加筋板材料辨识的导纳特征表达与冲击声特征提取

Translated title of the contribution: The admittance feature representation and impact sound feature extraction for the material identification of ribbed plates

Xuhua Tian, Ke'an Chen, Han Li, Lixue Yang

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

The admittance features representing the physical attributes are used as the intermediates to extract the material-attributes-related impact sound features of ribbed plates. Firstly, the admittance feature representations of metal ribbed plates are obtained and the relationships between the admittance features and the impact sound features are built via correlation analysis method, and material-attributes-related impact sound features are obtained indirectly. Then the performances of different sound features for the material recognition of ribbed-metal plates are verified through the Support Vector Machine classifier. The results indicate that, the obtained four sets of features mentioned above have a good accuracy about the materials of the metal ribbed plates, the accuracy of each set of features is related to the separable degree of the corresponding material attribute, and features extracted based on admittance functions have a higher average accuracy than timbre features. As a result, the method that extracting material-attributes-related sound features based on admittance features is efficient, and from which the sound features extracted have a better reflection on the physical attributes.

Translated title of the contributionThe admittance feature representation and impact sound feature extraction for the material identification of ribbed plates
Original languageChinese (Traditional)
Pages (from-to)699-707
Number of pages9
JournalShengxue Xuebao/Acta Acustica
Volume43
Issue number4
StatePublished - 1 Jul 2018

Fingerprint

Dive into the research topics of 'The admittance feature representation and impact sound feature extraction for the material identification of ribbed plates'. Together they form a unique fingerprint.

Cite this