Phased array ultrasonic and deep learning based internal defect detection in underwater concrete bridge structures

doi:10.1016/j.cscm.2025.e04946

Phased array ultrasonic and deep learning based internal defect detection in underwater concrete bridge structures

2025-06-17

0

OA

AI

DOI：10.1016/j.cscm.2025.e04946

Original

Original request for help

Save

Abstract

En 中文

• Developing an underwater PAUT device, integrating NLM to enhance imaging quality and ensure stable detection. • Creating an underwater concrete internal defect dataset with StyleGAN2-ADA to overcome data scarcity. • Proposing an enhanced SAM model for ultrasonic defect segmentation, using a Depth-wise Adapter and pyramid-based prompt encoder. • Real-world validation on underwater bridge piers, demonstrating the method’s reliability in detecting internal defects.

Keywords:

Underwater bridge piers

Phased Array Ultrasonic

Internal concrete defects

Deep learning

AI detection

Phased array ultrasonic and deep learning based internal defect detection in underwater concrete bridge structures

Abstract

Journal

Organization