Constitutive Modeling of A286 Superalloy: Comparison of Improved Khan-Huang-Liang, Improved Johnson-Cook, and Genetic Algorithm-Backpropagation Artificial Neural Network Models

This study aims to develop high-precision constitutive models for A286 superalloy to accurately predict material flow stress and provide robust support for numerical simulations. Uniaxial quasi-static compression tests were performed to obtain the flow stress of A286 superalloy across strain rates f...

Full description

Saved in:
Bibliographic Details
Published in:Journal of materials engineering and performance Vol. 34; no. 23; pp. 28170 - 28182
Main Authors: Tao, Liang, Feng, Zhiguo, Jiang, Yulian, Mo, Ningning, Lu, Rengang
Format: Journal Article
Language:English
Published: New York Springer US 01.12.2025
Springer Nature B.V
Subjects:
Accuracy
Artificial neural networks
Back propagation
Back propagation networks
Characterization and Evaluation of Materials
Chemistry and Materials Science
Compression tests
Computer simulation
Constitutive models
Correlation coefficients
Corrosion and Coatings
Deformation
Engineering Design
Genetic algorithms
Heat treating
Materials Science
Metal fatigue
Neural networks
Original Research Article
Quality Control
Reliability
Safety and Risk
Simulation
Software
Strain hardening
Superalloys
Temperature
Titanium alloys
Tribology
Yield strength
Yield stress
United States > US
genetic algorithm
artificial neural network
constitutive model
numerical simulation
superalloy
ISSN:1059-9495, 1544-1024
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This study aims to develop high-precision constitutive models for A286 superalloy to accurately predict material flow stress and provide robust support for numerical simulations. Uniaxial quasi-static compression tests were performed to obtain the flow stress of A286 superalloy across strain rates from 0.01 to 10 s −1 and temperatures from 25 to 600 °C. Based on the experimental data, three constitutive models were developed: an improved Khan-Huang-Liang (KHL) model, an improved Johnson-Cook (J-C) model, and a genetic algorithm-backpropagation artificial neural network (GA-BP ANN) model. The accuracy of the three models in predicting flow stress and their performance in numerical simulations were evaluated using the correlation coefficient ( R ), average absolute relative error ( AARE ), and relative error ( RE ). Results demonstrate that all three models effectively predict the material’s flow stress and are successfully applied in thin-walled tube simulations. Among them, the GA-BP ANN model achieves the highest accuracy in predicting flow stress ( R  = 0.999, AARE  = 1.6%) and simulation precision ( RE  = − 5.1%), followed by the improved J-C model ( R  = 0.979, AARE  = 1.7%, RE  = − 5.3%), and the improved KHL model with the lowest performance ( R  = 0.953, AARE  = 3.5%, RE  = − 6.2%).
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1059-9495
1544-1024
DOI:10.1007/s11665-025-11425-w