Priori knowledge-based multi-task wavelet network for guided wave interfacial debonding detection in RC structures

Reinforced concrete (RC) has been widely used in infrastructure construction. Interfacial debonding between concrete and reinforcing bars, which is one of the most serious causes of structural failure, has always been a focus of research. In this paper, a novel deep learning-based guided wave analysis framework, termed the Priori Knowledge-based Multi-task Wavelet Network, is proposed for detecting interfacial debonding in RC structures. An end-to-end structure is utilized to surmount the challenges of manual feature uncertainty and dependence on expert knowledge inherent in traditional methods. Incorporating the multi-task learning principles, a deep learning network with branching structures is designed to simultaneously recognize, localize, and quantify the size of interfacial debonding. Damage-sensitive and task-invariant features of guided wave signals are extracted automatically based on supervised learning. To improve the noise resilience the proposed framework incorporates the environmental adaptive training based on data augmentation and continuous wavelet transform. Both the numerical and real structures of RC beams containing with various interfacial debonding scenarios are established to evaluate the debonding detection performance of the framework. Evaluation results demonstrate that the framework exhibits superior interfacial debonding detection capability and enhanced generalizability to varying levels of external interference compared to baseline methods.