Multi-Requirement Compatible Design Study Technique for Exterior Panel by Machine Learning
機械学習を活用した車両外板の複数要件両立検討技術
- Delivery
- Available on this site
- Format
- Price
- Non-members (tax incl.):¥1,100 Members (tax incl.):¥880
- Publication code
- 20216124
- Paper/Info type
- Proceedings (Autumn)
No.108-21
- Pages
- 1-6(Total 6 p)
- Date of publication
- Oct 2021
- Publisher
- JSAE
- Language
- Japanese
- Event
- 2021 JSAE Annual Congress (Autumn) [Online]
Detailed Information
Author(J) | 1) 木村 成竹, 2) 岡田 直樹, 3) 山本 征吾, 4) 有本 慎一 |
---|---|
Author(E) | 1) Masatake Kimura, 2) Naoki Okada, 3) Seigo Yamamoto, 4) Shinichi Arimoto |
Affiliation(J) | 1) トヨタ自動車, 2) トヨタ自動車, 3) トヨタ自動車, 4) トヨタ自動車 |
Affiliation(E) | 1) Toyota Motor, 2) Toyota Motor, 3) Toyota Motor, 4) Toyota Motor |
Abstract(J) | 車両外板開発では意匠性や各種性能要件を両立させた形状を短期間で導出することが求められる.本論文では,機械学習の活用により意匠案から各種部品特性を瞬時に予測し,目標未達や背反があれば会議のその場で両立検討を実施し関係者で合意が図れるといった「同席開発」を実現するための検討手法の構築を目的とした. Translation |
Abstract(E) | Finding multi-requirement compatible design in a short period is required in body exterior panel development. This paper proposes a method which enable “concurrent development” where from a prototype design required characteristics are predicted instantly. If requirements are not met, counter measure study can be conducted on the spot and a design agreement can be reached within one meeting. The proposed method is applied to an actual development and its effectiveness is confirmed. |