Semantic Segmentation of Porosity in 4D Spatio-Temporal X-ray \mu CT of Titanium Coated Ni wires using Deep Learning

TL;DR

This paper presents a deep learning approach using a fully convolutional neural network to segment and analyze the evolution of porosity in 4D X-ray T data of titanium-coated nickel wires during homogenization, enabling precise measurement of pore volume changes.

Contribution

It introduces a novel application of deep learning for semantic segmentation of porosity in 4D T data, improving accuracy in pore analysis during material processing.

Findings

Model achieved an F1 Score of 0.95.

Detected increase in porosity for one pore type.

Detected decrease in porosity for another pore type.

Abstract

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 Otsus 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 0 mins, 240 mins, and 480 mins 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.