基于机器学习模型的飞机噪声预测  

Aircraft Noise Prediction Based on Machine Learning Model

作　　者：丰豪 周亚东 丁聪 曾维理[1] 郭文韬 FENG Hao;ZHOU Yadong;DING Cong;ZENG Weili;GUO Wentao(College of Civil Aviation,Nanjing University of Aeronautics and Astronautics,Nanjing 211106,P.R.China)

机构地区：[1]南京航空航天大学民航学院,中国南京211106

出　　处：《Transactions of Nanjing University of Aeronautics and Astronautics》2023年第S02期54-61,共8页南京航空航天大学学报（英文版）

基　　金：supported by the National Natural Science Foundation of China(No.52202442);National Key R&D Program of China(No.2022YFB260-2403)。

摘　　要：为了探索最佳实践模型和科学模型之外的飞机噪声预测方法,采用多元线性回归模型和随机森林回归模型对西雅图-塔科马国际机场2020—2022年夏季的飞机噪声值进行了预测。实验验证了机器学习模型在飞机噪声预测任务中的可行性和优势,结果表明随机森林回归模型预测结果的R^(2)均值为74.469%,比多元线性回归模型预测结果的R2均值高出5.361%;随机森林回归模型预测结果的RMSE均值为0.814,比多元线性回归模型预测结果的RMSE均值低0.106。In order to explore the aircraft noise prediction methods beyond the best practice model and scientific model,this paper uses multiple linear regression model and random forest regression model to predict the aircraft noise value of Seattle-Tacoma International Airport in the summer of 2020—2022.The experiment confirm the feasibility and advantages of the machine learning model in aircraft noise prediction tasks and find that the mean R^(2) predicted by the random forest regression model is 74.469%,5.361%higher than that of the multiple linear regression model.The mean RMSE predicted by the random forest regression model is 0.814,0.106 lower than that of the multiple linear regression model.

关 键 词：飞机噪声排放 飞机噪声预测 多元线性回归 随机森林回归 

分 类 号：U8[交通运输工程]