{"title":"A hybrid approach for reconstruction of transonic buffet aerodynamic noise: Integrating random forest and compressive sensing algorithm","authors":"","doi":"10.1016/j.ast.2024.109379","DOIUrl":null,"url":null,"abstract":"<div><p>Experimental measurements and numerical simulation methods for obtaining aerodynamic noise face issues such as high costs and long periods. A single machine learning method for predicting aerodynamic noise also requires a sufficient amount of data. According to this, this paper proposes a hybrid method integrating Random Forest and Compressive Sensing (RF_CS) to accurately reconstruct transonic buffet aerodynamic noise from sparse data. First, the RF algorithm, known for its strong nonlinear feature extraction capabilities, is used to obtain the basis function. Then, the basis coefficients are calculated using the L1 optimization algorithm based on limited sensor data and basis functions. Finally, a linear combination of basis functions and basis coefficients is used to reconstruct aerodynamic noise, including power spectral density, sound pressure level, and flow modes. Compared to the Compressive Sensing based on Proper Orthogonal Decomposition (POD_CS), the proposed algorithm can effectively reduce error by approximately 2–20 times and decrease the absolute error of modes by about 2–3 orders of magnitude. Specifically, the RF_CS method ensures that the reconstruction errors for power spectral density across various flow conditions are all below 3E-3, achieving generalization from one flow condition to the entire sample space. Additionally, this approach can utilize approximately 10 sensors to reconstruct accurate sound pressure level and modes, with errors within 5E-3 and 5E-5, respectively. This allows for generalization across the entire Mach number space based on a single Mach number condition.</p></div>","PeriodicalId":50955,"journal":{"name":"Aerospace Science and Technology","volume":null,"pages":null},"PeriodicalIF":5.0000,"publicationDate":"2024-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Aerospace Science and Technology","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1270963824005108","RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, AEROSPACE","Score":null,"Total":0}
引用次数: 0
Abstract
Experimental measurements and numerical simulation methods for obtaining aerodynamic noise face issues such as high costs and long periods. A single machine learning method for predicting aerodynamic noise also requires a sufficient amount of data. According to this, this paper proposes a hybrid method integrating Random Forest and Compressive Sensing (RF_CS) to accurately reconstruct transonic buffet aerodynamic noise from sparse data. First, the RF algorithm, known for its strong nonlinear feature extraction capabilities, is used to obtain the basis function. Then, the basis coefficients are calculated using the L1 optimization algorithm based on limited sensor data and basis functions. Finally, a linear combination of basis functions and basis coefficients is used to reconstruct aerodynamic noise, including power spectral density, sound pressure level, and flow modes. Compared to the Compressive Sensing based on Proper Orthogonal Decomposition (POD_CS), the proposed algorithm can effectively reduce error by approximately 2–20 times and decrease the absolute error of modes by about 2–3 orders of magnitude. Specifically, the RF_CS method ensures that the reconstruction errors for power spectral density across various flow conditions are all below 3E-3, achieving generalization from one flow condition to the entire sample space. Additionally, this approach can utilize approximately 10 sensors to reconstruct accurate sound pressure level and modes, with errors within 5E-3 and 5E-5, respectively. This allows for generalization across the entire Mach number space based on a single Mach number condition.
期刊介绍:
Aerospace Science and Technology publishes articles of outstanding scientific quality. Each article is reviewed by two referees. The journal welcomes papers from a wide range of countries. This journal publishes original papers, review articles and short communications related to all fields of aerospace research, fundamental and applied, potential applications of which are clearly related to:
• The design and the manufacture of aircraft, helicopters, missiles, launchers and satellites
• The control of their environment
• The study of various systems they are involved in, as supports or as targets.
Authors are invited to submit papers on new advances in the following topics to aerospace applications:
• Fluid dynamics
• Energetics and propulsion
• Materials and structures
• Flight mechanics
• Navigation, guidance and control
• Acoustics
• Optics
• Electromagnetism and radar
• Signal and image processing
• Information processing
• Data fusion
• Decision aid
• Human behaviour
• Robotics and intelligent systems
• Complex system engineering.
Etc.