Lei, Na Luo, Zhongxuan |
| author_sort | Hu, Jiangbei |
| collection | NTU |
| description | Topology optimization holds great significance as a research topic in the field of mechanical engineering, aiming to design and optimize structures to achieve desired performance while adhering to specific constraints. However, its high computational complexity and iterative optimization process severely impact the efficiency, which presents substantial obstacles to its practical applications. To tackle this challenge, recent research is dedicated to the advancement of iteration-free topology optimization methods that leverage neural networks and deep learning, aiming to directly predict optimal structures through optimization problem configurations. In this paper, we propose IF-TONIR, a novel data-driven topology optimization method that utilizes implicit neural representations. Our approach employs signed distance fields to represent structures, offering compact and smooth representations that effectively eliminate the checkerboard phenomenon commonly observed in density-based methods. IF-TONIR leverages Conditional Variational Autoencoders, which use a CNN-based encoder and a MLP-based decoder to learn and reconstruct optimal structures. We employ the features extracted from physical information as conditions to guide the decoder in generating optimal structures that adhere to specific design domain shapes and boundary conditions. Furthermore, we propose the integration of a topological loss based on persistent homology to train the model. This loss function effectively penalizes the existence of structural disconnections in the reconstructed output, thereby enhancing the overall physical reliability of the generated structures. Various experiments have demonstrated that our iteration-free topology optimization method based on implicit representations can accurately identify regions of high strain energy and generate continuous structures with low compliance. The methods also holds the theoretical capability of outputting optimal structures at any desired resolution. Our code and dataset are available on https://github.com/jbHu67/IF-TONIR.git |
| first_indexed | 2024-10-01T06:00:46Z |
| format | Journal Article |
| id | ntu-10356/173270 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:00:46Z |
| publishDate | 2024 |
| record_format | dspace |
| spelling | ntu-10356/1732702024-01-23T00:53:58Z IF-TONIR: iteration-free topology optimization based on implicit neural representations Hu, Jiangbei He, Ying Xu, Baixin Wang, Shengfa Lei, Na Luo, Zhongxuan School of Computer Science and Engineering Engineering::Computer science and engineering Topology Optimization Implicit Neural Representations Topology optimization holds great significance as a research topic in the field of mechanical engineering, aiming to design and optimize structures to achieve desired performance while adhering to specific constraints. However, its high computational complexity and iterative optimization process severely impact the efficiency, which presents substantial obstacles to its practical applications. To tackle this challenge, recent research is dedicated to the advancement of iteration-free topology optimization methods that leverage neural networks and deep learning, aiming to directly predict optimal structures through optimization problem configurations. In this paper, we propose IF-TONIR, a novel data-driven topology optimization method that utilizes implicit neural representations. Our approach employs signed distance fields to represent structures, offering compact and smooth representations that effectively eliminate the checkerboard phenomenon commonly observed in density-based methods. IF-TONIR leverages Conditional Variational Autoencoders, which use a CNN-based encoder and a MLP-based decoder to learn and reconstruct optimal structures. We employ the features extracted from physical information as conditions to guide the decoder in generating optimal structures that adhere to specific design domain shapes and boundary conditions. Furthermore, we propose the integration of a topological loss based on persistent homology to train the model. This loss function effectively penalizes the existence of structural disconnections in the reconstructed output, thereby enhancing the overall physical reliability of the generated structures. Various experiments have demonstrated that our iteration-free topology optimization method based on implicit representations can accurately identify regions of high strain energy and generate continuous structures with low compliance. The methods also holds the theoretical capability of outputting optimal structures at any desired resolution. Our code and dataset are available on https://github.com/jbHu67/IF-TONIR.git Ministry of Education (MOE) The authors gratefully acknowledge the support provided by the Ministry of Education, Singapore, under its Academic Research Fund Grants (MOE-T2EP20220-0005 & RT19/22), the National Key R&D Program of China under Grant (2021YFA1003003), LiaoNing Revitalization Talents Program (2022RG04), Fundamental Research Funds for the Central Universities (DUT22QN212). 2024-01-23T00:53:58Z 2024-01-23T00:53:58Z 2024 Journal Article Hu, J., He, Y., Xu, B., Wang, S., Lei, N. & Luo, Z. (2024). IF-TONIR: iteration-free topology optimization based on implicit neural representations. Computer-Aided Design, 167, 103639-. https://dx.doi.org/10.1016/j.cad.2023.103639 0010-4485 https://hdl.handle.net/10356/173270 10.1016/j.cad.2023.103639 2-s2.0-85176502250 167 103639 en MOE-T2EP20220-0005 RT19/22 Computer-Aided Design © 2023 Elsevier Ltd. All rights reserved. |
| spellingShingle | Engineering::Computer science and engineering Topology Optimization Implicit Neural Representations Hu, Jiangbei He, Ying Xu, Baixin Wang, Shengfa Lei, Na Luo, Zhongxuan IF-TONIR: iteration-free topology optimization based on implicit neural representations |
| title | IF-TONIR: iteration-free topology optimization based on implicit neural representations |
| title_full | IF-TONIR: iteration-free topology optimization based on implicit neural representations |
| title_fullStr | IF-TONIR: iteration-free topology optimization based on implicit neural representations |
| title_full_unstemmed | IF-TONIR: iteration-free topology optimization based on implicit neural representations |
| title_short | IF-TONIR: iteration-free topology optimization based on implicit neural representations |
| title_sort | if tonir iteration free topology optimization based on implicit neural representations |
| topic | Engineering::Computer science and engineering Topology Optimization Implicit Neural Representations |
| url | https://hdl.handle.net/10356/173270 |
| work_keys_str_mv | AT hujiangbei iftoniriterationfreetopologyoptimizationbasedonimplicitneuralrepresentations AT heying iftoniriterationfreetopologyoptimizationbasedonimplicitneuralrepresentations AT xubaixin iftoniriterationfreetopologyoptimizationbasedonimplicitneuralrepresentations AT wangshengfa iftoniriterationfreetopologyoptimizationbasedonimplicitneuralrepresentations AT leina iftoniriterationfreetopologyoptimizationbasedonimplicitneuralrepresentations AT luozhongxuan iftoniriterationfreetopologyoptimizationbasedonimplicitneuralrepresentations |