Convolutional neural network method for damage detection of CFRP in electrical impedance tomography

Abstract

Damage detection is vitally important for carbon fiber reinforced polymer (CFRP) laminates. When CFRP laminates are damaged, its impedance property is changed. Based on the electrical properties of CFRP laminates, the changed conductivity distribution can be reconstructed with the electrical impedance tomography (EIT) method. The detection method is attractive due to its simple equipment, low cost, and easy operation. However, image reconstruction of EIT faces a serious ill-conditioned nonlinear inverse problem. In order to solve this problem, a feature fusion convolutional neural network based on the dense connection (FF-D) method is applied in EIT to establish the mapping relationship between voltage measurement and conductivity distribution in this paper. The optimization can extract and utilize features to a greater degree and improve reconstruction accuracy and robustness. For the purpose of simulating the electrical properties of CFRP better, the conductivity values measured by an impedance analyzer are used as the data set. The correlation coefficient (CC) and root mean square error (RMSE) are used as indicators to evaluate the quality of image reconstruction. The simulation and experimental results suggest that the FF-D method can reconstruct images better than typical algorithms based on deep learning and conventional algorithms of EIT.