Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2410.20061 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912935492714496 |
|---|---|
| author | Tsumoto, Ryo Yaji, Kentaro Nomaguchi, Yutaka Fujita, Kikuo |
| author_facet | Tsumoto, Ryo Yaji, Kentaro Nomaguchi, Yutaka Fujita, Kikuo |
| contents | A generative design based on topology optimization provides diverse alternatives as entities in a computational model with a high design degree. However, as the diversity of the generated alternatives increases, the cognitive burden on designers to select the most appropriate alternatives also increases. Whereas the concept identification approach, which finds various categories of entities, is an effective means to structure alternatives, evaluation of their similarities is challenging due to shape diversity. To address this challenge, this study proposes a concept identification framework for generative design using deep learning (DL) techniques. One of the key abilities of DL is the automatic learning of different representations of a specific task. Deep concept identification finds various categories that provide insights into the mapping relationships between geometric properties and structural performance through representation learning using DL. The proposed framework generates diverse alternatives using a generative design technique, clusters the alternatives into several categories using a DL technique, and arranges these categories for design practice using a classification model. This study demonstrates its fundamental capabilities by implementing variational deep embedding, a generative and clustering model based on the DL paradigm, and logistic regression as a classification model. A simplified design problem of a two-dimensional bridge structure is applied as a case study to validate the proposed framework. Although designers are required to determine the viewing aspect level by setting the number of concepts, this implementation presents the identified concepts and their relationships in the form of a decision tree based on a specified level. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_20061 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Deep Concept Identification for Generative Design Tsumoto, Ryo Yaji, Kentaro Nomaguchi, Yutaka Fujita, Kikuo Machine Learning A generative design based on topology optimization provides diverse alternatives as entities in a computational model with a high design degree. However, as the diversity of the generated alternatives increases, the cognitive burden on designers to select the most appropriate alternatives also increases. Whereas the concept identification approach, which finds various categories of entities, is an effective means to structure alternatives, evaluation of their similarities is challenging due to shape diversity. To address this challenge, this study proposes a concept identification framework for generative design using deep learning (DL) techniques. One of the key abilities of DL is the automatic learning of different representations of a specific task. Deep concept identification finds various categories that provide insights into the mapping relationships between geometric properties and structural performance through representation learning using DL. The proposed framework generates diverse alternatives using a generative design technique, clusters the alternatives into several categories using a DL technique, and arranges these categories for design practice using a classification model. This study demonstrates its fundamental capabilities by implementing variational deep embedding, a generative and clustering model based on the DL paradigm, and logistic regression as a classification model. A simplified design problem of a two-dimensional bridge structure is applied as a case study to validate the proposed framework. Although designers are required to determine the viewing aspect level by setting the number of concepts, this implementation presents the identified concepts and their relationships in the form of a decision tree based on a specified level. |
| title | Deep Concept Identification for Generative Design |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2410.20061 |