Deep learning-based acoustic emission data clustering for crack evaluation of welded joints in field bridges

Abstract

To advance the intelligent operation and maintenance of bridges, a deep learning-based acoustic emission (AE) data clustering framework was developed for evaluating fatigue cracks in welded joints under conditions of operational noise interference and complex damage mechanisms. Specifically, a convolutional autoencoder (CAE) model was implemented to extract damage-sensitive features from AE wavelet images. Additionally, a physics-guided single-and-cross-case strategy using Gaussian mixture models (GMMs) was presented to diagnose overlapping microscopic noise and damage mechanisms across different cases with various crack lengths. Field tests demonstrated the efficiency of the proposed framework to distinguish AE data induced by noise, crack propagation, surface fretting, and impact, enabling accurate identification of no-damage, minor-damage, and serious-damage cases according to their characteristic mechanisms. Future work will incorporate long-term monitoring data from additional cases to further refine the damage quantification and enhance the overall robustness.