A Study on Online LS-SVM for Modelling of Electronically-Controlled Automotive Engine Performance
- Delivery
- Available on this site
- Format
- Price
- Non-members (tax incl.)：￥1,100 Members (tax incl.)：￥880
- Publication code
- 20080550
- Paper/Info type
- AVEC
- Pages
- 1-6(Total 6 p)
- Date of publication
- Oct 2008
- Publisher
- Others, Unknown
- Language
- English
- Event
- AVEC '08
Detailed Information
| Category(E) | Powertrain and Drivetrain Control II |
|---|---|
| Author(E) | 1) C. m. Vong, 2) P. k. Wong, 3) K. Li, 4) R. Zhang |
| Affiliation(E) | 1) University of Macau, 2) University of Macau, 3) University of Macau, 4) University of Macau |
| Abstract(J) | オンライン処理を用いて試験値よりトルク関数を即時更新する手法を開発した．N回の試行によって取得した該関数は，新しいデータが得られると表記手法により直ちにN+1に更新される．従来の新規再計算の結果と比較すると実際との誤差は本手法が僅かに劣るが，オンラインの即応性により台上試験規模を大幅縮小した新しいチューンアップを可能とした． Translation |
| Abstract(E) | Modern automotive engines are controlled by the electronic control unit (ECU). The engine performance referred to as output torque is significantly affected by the setup of control parameters in the ECU. Traditional ECU tune-up is done by trial-and-error method through repeated dynamometer tests. LS-SVM (Least Squares Support Vector Machines) is a powerful machine learning technique which can handle complex and nonlinear function estimation problems. It was employed to estimate the above engine performance function. However, current LS-SVM is an offline algorithm, i.e., the estimated torque functions built from LS-SVM can not be updated with the subsequent expensive dynamometer tests for verification. In the paper, online LS-SVM is presented and used for estimating the engine torque functions for precision prediction so that the number of dynamometer tests can be significantly reduced. |
