Self‐supervised representation learning of metro interior noise based on variational autoencoder and deep embedding clustering

The noise within train is a paradox; while harmful to passenger health, it is useful to operators as it provides insights into the working status of vehicles and tracks. Recently, methods for identifying defects based on interior noise signals are emerging, among which representation learning is the...

Full description

Saved in:
Bibliographic Details
Published in:Computer-aided civil and infrastructure engineering Vol. 40; no. 4; pp. 503 - 522
Main Authors: Wang, Yang, Xiao, Hong, Zhang, Zhihai, Guo, Xiaoxuan, Liu, Qiang
Format: Journal Article
Language:English
Published: Hoboken Wiley Subscription Services, Inc 01.02.2025
Subjects:
Artificial neural networks
Clustering
Data augmentation
Embedding
Fault detection
Machine learning
Modules
Neural networks
Noise reduction
Representations
Wavelet transforms
ISSN:1093-9687, 1467-8667
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The noise within train is a paradox; while harmful to passenger health, it is useful to operators as it provides insights into the working status of vehicles and tracks. Recently, methods for identifying defects based on interior noise signals are emerging, among which representation learning is the foundation for deep neural network models to understand the key information and structure of the data. To provide foundational data for track fault detection, a representation learning framework for interior noise, named the interior noise representation framework, is introduced. The method includes: (i) using wavelet transform to represent the original noise signal and designing a soft and hard denoising module for dataset denoising; (ii) deep residual convolutional denoising variational autoencoder (VAE) module performs representation learning with a VAE and deep residual convolutional neural networks, enabling richer data augmentation for sparsely labeled samples by manipulating the embedding space; (iii) deep embedding clustering submodule balances the representation of reconstruction and clustering features through the joint optimization of these aspects, categorizing metro noise into three distinct classes and effectively discriminating significantly different features. The experimental results show that, compared to traditional mechanism‐based models for characterizing interior noise, this approach offers a data‐driven general analysis framework, providing a foundational model for downstream tasks.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1093-9687
1467-8667
DOI:10.1111/mice.13336