Development of Causal Discovery Method with CVT Oil Pump Noise Analysis
CVTオイルポンプ音を題材とした因果探索手法の開発
- Delivery
- Available on this site
- Format
- Price
- Non-members (tax incl.):¥1,100 Members (tax incl.):¥880
- Publication code
- 20224257
- Paper/Info type
- Journal of Society of Automotive Engineers of Japan
Vol.76 No.4
- Pages
- 84-90(Total 7 p)
- Date of publication
- Apr 2022
- Publisher
- JSAE
- Language
- Japanese
Detailed Information
Category(J) | ホットトピックス Translation |
---|---|
Category(E) | Hot Topics |
Author(J) | 1) 小山 智樹, 2) 山本 宇紘, 3) 斎藤 誠, 4) 山下 寛子, 5) 金子 隆, 6) 浅野 貴文 |
Author(E) | 1) Tomoki Koyama, 2) Takahiro Yamamoto, 3) Makoto Saito, 4) Hiroko Yamashita, 5) Takashi Kaneko, 6) Takafumi Asano |
Affiliation(J) | 1) SUBARU, 2) SUBARU, 3) SUBARU, 4) SUBARU, 5) SUBARU, 6) SUBARU |
Abstract(J) | CVT構造が複雑化する中,計測データ量がますます膨大となり,オイルポンプ音の起振源や伝達経路の特定が困難になっている.そこで,短時間で確度が高い要因分析を行うため,統計的因果探索手法LiNGAMを用い,分析の効率化を図る.本稿は,自動車開発特有の時系列・多点計測データへの活用方法を中心に紹介する. Translation |
Abstract(E) | To elucidate main excitation force and transfer path of pump noise requires a huge effort and resource especially because of CVT is getting complicated hardware and control system. We used LiNGAM(Linear Non-Gaussian Acyclic Model)for understanding the causal structure of the issues to efficiency estimate the key factor from the measurement data. This article introduces the technical tips and the usefulness of this method with typical measurement data. |