Estimating the phase volume fraction of multi-phase steel via unsupervised deep learning

Sung Wook Kim,Seong-Hoon Kang,Seungchul Lee,Se-Jong Kim

doi:10.1038/s41598-021-85407-y

Abstract

Advanced high strength steel (AHSS) is a steel of multi-phase microstructure that is processed under several conditions to meet the current high-performance requirements from the industry. Deep neural network (DNN) has emerged as a promising tool in materials science for the task of estimating the phase volume fraction of these steels. Despite its advantages, one of its major drawbacks is its requirement of a sufficient amount of training data with correct labels to the network. This often comes as a challenge in many areas where obtaining data and labeling it is extremely labor-intensive. To overcome this challenge, an unsupervised way of learning DNN, which does not require any manual labeling, is proposed. Information maximizing generative adversarial network (InfoGAN) is used to learn the underlying probability distribution of each phase and generate realistic sample points with class labels. Then, the generated data is used for training an MLP classifier, which in turn predicts the labels for the original dataset. The result shows a mean relative error of 4.53% at most, while it can be as low as 0.73%, which implies the estimated phase fraction closely matches the true phase fraction. This presents the high feasibility of using the proposed methodology for fast and precise estimation of phase volume fraction in both industry and academia.

Highlights

Advanced high strength steel (AHSS) is a steel of multi-phase microstructure that is processed under several conditions to meet the current high-performance requirements from the industry
The basic form of phase identification as well as the estimation of phase volume fraction consists of manually counting the appearances of each micro-constituent through optical microscopy (OM) or scanning electron microscopy (SEM)
To the best of our knowledge, it is the first time to solve the problem via unsupervised deep learning, no longer requiring the tedious job of labeling data

Summary

Introduction

Advanced high strength steel (AHSS) is a steel of multi-phase microstructure that is processed under several conditions to meet the current high-performance requirements from the industry. The so-called point counting methodology is often used as a reference in the literature[1,2,3,4] for verifying if a proposed quantification method is appropriate Even though it generally assures high accuracy of the actual phase volume fraction, it is often limited in its usage for the enormous amount of time and a large number of images necessary to obtain a 95% r eliability[4,5]. EBSD offers several features, including image quality that allows us to show detailed features of the microstructures such as the boundaries It allows phase identification by phase contrast presented from different diffraction intensities of each phase. Tomaz et al.[2] presented an almost identical phase fraction estimation on a low manganese HTP steel utilizing EBSD with a maximum fraction difference of 5%, but the author acknowledges criteria for separation would vary for different types of steels and processing parameters

Methods

Results

Conclusion