Estimation of All Rib Defl ections of THOR-ATD by Means of Deep Neural Network Model
深層学習を用いたTHOR-ATDの全肋骨変形量の推定
- Delivery
- Available on this site
- Format
- Price
- Non-members (tax incl.)：￥1,100 Members (tax incl.)：￥880
- Publication code
- 20244013
- Paper/Info type
- Journal of Society of Automotive Engineers of Japan
Vol.78 No.1
- Pages
- 96-102(Total 7 p)
- Date of publication
- Jan 2024
- Publisher
- JSAE
- Language
- Japanese
Detailed Information
| Category(J) | ホットトピックス Translation |
|---|---|
| Category(E) | Hot Topics |
| Author(J) | 1) 川渕 貴之, 2) 三上 秀則, 3) 山戸田 武史, 4) 永井 洋介 |
| Author(E) | 1) Takayuki Kawabuchi, 2) Hidenori Mikami, 3) Takeshi Yamatoda, 4) Yosuke Nagai |
| Affiliation(J) | 1) 本田技術研究所, 2) 本田技研工業, 3) IDAJ, 4) フォトロン |
| Abstract(J) | 正面衝突事故においては高齢になるほど肋骨骨折を併発して死亡する割合が増加する。肋骨骨折を低減する拘束装置開発には胸部変形量を詳細に計測することは重要である。本稿では、衝突ダミーの計測器付き肋骨の変形量から深層学習モデルを用いて計測器のない肋骨の変形量を推定し、全ての肋骨の変形量を知る手法を紹介する。 Translation |
| Abstract(E) | The fatality rate of thoracic injury for elderly occupants in vehicle accidents is significantly high and associated with the number of fractured ribs (NFR) . The objective of this research is to estimate the deflections of all ribs by means of a neural network model using time-histories of rib deflections from four IR-TRACCs and the crash velocity without any installation of additional measurement devices in order to improve a NFR estimation accuracy. Although the number of training datasets was small, the neural network model trained by FEM simulation data could estimate the rib deflections with small error. |
