The electromechanical impedance (EMI) technique is one of common used methods for damage diagnosis. However, the mechanism of EMI-based damage diagnosing is usually complicated and difficult to be comprehensively described. To solve this problem to a certain extent, a novel EMI model for describing the interaction between piezoelectric transducer (PZT) and host structure is developed in this paper. The developed EMI model has advantages of simplicity in formula and excellent precision in signatures prediction. An efficaciously equivalent SMD (Spring-Mass-Damping) system is adopted to obtain the local structural mechanical impedance (LSMI) and to calculate the equivalent parameters ( k s , m s , c s ) in the vicinity of PZT. To verify the effectiveness of the novel model, a series of experiments are separately conducted on the specimen under healthy condition and damage condition. Through comparing the predicted curves with the experimental ones, the effectiveness of the developed model is demonstrated when used for predicting signatures, especially for resistance signatures. The developed EMI model has shown the potential application in the field of structural health monitoring and damage diagnosis.

Sandwich composites are prone to delamination and fracture during service when exposed to external low-velocity impact. One hindrance to overcome before a broader deployment of sandwich composites is the issue of impact energy assessment (IEA). To promote the solution to this issue, an ensemble deep learning approach is proposed in this study. The approach comprises data expansion, series-to-image conversion, and convolutional neural networks (CNN). The data expansion is implemented using vertical average interpolation. The enhanced data are transformed into images via the Gramian angular summation field to build an image dataset for the CNN model. To validate the developed ensemble approach, hammer-dropping impact experiments on the honeycomb sandwich composites are carried out based on the piezoelectric wafer active sensor network and electromechanical impedance measurement. Accuracy, precision, recall, and F1-score indicators are introduced to evaluate the ensemble approach performance. The above indicator values are all above 0.9600, demonstrating the effectiveness of the proposed ensemble approach in settling the IEA issue.