Machining feature recognition based on deep neural networks to support tight integration with 3D CAD systems
Abstract Recently, studies applying deep learning technology to recognize the machining feature of three-dimensional (3D) computer-aided design (CAD) models are increasing. Since the direct utilization of boundary representation (B-rep) models as input data for neural networks in terms of data struc...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2021-11-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-021-01313-3 |
| _version_ | 1818837071398174720 |
|---|---|
| author | Changmo Yeo Byung Chul Kim Sanguk Cheon Jinwon Lee Duhwan Mun |
| author_facet | Changmo Yeo Byung Chul Kim Sanguk Cheon Jinwon Lee Duhwan Mun |
| author_sort | Changmo Yeo |
| collection | DOAJ |
| description | Abstract Recently, studies applying deep learning technology to recognize the machining feature of three-dimensional (3D) computer-aided design (CAD) models are increasing. Since the direct utilization of boundary representation (B-rep) models as input data for neural networks in terms of data structure is difficult, B-rep models are generally converted into a voxel, mesh, or point cloud model and used as inputs for neural networks for the application of 3D models to deep learning. However, the model’s resolution decreases during the format conversion of 3D models, causing the loss of some features or difficulties in identifying areas of the converted model corresponding to a specific face of the B-rep model. To solve these problems, this study proposes a method enabling tight integration of a 3D CAD system with a deep neural network using feature descriptors as inputs to neural networks for recognizing machining features. Feature descriptor denotes an explicit representation of the main property items of a face. We constructed 2236 data to train and evaluate the deep neural network. Of these, 1430 were used for training the deep neural network, and 358 were used for validation. And 448 were used to evaluate the performance of the trained deep neural network. In addition, we conducted an experiment to recognize a total of 17 types (16 types of machining features and a non-feature) from the B-rep model, and the types for all 75 test cases were successfully recognized. |
| first_indexed | 2024-12-19T03:16:40Z |
| format | Article |
| id | doaj.art-557a425a39c54308ac5e8ef538e14b62 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-12-19T03:16:40Z |
| publishDate | 2021-11-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-557a425a39c54308ac5e8ef538e14b622022-12-21T20:37:52ZengNature PortfolioScientific Reports2045-23222021-11-0111112010.1038/s41598-021-01313-3Machining feature recognition based on deep neural networks to support tight integration with 3D CAD systemsChangmo Yeo0Byung Chul Kim1Sanguk Cheon2Jinwon Lee3Duhwan Mun4School of Mechanical Engineering, Korea UniversitySchool of Mechanical Engineering, Korea University of Technology and EducationDepartment of Integrative Systems Engineering, Ajou UniversitySchool of Mechanical Engineering, Korea UniversitySchool of Mechanical Engineering, Korea UniversityAbstract Recently, studies applying deep learning technology to recognize the machining feature of three-dimensional (3D) computer-aided design (CAD) models are increasing. Since the direct utilization of boundary representation (B-rep) models as input data for neural networks in terms of data structure is difficult, B-rep models are generally converted into a voxel, mesh, or point cloud model and used as inputs for neural networks for the application of 3D models to deep learning. However, the model’s resolution decreases during the format conversion of 3D models, causing the loss of some features or difficulties in identifying areas of the converted model corresponding to a specific face of the B-rep model. To solve these problems, this study proposes a method enabling tight integration of a 3D CAD system with a deep neural network using feature descriptors as inputs to neural networks for recognizing machining features. Feature descriptor denotes an explicit representation of the main property items of a face. We constructed 2236 data to train and evaluate the deep neural network. Of these, 1430 were used for training the deep neural network, and 358 were used for validation. And 448 were used to evaluate the performance of the trained deep neural network. In addition, we conducted an experiment to recognize a total of 17 types (16 types of machining features and a non-feature) from the B-rep model, and the types for all 75 test cases were successfully recognized.https://doi.org/10.1038/s41598-021-01313-3 |
| spellingShingle | Changmo Yeo Byung Chul Kim Sanguk Cheon Jinwon Lee Duhwan Mun Machining feature recognition based on deep neural networks to support tight integration with 3D CAD systems Scientific Reports |
| title | Machining feature recognition based on deep neural networks to support tight integration with 3D CAD systems |
| title_full | Machining feature recognition based on deep neural networks to support tight integration with 3D CAD systems |
| title_fullStr | Machining feature recognition based on deep neural networks to support tight integration with 3D CAD systems |
| title_full_unstemmed | Machining feature recognition based on deep neural networks to support tight integration with 3D CAD systems |
| title_short | Machining feature recognition based on deep neural networks to support tight integration with 3D CAD systems |
| title_sort | machining feature recognition based on deep neural networks to support tight integration with 3d cad systems |
| url | https://doi.org/10.1038/s41598-021-01313-3 |
| work_keys_str_mv | AT changmoyeo machiningfeaturerecognitionbasedondeepneuralnetworkstosupporttightintegrationwith3dcadsystems AT byungchulkim machiningfeaturerecognitionbasedondeepneuralnetworkstosupporttightintegrationwith3dcadsystems AT sangukcheon machiningfeaturerecognitionbasedondeepneuralnetworkstosupporttightintegrationwith3dcadsystems AT jinwonlee machiningfeaturerecognitionbasedondeepneuralnetworkstosupporttightintegrationwith3dcadsystems AT duhwanmun machiningfeaturerecognitionbasedondeepneuralnetworkstosupporttightintegrationwith3dcadsystems |