Development of aerodynamic noise reduction technology with correlation between unsteady vortex source and aerodynamic noise based on machine learning

2021 Fiscal Year Final Research Report

• Project/Area Number: 19K04168
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Review Section: Basic Section 19010:Fluid engineering-related
• Research Institution: Toyohashi University of Technology
• Principal Investigator: IIDA Akiyoshi 豊橋技術科学大学, 工学(系)研究科(研究院), 教授 (30338272)
• Project Period (FY): 2019-04-01 – 2022-03-31
• Keywords: 空力音 / 機械学習 / 渦 / 非定常流れ

Outline of Final Research Achievements

In order to investigate how machine learning can be used to predict aerodynamic noise, the relationship between aerodynamic noise and airfoil shape was investigated using the results of analysis of the flow field around the airfoil as training data. It was confirmed that aerodynamic noise could be predicted by taking into account the influence of temporal changes in the flow field image data.
The result were applied to fan noise analysis to calculate the airfoil shape with the lowest aerodynamic noise and fluid power and the highest fluid force (lift-drag ratio), and to estimate the fan with the optimized performance from the obtained shape data. As a result, the aerodynamic noise of the fan shape optimized by machine learning was lower than that of the conventional type, confirming that machine learning can be applied to predict aerodynamic noise and optimize fan performance.

Free Research Field

流体力学

Academic Significance and Societal Importance of the Research Achievements

空力騒音の予測は，計算負荷が大きいこと，高精度の解析を行うことが難しく，特に工業製品の開発において難しい計算技術の一つである．本研究では機械学習を用いることにより空力音の予測をこれまでの計算負荷と比べて小さくしたことに意義がある．得られた結果をファン解析に適用した結果，従来ファンに比べて，低騒音，高揚抗比，低動力のファンを提案することができた．機械学習が空力音の予測，工業製品の開発に適用可能であることを占めることができる．