Multi-Feature Fusion Framework for Ultrasonic A-Scan Denoising in Heavy-Haul Railways (IMAGE)

Tsinghua University Press

Multi-Feature Fusion Framework for Ultrasonic A-Scan Denoising in Heavy-Haul Railways

Caption

Schematic illustration of a physics-guided multi-feature fusion framework for ultrasonic A-scan signals in heavy-haul railway inspection. The method integrates Variational Mode Decomposition (VMD), Continuous Wavelet Transform (CWT), and time-domain statistical analysis to extract features from modal, time–frequency, and waveform domains. These features are combined within an ideal binary mask (IBM) paradigm to mitigate coupled non-Gaussian noise and improve defect echo identification.

Credit

Communications in Transportation Research

Usage Restrictions

News organizations may use or redistribute this image, with proper attribution, as part of news coverage of this paper only.

License

Original content

Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.