Predicting the Reflection Coefficient of a Viscoelastic Coating Containing a Cylindrical Cavity Based on an Artificial Neural Network Model  

作　　者：Yiping Sun Qiang Bai Xuefeng Zhao Meng Tao 

机构地区：[1]School of Mechanical Engineering,Guizhou University,Guiyang,550025,China [2]Aviation Academy,Guizhou Open University,Guiyang,550003,China

出　　处：《Computer Modeling in Engineering & Sciences》2022年第2期1149-1170,共22页工程与科学中的计算机建模（英文）

基　　金：the National Natural Science Foundation of China(Nos.51765008 and 11304050);the High-Level Innovative Talents Project of Guizhou Province(No.20164033);the Science and Technology Project of Guizhou Province(No.2020-1Z048);the Open Project of the Key Laboratory of Modern Manufacturing Technology of the Ministry of Education(No.XDKFJJ[2016]10).

摘　　要：A cavity viscoelastic structure has a good sound absorption performance and is often used as a reflective baffle or sound absorption cover in underwater acoustic structures.The acoustic performance field has become a key research direction worldwide.Because of the time-consuming shortcomings of the traditional numerical analysis method and the high cost of the experimental method for measuring the reflection coefficient to evaluate the acoustic performance of coatings,this innovative study predicted the reflection coefficient of a viscoelastic coating containing a cylindrical cavity based on an artificial neural network(ANN).First,themapping relationship between the input characteristics and reflection coefficient was analysed.When the elastic modulus and loss factor value were smaller,the characteristics of the reflection coefficient curve were more complicated.These key parameters affected the acoustic performance of the viscoelastic coating.Second,a dataset of the acoustic performance of the viscoelastic coating containing a cylindrical cavity was generated based on the finite elementmethod(FEM),which avoided a large number of repeated experiments.The minmax normalization method was used to preprocess the input characteristics of the viscoelastic coating,and the reflection coefficient was used as the dataset label.The grid search method was used to fine-tune the ANNparameters,and the prediction error was studied based on a 10-fold cross-validation.Finally,the error distributions were analysed.The average root means square error(RMSE)and the mean absolute percentage error(MAPE)predicted by the improved ANN model were 0.298%and 1.711%,respectively,and the Pearson correlation coefficient(PCC)was 0.995,indicating that the improved ANN model accurately predicted the acoustic performance of the viscoelastic coating containing a cylindrical cavity.In practical engineering applications,by expanding the database of the material range,cavity size and backing of the coating,the reflection coefficient of more sound-absorb

关 键 词：COATING acoustic performance artificial neural network predicting 

分 类 号：TG1[金属学及工艺—金属学]