A feasibility study of machine learning-assisted alloy design using wrought aluminum alloys as an example

Soofi, Yasaman J.; Rahman, Md Asad; Gu, Yijia; Liu, Jinling

doi:10.1016/j.commatsci.2022.111783

Cited by 13 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study uses random forest regressors for forward prediction due to their higher accuracy in predicting the mechanical properties of aluminium alloys [12,15]. Tree-based methods partition the feature space into distinct regions through successive splits, beginning at the root and continuing until a stop criterion is reached [29].…”

Section: Multi-target Random Forest Modelsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…Machine learning has emerged as a powerful tool for identifying non-linear relationships in metallic alloys (including Al alloys), successfully predicting mechanical properties based on alloy compositions and processing conditions [10][11][12][13][14][15][16]. Random forest models have predicted tensile strength and elongation in wrought Al alloys with 11% and 14% error rates, respectively [15]. In Al-Mg-Si alloys, random forest models have also been reported to perform better than neural network and support vector regression in tensile strength prediction, achieving an error rate of 2.87% on a test set [12].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Inverse Design of Aluminium Alloys Using Genetic Algorithm: A Class-Based Workflow

Bhat,

Barnard,

Birbilis

2024

Metals

View full text Add to dashboard Cite

The design of aluminium alloys often encounters a trade-off between strength and ductility, making it challenging to achieve desired properties. Adding to this challenge is the broad range of alloying elements, their varying concentrations, and the different processing conditions (features) available for alloy production. Traditionally, the inverse design of alloys using machine learning involves combining a trained regression model for the prediction of properties with a multi-objective genetic algorithm to search for optimal features. This paper presents an enhancement in this approach by integrating data-driven classes to train class-specific regressors. These models are then used individually with genetic algorithms to search for alloys with high strength and elongation. The results demonstrate that this improved workflow can surpass traditional class-agnostic optimisation in predicting alloys with higher tensile strength and elongation.

show abstract

Section: Multi-target Random Forest Modelsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Inverse Design of Aluminium Alloys Using Genetic Algorithm: A Class-Based Workflow

Bhat,

Barnard,

Birbilis

2024

Metals

View full text Add to dashboard Cite

show abstract

Classification of T6 Tempered 6XXX Series Aluminum Alloys Based on Machine Learning Principles

Tiwari,

Jalalian,

Mendis

et al. 2023

JOM

View full text Add to dashboard Cite

Aluminum alloys are widely used in each sector of engineering because of their lower density coupled with higher strength compared to many existing alloys of other metals. Due to these unique characteristics, there is acceleration in demand and discovery of new aluminum alloys with targeted properties and compositions. Traditional methods of designing new materials with desired properties, like ‘domain specialists and trial-and-error ' approaches, are laborious and costly. These techniques also lead to the expansion of alloy search area. Also, high demand for recycling of aluminum alloys requires fewer alloy groups. We suggest a machine learning design system to reduce the number of grades in the 6XXX series of aluminum alloys by collecting the features involving chemical composition and tensile properties at T6 tempering state. This work demonstrates the efficiency of grouping the aluminum alloys into a number of clusters by a combined PCA and K-means algorithm. To understand the physics inside the clusters we used an explainable artificial intelligence algorithm and connected the findings with sound metallurgical reasoning. Through machine learning we will narrow down the search space of 6XXX series aluminum alloys to few groups. This work offers a useful method for reducing compositional space of aluminum alloys.

show abstract

An Explainable Deep Learning Model Based on Multi-scale Microstructure Information for Establishing Composition–Microstructure–Property Relationship of Aluminum Alloys

Ma,

Zhang,

Han

et al. 2024

Integr Mater Manuf Innov

View full text Add to dashboard Cite

A feasibility study of machine learning-assisted alloy design using wrought aluminum alloys as an example

Cited by 13 publications

References 21 publications

Inverse Design of Aluminium Alloys Using Genetic Algorithm: A Class-Based Workflow

Inverse Design of Aluminium Alloys Using Genetic Algorithm: A Class-Based Workflow

Classification of T6 Tempered 6XXX Series Aluminum Alloys Based on Machine Learning Principles

An Explainable Deep Learning Model Based on Multi-scale Microstructure Information for Establishing Composition–Microstructure–Property Relationship of Aluminum Alloys

Contact Info

Product

Resources

About