航空学报 > 2025, Vol. 46 Issue (20): 531936-531936   doi: 10.7527/S1000-6893.2025.31936

基于多保真深度神经网络的超声速客机声爆预测

王雨桐1,2, 罗骁1,2, 刘红阳1,2, 宋超1,2, 赵莹1,3, 周铸1,2()   

  1. 1.中国空气动力研究与发展中心 计算空气动力研究所,绵阳 621000
    2.空天飞行空气动力科学与技术全国重点实验室,绵阳 621000
    3.西北工业大学 航空学院,西安 710072
  • 收稿日期:2025-03-05 修回日期:2025-03-18 接受日期:2025-04-27 出版日期:2025-05-14 发布日期:2025-05-13
  • 通讯作者: 周铸 E-mail:f-yforever@126.com

Sonic boom prediction of supersonic passenger aircraft based on multi-fidelity deep neural network

Yutong WANG1,2, Xiao LUO1,2, Hongyang LIU1,2, Chao SONG1,2, Ying ZHAO1,3, Zhu ZHOU1,2()   

  1. 1.Institute of Computational Aerodynamics,China Aerodynamics Research and Development Center,Mianyang 621000,China
    2.State Key Laboratory of Aerodynamics,Mianyang 621000,China
    3.School of Aeronautics,Northwestern Polytechnical University,Xi’an 710072,China
  • Received:2025-03-05 Revised:2025-03-18 Accepted:2025-04-27 Online:2025-05-14 Published:2025-05-13
  • Contact: Zhu ZHOU E-mail:f-yforever@126.com

摘要:

声爆作为制约超声速客机发展的核心问题,对其进行精确预测是开展超声速客机降噪设计的先决条件。在工程中主要采用计算流体力学(CFD)和声学传播理论相结合的声爆预测方法,其中近场超压分布的计算精度至关重要,但高精度解的获取成本高昂。为缓解声爆预测成本与精度之间的矛盾,采用多保真深度神经网络构建气动外形和近场超压分布之间的映射关系,并结合声学法实现快速准确的声爆预测。在剖析高低保真近场超压分布数据之间关联特性的基础上,本研究探讨了2种不同的多保真建模策略下深度神经网络的构建方法与预测性能。实验结果显示:通过增加自适应搜索方法,基于线性/非线性综合矫正策略的MF-DNN的兼顾鲁棒性与性能优势,而通过精细设计归一化方法和正则化系数,基于迁移学习的TF-DNN实现了最小的预测误差,相比于单保真深度神经网络,2个模型都可以在高保真数据较少的条件下,通过联合低保真度数据来显著提升近场超压分布和声爆值的预测精度,相关研究结果为超声速客机高效率低声爆设计提供支撑。

关键词: 超声速客机, 声爆, 多保真, 迁移学习, 深度神经网络

Abstract:

Sonic boom is a core issue restricting the development of supersonic passenger aircraft. Accurate prediction of sonic boom signatures is a prerequisite for the noise reduction design of supersonic passenger aircraft. In engineering, the sonic boom prediction method mainly combines Computational Fluid Dynamics (CFD) and acoustic propagation theory, in which the calculation accuracy of the near-field overpressure distribution is crucial, but the acquisition cost of high-precision solutions is high. To alleviate the contradiction between the cost and accuracy of sonic boom prediction, this paper uses a multi-fidelity deep neural network to construct the mapping relationship between the aerodynamic shape and the near-field overpressure distribution, and combines the acoustic propagation theory to achieve fast and accurate sonic boom prediction. Based on the analysis of the correlation characteristics between the high and low fidelity near-field overpressure data, this study explores the construction methods and prediction performance of deep neural networks under two different multi-fidelity modeling strategies. The experimental results show that by adding an adaptive search method, the MF-DNN based on the linear/nonlinear comprehensive correction strategy has both robustness and performance advantages, and by carefully designing the normalization method and regularization coefficient,the TF-DNN based on transfer learning achieves the smallest prediction error. Compared with the single-fidelity deep neural network, both models can significantly improve the prediction accuracy of the near-field overpressure distribution and sonic boom value by combining low-fidelity data under the condition of less high-fidelity data. Relevant research results provide support for the high-efficiency and low-sonic-boom design of supersonic passenger aircraft.

Key words: supersonic passenger aircraft, sonic boom, multi-fidelity, transfer learning, deep neural network

中图分类号: