Development of Microstructure Simulation System in SIP-Materials Integration Projects

Koyama, Toshiyuki; Ohno, Munekazu; Yamanaka, Akinori; Kasuya, Tadashi; Tsukamoto, Shiro

doi:10.2320/matertrans.mt-ma2020001

Cited by 13 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The module was built as part of the Cross-ministerial Strategic Innovation Promotion Program (SIP) project on materials integration (MI) 41 . It consists of the microstructure prediction at different conditions using phase-field simulation 55 for simulated microstructure image analysis, which includes γ′ size (the mean diameter of a circle of equal projection area for γ′-precipitate) as well as volume fraction and the performance prediction (i.e., 0.2% proof stress) 19 , 56 , as schematically shown in Fig. 3 .…”

Section: Methodsmentioning

confidence: 99%

Artificial intelligence inspired design of non-isothermal aging for γ–γ′ two-phase, Ni–Al alloys

Nandal

Dieb

Bulgarevich

et al. 2023

Sci Rep

Self Cite

View full text Add to dashboard Cite

In this paper, a state-of-the-art Artificial Intelligence (AI) technique is used for a precipitation hardening of Ni-based alloy to predict more flexible non-isothermal aging (NIA) and to examine the possible routes for the enhancement in strength that may be practically achieved. Additionally, AI is used to integrate with Materials Integration by Network Technology, which is a computational workflow utilized to model the microstructure evolution and evaluate the 0.2% proof stress for isothermal aging and NIA. As a result, it is possible to find enhanced 0.2% proof stress for NIA for a fixed time of 10 min compared to the isothermal aging benchmark. The entire search space for aging scheduling was ~ 3 billion. Out of 1620 NIA schedules, we succeeded in designing the 110 NIA schedules that outperformed the isothermal aging benchmark. Interestingly, it is found that early-stage high-temperature aging for a shorter time increases the γ′ precipitate size up to the critical size and later aging at lower temperature increases the γ′ fraction with no anomalous change in γ′ size. Therefore, employing this essence from AI, we designed an optimum aging route in which we attained an outperformed 0.2% proof stress to AI-designed NIA routes.

show abstract

Section: Methodsmentioning

confidence: 99%

Artificial intelligence inspired design of non-isothermal aging for γ–γ′ two-phase, Ni–Al alloys

Nandal

Dieb

Bulgarevich

et al. 2023

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…This will be reported separately [18]. The workflow is implemented on the MInt system [19][20] developed in the SIP project [20][21][22][23][24][25][26][27][28][29][30][31][32][33], and can be executed via an application programming interface and the calculation results can be retrieved. In this study, we substituted each step of this workflow using two Bayesian statistical models via the HAZ geometry and constructed a prediction model (tandem Bayesian model) that links the two models in a Bayesian manner.…”

Section: Development Of a Tandem Bayesian Modelmentioning

confidence: 99%

Search for high-creep-strength welding conditions considering HAZ shape factors

IZUNO,

Demura,

Yamazaki

et al. 2023

Preprint

View full text Add to dashboard Cite

The creep rupture life of ferritic heat-resistant steel weld joints is limited by Type IV cracking that occurs in the heat-affected zone (HAZ), whose shape affects creep damage accumulation. In this study, we address the inverse problem of extending the creep rupture life of weld joints by controlling HAZ shape via welding conditions. As reported separately, we have developed a workflow that predicts weld joint creep rupture life from the predicted HAZ shape from welding conditions, and have implemented it in the material design system. Using this workflow, we presented a tandem Bayesian model for predicting the creep rupture life from welding conditions via the geometric features of HAZ shapes (HAZ shape factors), which are considered to determine the creep rupture life. The prediction model of a HAZ shape factor from welding conditions was formed by Gaussian process regression. The prediction model of the creep rupture life was formed by Bayesian linear regression. These models were probabilistically connected by Bayesian statistical mathematics. An algorithm to increase the creep rupture life was developed to search for welding conditions. This method was applied to a 2 1/4Cr–1Mo heat-resistant steel weld joint simulated with a plate I-bevel three-layer gas tungsten arc welding. The number of welding conditions combination reaches 78 = 5764801. Start from 49 initial HAZ shape factors and 22 creep rupture life data, we performed forward calculations of 20 rupture lives to find welding conditions that can improve the creep rupture life by 12% over the initial data.

show abstract

Search for high-creep-strength welding conditions considering HAZ shape factors for 2 1/4Cr–1Mo steel

Izuno,

Demura,

Yamazaki

et al. 2024

Weld World

View full text Add to dashboard Cite

The creep rupture life of ferritic heat-resistant steel weld joints is limited by Type IV cracking that occurs in the heat-affected zone (HAZ), whose shape affects creep damage accumulation. In this study, we address the inverse problem of extending the creep rupture life of weld joints by controlling HAZ shape via welding conditions. As reported separately, we have developed a workflow that predicts weld joint creep rupture life from the predicted HAZ shape from welding conditions and have implemented it in the material design system. Using this workflow, we presented a tandem Bayesian model for predicting the creep rupture life from welding conditions via the geometric features of HAZ shapes (HAZ shape factors), which are considered to determine the creep rupture life. The prediction model of a HAZ shape factor from welding conditions was formed by Gaussian process regression. The prediction model of the creep rupture life was formed by Bayesian linear regression. These models were probabilistically connected by Bayesian statistical mathematics. An algorithm to increase the creep rupture life was developed to search for welding conditions. This method was applied to a 2 1/4Cr–1Mo heat-resistant steel weld joint simulated with a plate I-bevel three-layer gas tungsten arc welding. The number of welding conditions combination reaches $${7}^{8}=5764801$$ 7 8 = 5764801 . Start from 49 initial HAZ shape factors and 22 creep rupture life data, we performed forward calculations of 20 rupture lives to find welding conditions that can improve the creep rupture life by 12% over the initial data.

show abstract

Development of Microstructure Simulation System in SIP-Materials Integration Projects

Cited by 13 publications

References 8 publications

Artificial intelligence inspired design of non-isothermal aging for γ–γ′ two-phase, Ni–Al alloys

Artificial intelligence inspired design of non-isothermal aging for γ–γ′ two-phase, Ni–Al alloys

Search for high-creep-strength welding conditions considering HAZ shape factors

Search for high-creep-strength welding conditions considering HAZ shape factors for 2 1/4Cr–1Mo steel

Contact Info

Product

Resources

About