A new method for CF morphology distribution evaluation and CFRC property prediction using cascade deep learning

Abstract This work presents a deep-learning method to characterize the carbon fiber (CF) morphology distribution in carbon fiber reinforced cement-based composites (CFRC), predict the CFRC properties, and measure the contributions of different CF morphology distribution directly using X-ray images. Firstly, the components of CFRC in slices of X-ray images were segmented and identified using a fully convolutional network (FCN). Then the CF morphology distribution evaluation were conducted based on the results of the FCN. At last, the prediction of CFRC properties was realized using a cascade deep learning algorithm and CF morphology distribution results. The results showed that the FCN provided more reasonable segmentation results for each component in CFRC than traditional methods. CF clustered areas and CF bundles increased sharply with the increase of CF content, while uniformly dispersed CF areas showed the opposite trend. The cascade deep learning provided a method to predict the CFRC properties (e.g. resistivity and bending strength) using X-ray scanning images, which could also quantificationally measure the contributions of different CF morphology distribution to properties of the CFRC. Therefore, the proposed method could be regarded as a nondestructive and effective test for CFRC property evaluation.