Hot deformation behaviors of AZ91 magnesium alloy: Constitutive equation, ANN-based prediction, processing map and microstructure evolution

WANG, Dong-xiao; Zhu, Qiang-qiang; Wei, Zhao; Lin, Baosen; Jing, Yuanwei; Shi, Yan; Misra, R.D.K.; Li, J.P.

doi:10.1016/j.jallcom.2022.164580

Cited by 58 publications

(10 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The supervised learning comprised 60% of specimens, the verification time series comprised 20% of specimens, and the testing data source held 20% of all specimens. The verification dataset is used to reduce the possibility of an over or forgetting [35]. This implies that whenever the inaccuracy of a learning test dataset drops while the fault of a testing dataset set grows, then network training is halted, and overtraining is prevented.…”

Section: Resultsmentioning

confidence: 99%

Optimization Process of Potassium Carbonate Activated Carbon through Jute-Based Core Materials by Using Artificial Neural Network with Response Surface Methodology

Natrayan

Niveditha

Kaliappan³

et al. 2023

Adsorption Science & Technology

View full text Add to dashboard Cite

Potassium carbonate was tested as novel information for producing carbonaceous materials from jute cores. Two quadratic models have been developed for both answers to link the preparatory parameters: activating temperatures, molar ratio, and incubation time. The RSM and ANN models were used to improve the processing conditions to maximise the quantities of iodine and methylene blue penetration. The best charcoal was obtained using 900°C activating temperatures, a 1.5 molar ratio, and a 4-hour activating time. This resulted in iodine and methylene blue absorption of 1260.07 mg/g and 369.21 mg/g, respectively. It was discovered that the K2CO3-based pyrolysis process might be anticipated to become a safe yet incredibly efficient process of making activated carbons with a very well-defined and monocultural porous structure. Even though the precise emphasis given to K2CO3 is unknown at the moment, given the creation of K2C3O4 just after evolvement with one additional molarity of CO at approximately 870°C, these same porous and papule responses begun by K2CO3 stimulation might be temporarily posited to be quite comparable to an initiation action needed to make progress by K2C3O4. The influence of control parameters was examined in this study using variance analysis like the ANOVA test. Furthermore, the response surface (RSM) and artificial neural networks (ANN) are employed to improve the output results while optimising the methylene blue and iodine qualities. Consequently, the experimental findings correlate well with the statistics.

show abstract

Section: Resultsmentioning

confidence: 99%

Optimization Process of Potassium Carbonate Activated Carbon through Jute-Based Core Materials by Using Artificial Neural Network with Response Surface Methodology

Natrayan

Niveditha

Kaliappan³

et al. 2023

Adsorption Science & Technology

View full text Add to dashboard Cite

show abstract

“…Following the principle of the maximum entropy generation rate, the criterion for the instability parameter (ξ) can be described as Equation ( 14) [51,52]. If ξ < 0, there is a high likelihood of adiabatic shear bands, microscopic pores, cracks, and triangular grain boundary cracking occurring inside the material.…”

Section: Processing Mapsmentioning

confidence: 99%

Hot Deformation Behavior and Microstructural Evolution of a TiB2/Al-Zn-Mg-Cu-Zr Composite

Huang,

Xiang,

et al. 2024

Materials

View full text Add to dashboard Cite

In the present work, the hot deformation behavior and microstructural evolution of a TiB2/Al-Zn-Mg-Cu-Zr composite were studied. Hot compression tests were conducted within a temperature range of 370 °C to 490 °C and a strain rate of 0.001 s−1 to 10 s−1. We established the Arrhenius constitutive equation with Zener–Hollomon parameters and processing maps and discussed the microstructural evolution during hot deformation. The results indicated that the safe processing parameter region falls within 370 °C–490 °C and 0.001 s−1–0.025 s−1. The influence of the strain rate on the safe processing range is more dominant than that of deformation temperature, which is primarily attributed to TiB2. Dynamic softening is primarily governed by dynamic recovery (DRV). Small particles (η, Al3Zr) can pin dislocations, promoting the rearrangement and annihilation of dislocations and facilitating DRV. Higher temperatures and lower strain rates facilitated dynamic recrystallization (DRX). Continuous dynamic recrystallization (CDRX) occurs near high-angle grain boundaries induced by strain-induced boundary migration (SIBM). TiB2 and large second-phase particles generate high-density geometrically necessary dislocations (GNBs) during hot deformation, which serve as nucleation sites for discontinuous dynamic recrystallization (DDRX). This enhances dynamic softening and improves formability.

show abstract

“…During the hot deformation process of magnesium alloys, DRX is commonly observed, with continuous dynamic recrystallization (CDRX) and DDRX being the main types of DRX [19][20][21]. Wang et al [22] found in the hot deformation of AZ91 alloy at 523 K, twininduced DRX primarily occurs in the form of DDRX. Li et al [23] studied the softening mechanism of Mg-2Ho alloy during hot deformation, namely DDRX and CDRX.…”

Section: Introductionmentioning

confidence: 99%

Prediction of flow stress in Mg-3Dy alloy based on constitutive equation and PSO-SVR model

Liu,

Feng,

Liu

et al. 2024

Mater. Res. Express

View full text Add to dashboard Cite

This study conducted hot compression experiments on as-cast Mg-3Dy alloy under deformation parameters of 380-470℃ and 0.001-1s-1. The microstructure of the alloy was observed using EBSD, and the flow stress of the Mg-3Dy alloy was predicted using the Arrhenius model and the particle swarm optimization-support vector regression (PSO-SVR) model. The organizational analysis results showed that the main recrystallization mechanism in the alloy is the discontinuous dynamic recrystallization (DDRX) mechanism. The generation of twins in the alloy was mostly the result of local stress action. The optimal processing window for this alloy was determined to be 380-470 °C and 0.001-0.01 s-1 through the thermal processing map. The prediction accuracies of the Arrhenius model and PSO-SVR model were evaluated using the correlation coefficient R2 and mean squared error MSE. The results showed that the PSO-SVR model significantly outperforms the Arrhenius model in prediction accuracy, with R2 value of 0.99982 and MSE of 0.074.

show abstract

Hot deformation behaviors of AZ91 magnesium alloy: Constitutive equation, ANN-based prediction, processing map and microstructure evolution

Cited by 58 publications

References 38 publications

Optimization Process of Potassium Carbonate Activated Carbon through Jute-Based Core Materials by Using Artificial Neural Network with Response Surface Methodology

Optimization Process of Potassium Carbonate Activated Carbon through Jute-Based Core Materials by Using Artificial Neural Network with Response Surface Methodology

Hot Deformation Behavior and Microstructural Evolution of a TiB2/Al-Zn-Mg-Cu-Zr Composite

Prediction of flow stress in Mg-3Dy alloy based on constitutive equation and PSO-SVR model

Contact Info

Product

Resources

About