Machine learning-assisted constitutive modeling of a novel powder metallurgy superalloy

Wen, Hongning; Jin, Junsong; Tang, Xuefeng; Wang, Xinyun; Yang, Heyang; Zhang, Yiding; Zhang, Mao; Deng, Lei; Wei, Qingsong; Chen, Junzhi; Ma, Xiaolong; Guo, Jianzheng

doi:10.1016/j.ijmecsci.2023.108654

Cited by 14 publications

(2 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wang et al [37] used a machine learning algorithm based on singular value decomposition and deep neural networks to build metamodels for constitutive models, which not only assists in parameter fitting but also facilitates the understanding and analysis of constitutive models. Wen et al [38] proposed a machine learning-assisted physical model to predict the flow behavior and microstructure evolution of a novel FGH4113A superalloy during thermomechanical processing and compared the predicted values with experimental data to show that the prediction accuracy is better than the traditional model. There are a variety of machine learning algorithms, and different algorithms are suitable for different situations, depending on the type of problem to be solved and the quality of the data set.…”

Section: Introductionmentioning

confidence: 99%

The Prediction of Flow Stress in the Hot Compression of a Ni-Cr-Mo Steel Using Machine Learning Algorithms

Pan,

Song,

Gao

et al. 2024

Processes

View full text Add to dashboard Cite

The constitutive model refers to the mapping relationship between the stress and deformation conditions (such as strain, strain rate, and temperature) after being loaded. In this work, the hot deformation behavior of a Ni-Cr-Mo steel was investigated by conducting isothermal compression tests using a Gleeble-3800 thermal simulator with deformation temperatures ranging from 800 °C to 1200 °C, strain rates ranging from 0.01 s−1 to 10 s−1, and deformations of 55%. To analyze the constitutive relation of the Ni-Cr-Mo steel at high temperatures, five machine learning algorithms were employed to predict the flow stress, namely, back-propagation artificial neural network (BP-ANN), Random Committee, Bagging, k-nearest neighbor (k-NN), and a library for support vector machines (libSVM). A comparative study between the experimental and the predicted results was performed. The results show that correlation coefficient (R), root mean square error (RMSE), mean absolute value error (MAE), mean square error (MSE), and average absolute relative error (AARE) obtained from the Random Committee on the testing set are 0.98897, 8.00808 MPa, 5.54244 MPa, 64.12927 MPa2 and 5.67135%, respectively, whereas the metrics obtained via other algorithms are all inferior to the Random Committee. It suggests that the Random Committee can predict the flow stress of the steel more effectively.

show abstract

Section: Introductionmentioning

confidence: 99%

The Prediction of Flow Stress in the Hot Compression of a Ni-Cr-Mo Steel Using Machine Learning Algorithms

Pan,

Song,

Gao

et al. 2024

Processes

View full text Add to dashboard Cite

show abstract

“…ML is the method that focuses on creating algorithms capable of learning from, predicting, or categorizing data which has been widely employed in the field of materials science [16][17][18][19]. For instance, ML methodologies have been employed to characterize material behaviors such as deformation [20], recrystallization [18], work-hardening [21], and even the compositional design of new alloys [22]. However, predicting the performance of DMHT turbine disks using machine learning is still challenging, and there have been no previous reports on this topic based on the authors' knowledge.…”

Section: Introductionmentioning

confidence: 99%

The Integration of ANN and FEA and Its Application to Property Prediction of Dual-Performance Turbine Disks

Li,

Zhang,

Cheng

et al. 2024

Materials

Self Cite

View full text Add to dashboard Cite

Regulating the microstructure of powder metallurgy (P/M) nickel-based superalloys to achieve superior mechanical properties through heat treatment is a prevalent method in turbine disk design. However, in the case of dual-performance turbine disks, the complexity and non-uniformity of the heat treatment process present substantial challenges. The prediction of yield strength is typically derived from the analysis of microstructures under various heat treatment regimes. This method is time-consuming, expensive, and the accuracy often depends on the precision of microstructural characterization. This study successfully employed a coupled method of Artificial Neural Network (ANN) and finite element analysis (FEA) to reveal the relationship between the heat treatment process and yield strength. The coupled method accurately predicted the location specified and temperature-dependent yield strength based on the heat treatment parameters such as holding temperatures and cooling rates. The root mean square error (RMSE) and mean absolute percentage deviation (MAPD) for the training set are 50.37 and 3.77, respectively, while, for the testing set, they are 50.13 and 3.71, respectively. Furthermore, an integrated model of FEA and ANN is established using a Abaqus user subroutine. The integrated model can predict the yield strength based on temperature calculation results and automatically update material properties of the FEA model during the loading process simulation. This allows for an accurate calculation of the stress–strain state of the turbine disk during actual working conditions, aiding in locating areas of stress concentration, plastic deformation, and other critical regions, and provides a novel reliable reference for the rapid design of the turbine disk.

show abstract

Modelling and industrial experiment on the dynamic deviation of rolling force during high precision rolling process

Chen,

Liu,

Lin

2025

Alexandria Engineering Journal

View full text Add to dashboard Cite

Machine learning-assisted constitutive modeling of a novel powder metallurgy superalloy

Cited by 14 publications

References 59 publications

The Prediction of Flow Stress in the Hot Compression of a Ni-Cr-Mo Steel Using Machine Learning Algorithms

The Prediction of Flow Stress in the Hot Compression of a Ni-Cr-Mo Steel Using Machine Learning Algorithms

The Integration of ANN and FEA and Its Application to Property Prediction of Dual-Performance Turbine Disks

Modelling and industrial experiment on the dynamic deviation of rolling force during high precision rolling process

Contact Info

Product

Resources

About