Ring Array Scatter Feature Adaption Deep Transfer Imaging Method for Composite Plate Structure Health Monitoring Using Guided Waves

Whole structure fast detection system suitable for multiple classes of materials is an engineering goal in the structural health monitoring community. However, mode selection caused by the difference in damage modes among different structures seriously affects the intelligence and automation of guided wave detection. In this article, a scatter feature adaption intelligent detection method based on ultrasonic guided wave is proposed to monitor different structures according to deep feature generalization. First, the deep convolutional neural network is constructed, and the multilayer feature mapping relationship is constructed for both source domain and target domain signals. Second, the maximum mean difference (MMD) method was utilized to construct a quantitative difference evaluation mechanism for the guided wave scatter signals with different structures. At the same time, both the feature distance loss and the source-domain label loss are used to optimize the deep network model. Finally, the visual damage localization is realized by improved possibility imaging methods according to the multisensor damage index. Experimental results show that the proposed method can realize the damage monitoring in another target domain by adapting the scatter signals in a single source domain and a single target domain, and has great advantages compared with the existing methods in such problems.