Structure prediction of multi-principal element alloys using ensemble learning

Abstract

Purpose The purpose of this paper, is to predict the various phases and crystal structure from multi-component alloys. Nowadays, the concept and strategies of the development of multi-principal element alloys (MPEAs) significantly increase the count of the potential candidate of alloy systems, which demand proper screening of large number of alloy systems based on the nature of their phase and structure. Experimentally obtained data linking elemental properties and their resulting phases for MPEAs is profused; hence, there is a strong scope for categorization/classification of MPEAs based on structural features of the resultant phase along with distinctive connections between elemental properties and phases. Design/methodology/approach In this paper, several machine-learning algorithms have been used to recognize the underlying data pattern using data sets to design MPEAs and classify them based on structural features of their resultant phase such as single-phase solid solution, amorphous and intermetallic compounds. Further classification of MPEAs having single-phase solid solution is performed based on crystal structure using an ensemble-based machine-learning algorithm known as random-forest algorithm. Findings The model developed by implementing random-forest algorithm has resulted in an accuracy of 91 per cent for phase prediction and 93 per cent for crystal structure prediction for single-phase solid solution class of MPEAs. Five input parameters are used in the prediction model namely, valence electron concentration, difference in the pauling negativeness, atomic size difference, mixing enthalpy and mixing entropy. It has been found that the valence electron concentration is the most important feature with respect to prediction of phases. To avoid overfitting problem, fivefold cross-validation has been performed. To understand the comparative performance, different algorithms such as K-nearest Neighbor, support vector machine, logistic regression, naïve-based approach, decision tree and neural network have been used in the data set. Originality/value In this paper, the authors described the phase selection and crystal structure prediction mechanism in MPEA data set and have achieved better accuracy using machine learning.

pyMPEALab Toolkit for Accelerating Phase Design in Multi-principal Element Alloys

“…Most of the earlier works on machine learning based phase predictions of HEA/MPEA [19,35,36] do not consider the composition vector of alloy as a fingerprint in the model. Neither do these models associate the composition vector with other fingerprints.…”

Designing hexagonal close packed high entropy alloys using machine learning

“…The DT predicated ensemble algorithm can give better performance for independent base learners, which can be achieved through randomization. While growing the trees, a better tree diversity is needed for randomization, which facilitates truncating the correlation [38]. A robust and stable classifier (model) in supervised ML tasks with accurate predictions can be achieved utilizing an ensemble method to reduce the factors, i.e.…”

“…variance, noise, and bias. Nevertheless, the main drawback that an ensemble learner faces is the imminent rise in computational time due to multiple individual classifiers training [38]. As a result, the ET algorithm has been highlighted, which works virtually akin to, yet more expeditious than the random forest algorithm.…”

Processing Technique Selection for Steels Based on Mechanical Properties Using Machine Learning Framework

“…In machine learning, logistic regression is useful while obtaining a particular class or event existing from the actual class table . Various classification techniques such as logistic regression, support vector machine, K-nearest neighbor, and random forest is used to compare the results [34][35][36][37][38]. In this paper, a multi class classification is discussed to predict the thermomechanical processing routes, namely hot rolled (HR), cold drawn (CR) annealed cold drawn (ACR), and spheroidite annealed cold drawn (SCR) as describe in table 1.…”