Texture-Based Metallurgical Phase Identification in Structural Steels: A Supervised Machine Learning Approach

Dayakar L Naik,Hizb Ullah Sajid,Ravi Kiran

doi:10.3390/met9050546

Dayakar L Naik, Hizb Ullah Sajid + Show 1 more

Open Access

https://doi.org/10.3390/met9050546

Copy DOI

Journal: Metals	Publication Date: May 10, 2019
Citations: 25	License type: CC BY 4.0

Affiliation: Dakota State University, North Dakota State University

Abstract

Automatic identification of metallurgical phases based on thresholding methods in microstructural images may not be possible when the pixel intensities associated with the metallurgical phases overlap and, hence, are indistinguishable. To circumvent this problem, additional visual information about the metallurgical phases, referred to as textural features, are considered in this study. Mathematically, textural features are the second order statistics of an image domain and can be distinct for each metallurgical phase. Textural features are evaluated from the gray level co-occurrence matrix (GLCM) of each metallurgical phase (ferrite, pearlite, and martensite) present in heat-treated ASTM A36 steels in this study. The dataset of textural features and pixel intensities generated for the metallurgical phases is used to train supervised machine learning classifiers, which are subsequently employed to predict the metallurgical phases in the microstructure. Naïve Bayes (NB), k-nearest neighbor (K-NN), linear discriminant analysis (LDA), and decision tree (DT) classifiers are the four classifiers employed in this study. The performances of all four classifiers were assessed prior to their deployment, and the classification accuracy was found to be >97%. The proposed technique has two unique advantages: (1) unlike pixel intensity-based methods, the proposed method does not misclassify the grain boundaries as a metallurgical phase, and (2) the proposed method does not require the end-user to input the number of phases present in the microstructure.

Highlights

It is well known that the macroscopic mechanical properties of any material are governed by its underlying microstructure [1]
It was interesting to note that ‘pixel intensity’ and ‘maximum probability’ remained the top relevant features for all five window sizes considered in this study
The robustness of the method proposed in this study relied on adding textural features that may not be perceivable by an ordinary human eye but could be measured mathematically and used by a machine learning algorithm to classify/identify unknown metallurgical phases

Summary

Introduction

It is well known that the macroscopic mechanical properties of any material are governed by its underlying microstructure [1]. Under different mechanical and thermal manufacturing and operating conditions, these microstructural features undergo changes that result in modified bulk properties of the metal [4]. Material characterization techniques such as X-ray, neutron and electron diffraction, light optical microscopy, and electron and ion beam microscopy are employed to investigate and quantify the microstructural features of metals at various length scales [1]. Some of these techniques are time-consuming and expensive; researchers often resort to light optical microscopy for performing tasks such as metallurgical phase identification and evaluation of grain

Objectives

Methods

Results

Conclusion