학술논문
Detection of ballastless track interlayer gap based on vehicle’s multivariate dynamic response and deep learning
Document Type
Article
Author
Source
In Mechanical Systems and Signal Processing 15 January 2025 223
Subject
Language
ISSN
0888-3270
Abstract
Highlights •The interlayer impact effect and variation in the seam zones under the vehicle load are analyzed.•An IELMD algorithm is designed for adaptive noise reduction of vehicle dynamic signals.•Fusion vehicle’s multivariate dynamic data and deep learning locate initial seams accurately.•A deep learning model, DTA-Tcnformer, is constructed to locate and classify initial seams.•The research serves the rapid detection of initial defects in ballastless tracks of high-speed railways.