Rebar Clutter Suppression and Fusion Imaging for Enhanced Detection of Void Defects in Ballastless Tracks Using Ground Penetrating Radar

Void defects significantly undermine the safety and operational performance of ballastless tracks in high-speed railways [1]. Ground Penetrating Radar (GPR), serving as a non-destructive testing tool, is widely used for detecting internal defects in ballastless tracks, owing to its fast detection speed and high resolution. However, the complex rebar distribution in track slabs causes severe interference in GPR data during detection, reducing the detectability of void signals, while the sensitivity of GPR data to void defects detection varies across different polarization modes, further complicating accurate identification [2].

To address these challenges, this paper proposes a void defects detection method by rebar clutter suppression and polarization fusion imaging. First, a deep learning model is developed to suppress rebar clutter in GPR data, improving void signal visibility. Then, Reverse Time Migration (RTM) is applied to fuse data from HH and VV polarization modes, further enhancing imaging resolution and accuracy [3].

The proposed method is validated through forward modeling and field experiments. Results demonstrate its effectiveness in suppressing rebar clutter and improving void detection and imaging. This paper provides an approach for structural health monitoring of ballastless tracks, offers insights into advancing GPR applications in complex rebar environments, and introduces a new perspective for using GPR in the detection of ballastless tracks.

References:

[1] Yang, Y., & Zhao, W. (2019). Curvelet transform‐based identification of void diseases in ballastless track by ground‐penetrating radar. Structural Control and Health Monitoring, 26(4), e2322.

[2] Wang, X., Liu, H., Meng, X., Cui, J., & Du, Y. (2024). Enhanced imaging of concealed defects behind concrete linings using Residual Channel attention network for rebar clutter suppression. Automation in Construction, 166, 105574.

[3] Liu, H., Yue, Y., Lian, Y., Meng, X., Du, Y., & Cui, J. (2024). Reverse-time migration of GPR data for imaging cavities behind a reinforced shield tunnel. Tunnelling and Underground Space Technology, 146, 105649.