Research on Neural Network Prediction of Multidirectional Forging Microstructure Evolution of GH4169 Superalloy

Jin, Yongbo; Zhao, Jingqi; Zhang, Chunxiang; Luo, Junting; Wang, Sirui

doi:10.1007/s11665-021-05536-3

Cited by 8 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work, the feature selection techniques include genetic algorithm (GA), [23] backward elimination (BE), [24] and forward selection (FS). [25] The modeling algorithms include support vector regression (SVR), [26][27] artificial neural network (ANN), [28][29] and partial least squares (PLS). [30] Therefore, GA, BE, and FS nested SVR, ANN, and PLS were adopted for feature selection, respectively.…”

Section: Feature Selectionmentioning

confidence: 99%

Accelerated Discovery of Ternary Gold Alloy Materials with Low Resistivity via an Interpretable Machine Learning Strategy

Wang

Zhou

et al. 2022

Chemistry An Asian Journal

View full text Add to dashboard Cite

New ternary gold alloys with low resistivities (1) were screened out via an interpretable machine learning strategy by using the support vector regression (SVR) model integrated with SHAP analysis. The correlation coefficient (R) and the root mean square error (RMSE) of test set were 0.876 and 0.302, respectively, indicating the strong generalization ability of the model. The average 1 of top 10 candidates was 1.22 × 10 À 7 Ω m, which was 41% lower than the known minimum of 2.08 × 10 À 7 Ω m. The outputs of SVR model were analyzed with the critical SHAP values including first ionization energy of C-site (584 kJ • mol À 1 ), electronegativity of Csite (1.72) and the second ionization energy of B-site (1135 kJ • mol À 1 ), respectively. Moreover, an online web server was developed to share the model at http://materials-datamining.com/onlineservers/wxdaualloy.

show abstract

Section: Feature Selectionmentioning

confidence: 99%

Accelerated Discovery of Ternary Gold Alloy Materials with Low Resistivity via an Interpretable Machine Learning Strategy

Wang

Zhou

et al. 2022

Chemistry An Asian Journal

View full text Add to dashboard Cite

show abstract

“…These models have been extensively employed in simulation models for manufacturing processes in which high processing temperatures are involved. For example, based on the hot compression experimental data of In718 superalloy, Jin et al [ 19 , 20 ] established a constitutive equation based on the Sellars–Tegart model to predict the flow stress of In718 at high temperatures in their simulation of the forging processes. Wang et al [ 21 ] also used the Sellars–Tegart model to predict the characterization of residual stresses and grain structures after hot forging of In718 alloy.…”

Section: Introductionmentioning

confidence: 99%

Towards an Optimized Artificial Neural Network for Predicting Flow Stress of In718 Alloys at High Temperatures

et al. 2023

View full text Add to dashboard Cite

Artificial neural networks (ANNs) have been an important approach for predicting the value of flow stress, which is dependent on temperature, strain, and strain rate. However, there is still a lack of sufficient knowledge regarding what structure of ANN should be used for predicting metal flow stress. In this paper, we train an ANN for predicting flow stress of In718 alloys at high temperatures using our experimental data, and the structure of the ANN is optimized by comparing the performance of four ANNs in predicting the flow stress of In718 alloy. It is found that, as the size of the ANN increases, the ability of the ANN to retrieve the flow stress results from a training dataset is significantly enhanced; however, the ability to predict the flow stress results absent from the training does not monotonically increase with the size of the ANN. It is concluded that the ANN with one hidden layer and four nodes possesses optimized performance for predicting the flow stress of In718 alloys in this study. The reason why there exists an optimized ANN size is discussed. When the ANN size is less than the optimized size, the prediction, especially the strain dependency, falls into underfitting and fails to predict the curve. When the ANN size is less than the optimized size, the predicted flow stress curves with the temperature, strain, and strain rate will contain non-physical fluctuations, thus reducing their prediction accuracy of extrapolation. For metals similar to the In718 alloy, ANNs with very few nodes in the hidden layer are preferred rather than the large ANNs with tens or hundreds of nodes in the hidden layers.

show abstract

“…The cellular automata (CA) [ 12 , 13 , 14 ] method can be used, for example, for simulation of dynamic recrystallization behavior under hot isothermal compressions for as-extruded 3Cr20Ni10W2 heat-resistant alloy [ 12 ], modeling of solidification microstructure evolution in laser powder bed fusion-fabricated 316L stainless steel [ 13 ], simulation of coupled hydrogen porosity, and microstructure during solidification of ternary aluminum alloys [ 14 ]. Other examples of used numerical methods to model the evolution of microstructure in materials are analysis of metal extrusion by the finite volume method (FVM) [ 15 ], prediction of multidirectional forging microstructure evolution of GH4169 superalloy by the neural network [ 16 ], and prediction of microstructure evolution with convolutional recurrent neural networks [ 17 ]. Multiscale models, which are a combination of several methods (for example, finite element and cellular automata or cellular automata and finite volume), are also used.…”

Section: Introductionmentioning

confidence: 99%

New Platforms Based on Frontal Cellular Automata and Lattice Boltzmann Method for Modeling the Forming and Additive Manufacturing

Łach

Svyetlichnyy

2022

Materials

View full text Add to dashboard Cite

Materials science gives theoretical and practical tools, while new modeling methods and platforms provide rapid and efficient development, improvement, and optimization of old and new technologies. Recently, impressive progress has been made in the development of computer software and systems. The frontal cellular automata (FCA), lattice Boltzmann method (LBM), and modeling platforms based on them are considered in the paper. The paper presents basic information on these methods and their application for modeling phenomena and processes in materials science. Recrystallization, crystallization, phase transformation, processes such as flat and shape rolling, additive manufacturing technologies (Selective Laser Sintering (SLS)/ Selective Laser Melting (SLM)), and others are examples of comprehensive and effective modeling by the developed systems. Selected modeling results are also presented.

show abstract

Research on Neural Network Prediction of Multidirectional Forging Microstructure Evolution of GH4169 Superalloy

Cited by 8 publications

References 17 publications

Accelerated Discovery of Ternary Gold Alloy Materials with Low Resistivity via an Interpretable Machine Learning Strategy

Accelerated Discovery of Ternary Gold Alloy Materials with Low Resistivity via an Interpretable Machine Learning Strategy

Towards an Optimized Artificial Neural Network for Predicting Flow Stress of In718 Alloys at High Temperatures

New Platforms Based on Frontal Cellular Automata and Lattice Boltzmann Method for Modeling the Forming and Additive Manufacturing

Contact Info

Product

Resources

About