Modeling hot deformation behavior of low-cost Ti-2Al-9.2Mo-2Fe beta titanium alloy using a deep neural network

Li, Chenglin; Narayana, P.L.; Reddy, N.S.; Choi, Sunwoong; Yeom, Jong‐Taek; Hong, Jae‐Keun; Park, Chan Hee

doi:10.1016/j.jmst.2018.11.018

Cited by 46 publications

(8 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…the hot working. In addition, artificial neural networks based on machine learning have been applied to predict the hot deformation behavior [95], flow stress [96], microstructure evolution [97], and processing parameters [98] of titanium alloys. For example, a low-cost titanium alloy with bone-like Young's modulus was designed using neural networks, as shown in Figure 2 [99].…”

Section: Hot Working and Machiningmentioning

confidence: 99%

Low-Cost Preparation Technologies for Titanium Alloys: A Review

Feng¹,

Li²

2023

Titanium Alloys - Recent Progress in Design, Processing, Characterization, and Applications

View full text Add to dashboard Cite

The titanium industry has been developing for nearly 70 years since the birth of Ti-6Al-4 V alloy. Due to its high specific strength, high and low-temperature resistance, corrosion resistance and good biocompatibility, titanium alloy is used in aerospace, marine engineering, and biomedical fields. However, the high production cost of titanium alloys currently limits their widespread use like steel and aluminum alloys. Therefore, the low-cost preparation technology for titanium alloys becomes hot research in recent years. This chapter provides a comprehensive overview of low-cost preparation technologies for titanium alloys from four aspects: raw materials, melting, hot working and machining, and advanced technologies. This review would be of interest to scholars in related fields.

show abstract

Section: Hot Working and Machiningmentioning

confidence: 99%

Low-Cost Preparation Technologies for Titanium Alloys: A Review

Feng¹,

Li²

2023

Titanium Alloys - Recent Progress in Design, Processing, Characterization, and Applications

View full text Add to dashboard Cite

show abstract

“…High-temperature deformation behavior of Ti alloy is nonlinearly affected by various factors, which can be effectively solved through machine learning. Indeed, there have been several endeavors to predict a high-temperature flow curve [ 9 , 10 , 11 , 12 ] or to plot a processing map [ 13 , 14 , 15 ] of Ti alloys using machine learning. However, most of these studies employed the artificial neural network (ANN) as a machine-learning approach; they either compared ANN with a constitutive approach [ 10 , 11 ] or tried to improve ANN performance [ 13 ].…”

Section: Introductionmentioning

confidence: 99%

“…Indeed, there have been several endeavors to predict a high-temperature flow curve [ 9 , 10 , 11 , 12 ] or to plot a processing map [ 13 , 14 , 15 ] of Ti alloys using machine learning. However, most of these studies employed the artificial neural network (ANN) as a machine-learning approach; they either compared ANN with a constitutive approach [ 10 , 11 ] or tried to improve ANN performance [ 13 ]. Few exceptional studies [ 12 , 15 ] adopted the genetic algorithm and support vector regression for their prediction.…”

Section: Introductionmentioning

confidence: 99%

Enhanced processing map of Ti–6Al–2Sn–2Zr–2Mo–2Cr–0.15Si aided by extreme gradient boosting

Bae

Kim

et al. 2022

Heliyon

View full text Add to dashboard Cite

“…Meanwhile, because of the high learning adaptability of artificial intelligence, Peng et al [ 41 ] and Mosleh et al [ 42 ] developed high-accuracy artificial intelligence models to forecast the flow behavior of a Ti60 alloy and Ti-2.5Al-1.8Mn alloy, respectively. Correspondingly, several artificial intelligence algorithms have been proposed to precisely model the high-temperature flow features of other titanium alloys, such as a Ti-2Al-9.2Mo-2Fe beta alloy [ 43 ], a Ti40 alloy [ 44 ], and a Ti600 alloy [ 45 ]. However, the two aforementioned types of constitutive models have difficulty clarifying the microstructural change mechanisms of alloys during high-temperature forming.…”

Section: Introductionmentioning

confidence: 99%

Microstructural Variation and a Physical Mechanism Model for a Ti-55511 Alloy during Double-Stage Hot Deformation with Stepped Strain Rates in the β Region

Lin

et al. 2021

Materials

View full text Add to dashboard Cite

The microstructural variation and high-temperature flow features of a Ti-55511 alloy in the β region are studied by utilizing double-stage compression with a stepped strain rate. The results demonstrate that the stresses in the latter stage of hot compression markedly reduce as the strain at the previous stage or the strain rate at the previous/latter stage drops. Moreover, the annihilation/interaction of substructures is promoted, and the distinct refinement of the dynamic recrystallization (DRX) in the β grain can be found. However, the coarsening of the β grain and the consumption of dislocation substructures are accelerated at high temperatures. Furthermore, the principal DRX nucleation mechanism of the Ti-55511 alloy during double-stage compression with a stepped strain rate in the β region is discontinuous DRX. Additionally, by using the microstructural variation characteristics related to the forming parameters, a physical mechanism equation is modeled to forecast the forming features, the DRX fraction, and the size of the β grain in the investigated alloy. The forecasted results are in accordance with the tested results, indicating that the established model can accurately forecast the microstructure variation and flow features of the studied alloy.

show abstract

Modeling hot deformation behavior of low-cost Ti-2Al-9.2Mo-2Fe beta titanium alloy using a deep neural network

Cited by 46 publications

References 44 publications

Low-Cost Preparation Technologies for Titanium Alloys: A Review

Low-Cost Preparation Technologies for Titanium Alloys: A Review

Enhanced processing map of Ti–6Al–2Sn–2Zr–2Mo–2Cr–0.15Si aided by extreme gradient boosting

Microstructural Variation and a Physical Mechanism Model for a Ti-55511 Alloy during Double-Stage Hot Deformation with Stepped Strain Rates in the β Region

Contact Info

Product

Resources

About