An e-Axle Loss Evaluation Method Using Continuous Measurement, Assuming Machine-Learning-Based Data Analysis
機械学習によるデータ解析を前提とした連続計測によるe-Axle損失評価手法
- Delivery
- Available on this site
- Format
- Price
- Non-members (tax incl.)：￥1,100 Members (tax incl.)：￥880
- Publication code
- 20266012
- Paper/Info type
- Proceedings (Autumn)
No.95-26
- Pages
- 1-5(Total 5 p)
- Date of publication
- Oct 2026
- Publisher
- JSAE
- Language
- Japanese
- Event
- 2026 JSAE Annual Congress (Autumn)
Detailed Information
| Author(J) | 1) 児玉 亮哉, 2) 土川 晴久, 3) 松井 弘毅, 4) 犬飼 隆哉, 5) 鷹嶋 一直 |
|---|---|
| Author(E) | 1) Ryoya Kodama, 2) Haruhisa Tsuchikawa, 3) Hiroki Matsui, 4) Takaya Inukai, 5) Kazunao Takashima |
| Affiliation(J) | 1) 日産自動車, 2) 日産自動車, 3) 日産自動車, 4) 日産自動車, 5) 日産自動車 |
| Affiliation(E) | 1) Nissan Motor, 2) Nissan Motor, 3) Nissan Motor, 4) Nissan Motor, 5) Nissan Motor |
| Abstract(J) | 電動車の主要因であるe-Axle損失の計測は，車両状態において回転数・トルクに加え油温・電圧にも依存し，多次元条件の計測が必要で長期化する．本研究では，動作領域で油温・電圧が広く変動するよう連続計測を設計し，取得データに基づく機械学習によりe-Axle損失MAPを短期間で構築し，有効性を確認した． Translation |
| Abstract(E) | Measurement of e-Axle losses, a major loss contributor in electrified vehicles, depends under in-vehicle operating conditions not only on rotational speed and torque but also on oil temperature and voltage. Therefore, measurements across multidimensional conditions are required, resulting in long test durations. In this study, we designed a continuous measurement approach that enables wide variations in oil temperature and voltage over the operating region, and rapidly constructed an e-Axle loss map using machine learning based on the acquired data. The effectiveness of the proposed approach for loss evaluation was confirmed. |
