Recognition of abnormal car door noise based on multi-scale feature fusion
To accurately identify the abnormal door-closing noise, the authors propose a method to recognize the time-frequency image of door closing sound based on a multi-scale feature fusion network model. The door-closing sound signal is transformed into a time-frequency image through wavelet analysis, and a classification model based on multi-scale feature fusion is designed. The model introduces multi-scale filters and dilated convolution and adds two improved inception modules to keep the model lightweight. At the same time, richer spatial features can be obtained. The features of different scales are spliced and input to the fully connected layer, and a dropout layer is added to the fully connected layer to suppress overfitting. By comparing the loss and accuracy rate, adjusting different hyperparameters, the optimal model is obtained. The experimental results show that the multi-scale feature fusion network model has a higher accuracy rate than the transfer learning model. Test accuracy rate is 86% and can effectively recognize abnormal door-closing noise. It provides a feasible theoretical basis for the direction of abnormal door noise recognition.
- Record URL:
-
Availability:
- Find a library where document is available. Order URL: http://worldcat.org/issn/09544070
-
Supplemental Notes:
- © IMechE 2022.
-
Authors:
- Wang, Xiaolan
-
0000-0003-3846-1753
- Song, Yongchao
- Su, Lili
- Wang, Yansong
- Pan, Zuofeng
- Publication Date: 2023-5
Language
- English
Media Info
- Media Type: Web
- Features: References;
- Pagination: pp 1353-1364
-
Serial:
- Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering
- Volume: 237
- Issue Number: 6
- Publisher: Sage Publications Limited
- ISSN: 0954-4070
- EISSN: 2041-2991
- Serial URL: http://pid.sagepub.com/content/current
Subject/Index Terms
- TRT Terms: Classification; Doors (Vehicles); Networks; Noise sources; Wavelets
- Subject Areas: Highways; Vehicles and Equipment;
Filing Info
- Accession Number: 01882948
- Record Type: Publication
- Files: TRIS
- Created Date: May 23 2023 10:09AM