AUTHOR=Lu Lingling , Wang Yabo , Bi Jianquan , Liu Cheng , Song Hongwei , Huang Chenguang 

TITLE=Internal Damage Identification of Sandwich Panels With Truss Core Through Dynamic Properties and Deep Learning

JOURNAL=Frontiers in Materials

VOLUME=Volume 7 - 2020

YEAR=2020

URL=https://www.frontiersin.org/journals/materials/articles/10.3389/fmats.2020.00301

DOI=10.3389/fmats.2020.00301

ISSN=2296-8016

ABSTRACT=For sandwich panels with truss core, the weakest part is the low density truss core, some effective damage identification methods have been proposed for sandwich panels. However, those works mainly focused on damage location identification and few works discussed the damage extent detection. In the work, a damage identification method integrating deep learning technique with dynamic properties is proposed to identify both location and extent of internal damages in sandwich panels with truss core. An analytical model verified by experiments based on laser vibrometer is used to get raw data, which can generate various damages inside the two face sheets. Instead of using captured surface photos or raw data as the DL training dataset, the dataset is constructed using damage indexes instead of raw data. By combing with the analytical model, dataset of specimens with various defeats was collected and used as the input of the neural networks. Abilities of identifying damage location and damage extent were used to evaluate the effectiveness of the proposed technique. According to the results, it shows that the proposed method could identify the location and extent of internal damages accurately.