Scholarlink

Sound Absorption Coefficient (SAC) evaluation at various frequencies in 1/3rd octave band is very important for passive noise control. Reverberation Chamber and Sound Impedance Tube facility is widely used for measurement of SAC of acoustical materials. However, both these methods are time-consuming and need rigorous experimentation in order to evaluate and analyze the SAC of acoustical materials. The analytical models thus prove to be very helpful in simulation and devising newer acoustical materials of enhanced SAC. The analytical models also sometimes suffer from disadvantages of high prediction errors. The present chapter thus explores the use of Artificial Neural Network (ANN) in order to predict the SAC of acoustical materials based on the input values of some nonacoustical parameters. The prediction model so developed and tested for its performance using some statistical tests. The study concludes that ANN can be used as a reliable tool for SAC prediction of acoustical materials.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Prediction of Sound Absorption Coefficient of Acoustical Materials Using Artificial Neural Network Model

  • 工具书词条

  • 发表日期：

    2025年

查看全文
  • Chitra Gautam,
  • Naveen Garg,
  • A. Devi,
  • Gaurav Purohiit

摘要

Sound Absorption Coefficient (SAC) evaluation at various frequencies in 1/3rd octave band is very important for passive noise control. Reverberation Chamber and Sound Impedance Tube facility is widely used for measurement of SAC of acoustical materials. However, both these methods are time-consuming and need rigorous experimentation in order to evaluate and analyze the SAC of acoustical materials. The analytical models thus prove to be very helpful in simulation and devising newer acoustical materials of enhanced SAC. The analytical models also sometimes suffer from disadvantages of high prediction errors. The present chapter thus explores the use of Artificial Neural Network (ANN) in order to predict the SAC of acoustical materials based on the input values of some nonacoustical parameters. The prediction model so developed and tested for its performance using some statistical tests. The study concludes that ANN can be used as a reliable tool for SAC prediction of acoustical materials.