Machine-learning-guided descriptor selection for predicting corrosion resistance in multi-principal element alloys

M F N Taufique,Ram Devanathan,Ganesh Balasubramanian,Duane D Johnson,Hrishabh Khakurel,Ankit Roy

doi:10.1038/s41529-021-00208-y

Abstract

More than $270 billion is spent on combatting corrosion annually in the USA alone. As such, we present a machine-learning (ML) approach to down select corrosion-resistant alloys. Our focus is on a non-traditional class of alloys called multi-principal element alloys (MPEAs). Given the vast search space due to the variety of compositions and descriptors to be considered, and based upon existing corrosion data for MPEAs, we demonstrate descriptor optimization to predict corrosion resistance of any given MPEA. Our ML model with descriptor optimization predicts the corrosion resistance of a given MPEA in the presence of an aqueous environment by down selecting two environmental descriptors (pH of the medium and halide concentration), one chemical composition descriptor (atomic % of element with minimum reduction potential), and two atomic descriptors (difference in lattice constant (Delta {{{mathrm{a}}}}) and average reduction potential). Our findings show that, while it is possible to down select corrosion-resistant MPEAs by using ML from a large search space, a larger dataset and higher quality data are needed to accurately predict the corrosion rate of MPEAs. This study shows both the promise and the perils of ML when applied to a complex chemical phenomenon like corrosion of alloys.

Highlights

Corrosion of industrial machinery, bridges, engineering equipment, vehicles, and structures under different corrosive environments is a major concern for food processing and chemical industries, power plants, maritime and air transport
Birbilis et al and Yeh et al suggested that an emerging class of materials, high entropy alloys (HEAs) and multi-principal element alloys (MPEAs), are being considered as preferred candidates for corrosionresistant applications compared to conventional alloys, such as stainless steels, Ni-based alloys, and Ti-based alloys[2,3]
According to the “no-free-lunch” theorem[34], there does not exist a perfect model for a given problem

Summary

Introduction

Bridges, engineering equipment, vehicles, and structures under different corrosive environments is a major concern for food processing and chemical industries, power plants, maritime and air transport. It is reported that in the United States 6.2% of the gross domestic product (GDP) is spent to replace engineering equipment in industries due to corrosion[1]. The development of corrosion-resistant materials and coatings capable of extending the lifespan of equipment and structures can yield substantial economic benefits. Birbilis et al and Yeh et al suggested that an emerging class of materials, high entropy alloys (HEAs) and multi-principal element alloys (MPEAs), are being considered as preferred candidates for corrosionresistant applications compared to conventional alloys, such as stainless steels, Ni-based alloys, and Ti-based alloys[2,3]. Certain MPEA compositions have exhibited excellent hardness, exceptional wear properties, as well as high-temperature strength relative to traditional alloys[2,4,5,6,7,8]

Objectives

Methods

Results