SEMANTIC SEGMENTATION OF POROSITY IN 4D SPATIO-TEMPORAL X-RAY µCT OF TITANIUM COATED NI WIRES USING DEEP LEARNING

作     者：Elavarthi, Pradyumna Bhattacharjee, Arun Ralescu, Anca Paz y Puente, Ashley 

作者机构：Department of Electrical Engineering and Computer Science University of Cincinnati OH45221 United States Department of Mechanical and Materials Science University of Cincinnati OH45221 United States 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2023年

核心收录：

主　　题：Volume fraction 

摘      要：A fully convolutional neural network was used to measure the evolution of the volume fraction of two different Kirkendall pores during the homogenization of Ti-coated Ni wires. Traditional methods like Otsu’s thresholding and the Largest connected component analysis were used to obtain the masks for training the segmentation model. Once trained, the model was used to semantically segment the two types of pores at different stages in their evolution. Masks of the pores predicted by the network were then used to measure the volume fraction of porosity at 0mins, 240mins, and 480mins of homogenization. The model predicted an increase in porosity for one type of pore and a decrease in porosity for another type of pore due to pore sintering, and it achieved an F1 Score of 0.95. © 2023, CC BY-NC-SA.