超音速飞机压强场的机器学习预测方法研究  

Machine Learning Prediction of Supersonic Aircraft Pressure Fields

作　　者：张玉龙 张润森 袁永伟[1] 舒凤金 张世芳[1] ZHANG Yulong;ZHANG Runsen;YUAN Yongwei;SHU Fengjin;ZHANG Shifang(College of Mechatronical&Electrical Engineering,Hebei Agricultural University,Baoding 071000;Baoding Kaiborui Machinery Manufacturing Co.,Ltd.,Baoding 071000)

机构地区：[1]河北农业大学机电工程学院,保定071000 [2]保定凯博瑞机械制造有限公司,保定071000

出　　处：《现代制造技术与装备》2023年第7期54-56,共3页Modern Manufacturing Technology and Equipment

基　　金：河北省军民两用关键技术和产品研发专项“音爆测控试验装置研发”(SJMYF2022X07)。

摘　　要：超音速飞行过程中由于近场空气压强过大而产生音爆现象,会对周围环境产生重要影响。如何预测飞机近场和远场的压强值,对超音速飞机设计和评估极其关键。首先通过Fluent计算飞机在不同马赫数下近场的压强,其次通过机器学习线性回归算法拟合远场的压强场,最后通过模拟数据验证模型的准确性。结果显示,模型预测精度相对误差在5%以内,研究结果可以为超音速飞行器音爆测量与预测提供理论基础。The sonic boom phenomenon occurs during the flight of supersonic aircraft due to excessive air pressure in the near field,which has an important impact on the surrounding environment.How to predict the pressure values in the near-field and far-field of an aircraft is extremely critical for supersonic aircraft design and evaluation.In this paper,first we calculate the pressure in the near field of the aircraft at different Mach numbers by Fluent,then we fit the pressure field model in the far field by machine learning linear regression algorithm,and finally the accuracy of the model is verified by simulation data,and the relative error of the model prediction accuracy is within 5%.The results of this paper can provide a theoretical basis for sonic boom measurement and prediction of supersonic vehicles.

关 键 词：超音速飞机 音爆 压强场 

分 类 号：V221[航空宇航科学与技术—飞行器设计]