A Machine Learning Approach to Estimate Tire Block Force Spectrum for Road Noise Simulation
- Delivery
- Available on this site
- Format
- Price
- Non-members (tax incl.):¥1,100 Members (tax incl.):¥880
- Publication code
- 20265026
- Paper/Info type
- Proceedings (Spring)
No.6-26
- Pages
- 1-5(Total 5 p)
- Date of publication
- May 2026
- Publisher
- JSAE
- Language
- English
- Event
- 2026 JSAE Annual Congress (Spring)
Detailed Information
| Author(J) | 1) Yonghun Kim, 2) Taeyoung Kim, 3) Hyunseok Kang |
|---|---|
| Author(E) | 1) Yonghun Kim, 2) Taeyoung Kim, 3) Hyunseok Kang |
| Affiliation(J) | 1) Hankook Tire, 2) Hankook Tire, 3) Hankook Tire |
| Affiliation(E) | 1) Hankook Tire, 2) Hankook Tire, 3) Hankook Tire |
| Abstract(E) | To predict vehicle road noise using the Frequency Based Sub-structuring (FBS) method or to operate a virtual noise simulator, accurate tire block forces are essential. Prior to manufacturing a physical tire, these forces are commonly estimated through finite-element (FE) analysis; however, FE simulations typically require several days, making it difficult to rapidly assess the impact of design modifications on road-noise performance. To overcome this limitation, this study proposes a data-driven modeling framework capable of predicting the tire block-force spectrum directly from design specifications. The methodology, including feature construction, model training, and validation procedures, is described in detail, and the applicability of the proposed approach is demonstrated through prediction results. |