Guided-Wave-Based Real-Time Damage Detection in Composite Structures: A Gramian Angular Field Image Coding Lightweight Network Approach

Abstract

Ultrasonic guided wave (UGW)-based damage detection is regarded as a leading technology in structural health monitoring (SHM) for assessing the integrity of composite structures. However, achieving accurate and effective real-time damage detection remains a challenge. To address this issue, a novel UGW-based damage detection approach is proposed for real-time damage localization and quantification in composite plates. In the proposed approach, first, considering the expensive calculation of multipath UGW signals, an efficient UWG signal compression method is constructed on the basis of differential-driven piecewise aggregate approximation (DPAA) algorithm to further improve the calculation efficiency. Next, the Gramian angular field (GAF) image encoding feature extraction method is innovatively used to transform the concatenated 1-D guided wave signal into a 2-D image, which preserves the original time information and captures the temporal correlation between different timestamps in the guided wave signal. Then, by incorporating the specially designed partial group convolution (PGC) block and dynamic multiscale residual channel attention (DMRCA) mechanism, the proposed lightweight PGC-DMRCA network is capable of detecting damage in real-time with high accuracy and low computational complexity. Notably, the performance of the proposed lightweight network is verified using two real-world datasets and a publicly available dataset. Experimental results demonstrate that the proposed lightweight approach delivers exceptional performance in locating and quantifying damage, surpassing mainstream end-to-end damage detection methodologies in both accuracy and efficiency.