Deep learning based semantic segmentation of μCT images for creating digital material twins of fibrous reinforcements

In this study, a novel approach of processing mu CT images to create digital material twins is presented. A deep convolutional neural network (DCNN) was implemented and used to segment mu CT images of two different types of reinforcement (2D glass and 3D carbon). The DCNN successfully segmented the images based on multi-scale features extracted using data-driven convolutional filters. The network was trained using scanned mu CT images, along with images extracted from computer-generated virtual models of the reinforcements. One of the convolutional layers of the trained network was utilized to extract features to be used in creating a machine learning-based model. The extracted features and the raw gray-scale data were used to train a supervised k-nearest neighbor (k-NN) model for pixel-wise classification. The performance of both approaches was evaluated by comparing the results with manually segmented images. The trained deep neural network was able to provide faster and superior predictions of different features of the reinforcements as compared to the conventional machine learning approach.