タイヤ車外騒音の評価技術開発と発生メカニズム検討（第2報）

宗　虎太郎・谷本　隆一（セキソー）

前報では，タイヤから発生する車外騒音のマップ化と，前後輪からの放射音の離間対策について報告した．本報では，タイヤ音が車外に拡散するメカニズムを解明し，音が拡がる前にバンパー裏空間などに閉じ込める対策手法を考案した．そして，実車試験においてタイヤまわりの音の流れを改善し，車外騒音の低減に成功した．

全系共振に対するサスペンションとタイヤのモードエネルギー寄与度解析

橋岡　正人・駒田　匡史・水野　浩明（トヨタ自動車）・松村　雄一（岐阜大学）

ロードノイズに影響するタイヤとサスペンションが強く振動連成する全系共振に対して，分系の寄与を明確にする必要がある．本研究では，分系のモードエネルギー寄与度解析から重要な固有モードを抽出し，振動連成のメカニズムを理解したのち，全系のblocked forceを制御するための分系の変更指針を示す．

A Machine Learning Approach to Estimate Tire Block Force Spectrum for Road Noise Simulation

Yonghun Kim･Taeyoung Kim･HyunSeok Kang (Hankook Tire)

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.

Efficient Machine Learning Optimisation of Gear Micro Geometry and Comparison with Manually Designed Gears

Andrew Wild･Simon Terry･Paul Langlois (SMT)･Jaekwon Lee･Shinya Sudo (Hino Motors)

Optimisation of gear micro geometry guided by machine-learnt surrogate models is compared to a past engineer-led optimisation and proven to be a highly efficient technique. Subject to engineer-defined objectives, the optimiser identifies high-performing micro geometries with no further human intervention, with all predictions automatically validated by a hybrid Hertzian and FE-based loaded tooth contact analysis. Going beyond the scope of the original manual optimisation, the optimiser is used to identify micro geometries that are torque robust or retain similar performance to the specification without using different micro geometries on the two input gears, thereby theoretically reducing manufacturing costs.