An intelligent design for Ni-based superalloy based on machine learning and multi-objective optimization

[Display omitted] •A prediction model of Multi-objective Evolutionary Algorithm combined with Machine Learning was established to optimize multiple properties simultaneously.•Ni-based superalloy candidates were obtained with high γ′ solves temperature, high γ′ volume fraction and low topologically c...

Full description

Saved in:
Bibliographic Details
Published in:Materials & design Vol. 221; p. 110935
Main Authors: Deng, Yuedan, Zhang, Yu, Gong, Xiufang, Hu, Wang, Wang, Yucheng, Liu, Ying, Lian, Lixian
Format: Journal Article
Language:English
Published: Elsevier Ltd 01.09.2022
Elsevier
Subjects:
Machine learning
Microscopic parameters
Multi-objective evolutionary algorithm
Ni-based superalloys
Thermo-Calc
Ni-based superalloys
Multi-objective evolutionary algorithm
Microscopic parameters
Thermo-Calc
Machine learning
ISSN:0264-1275, 1873-4197
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:[Display omitted] •A prediction model of Multi-objective Evolutionary Algorithm combined with Machine Learning was established to optimize multiple properties simultaneously.•Ni-based superalloy candidates were obtained with high γ′ solves temperature, high γ′ volume fraction and low topologically closed-packed phase content.•Properties of Ni-based superalloy candidates verified by experiment showed great accuracy with prediction. The simultaneous consideration of multiple conflicting properties in alloy optimization design is necessary yet remains challenging. A comprehensive strategy of machine learning (ML) and multi-objective optimization based on thermodynamic simulation data was proposed to accelerate the composition design of Ni-based superalloys. The microscopic parameters were determined by Pearson correlation analysis and domain knowledge as the key affect factors of tensile strength and elongation. The Multi-objectives Evolutionary Algorithm (MOEA) was adopted to search the well-built surrogate by ML meta-heuristically for the Pareto front of three objectives and its responding Pareto optimal solution set of composition. Furthermore, nine high-performance superalloy samples selected from the obtained Pareto front were well verified by fabricating and testing in the laboratory. Specially, a new composition among the nine as-fabricated samples was the best one according to the pre-defined design preferences with the γ′ solvus temperature, γ′ volume fraction, and TCP phases content approximating to 1210 °C, 65%, and 0.01%, respectively. This intelligent cooperation strategy based on ML and MOEA extends the methodology for multi-composition and multi-property design materials, which can optimize multiple conflicting objectives simultaneously rather than do one by one.
ISSN:0264-1275
1873-4197
DOI:10.1016/j.matdes.2022.110935