A machine learning accelerated distributed task management system (Malac-Distmas) and its application in high-throughput CALPHAD computation aiming at efficient alloy design

Gao, Jianbao; Zhong, Jue; Liu, Guangchen; Yang, Shenglan; Song, Bo; Zhang, Lijun; Liu, Zuming

doi:10.1016/j.apmate.2021.09.005

Cited by 17 publications

(10 citation statements)

References 75 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As discussed above, the quantitative relationship of "Composition -Process -Microstructure -Properties" of casting aluminum alloys can be established by combining CT and ML techniques to develop highperformance alloys efficiently. A nice example in the design of Sr-modified casting A356 alloys was reported very recently by the present authors [168,184] . First, a reliable thermodynamic database for the Al-rich Al-Si-Mg-Sr quaternary system was established, from which the quantitative relationship between the composition and microstructure of the A356-Sr system was constructed.…”

Section: Design Of Sr-modified Casting A356 Alloys Driven By Combining Ct and MLmentioning

confidence: 60%

“…To establish the self-consistent thermodynamic database of the Al-rich Al-Si-Mg-Sr quaternary system, all the thermodynamic parameters of six boundary binaries, i.e., Al-Si, Al-Mg, Al-Sr, Mg-Si, Mg-Sr, and Si-Sr were first unified. Subsequently, the thermodynamic parameters for the Al-Si-Sr and Al-Mg-Sr systems were reassessed using the CALPHAD method based on all critically reviewed experimental phase equilibria and thermodynamic property information [184] . Then, the thermodynamic database for the Al-Si-Mg-Sr quaternary system was established by combining the four ternary subsystems, and the phase equilibria/thermodynamic properties of the quaternary system were predicted via direct extrapolation from the ternary systems.…”

Section: Figure 14mentioning

confidence: 99%

See 1 more Smart Citation

Boosting for concept design of casting aluminum alloys driven by combining computational thermodynamics and machine learning techniques

Wang¹,

Liu²,

Gao³

et al. 2021

JMI

Self Cite

View full text Add to dashboard Cite

Casting aluminum alloys are commonly used in industries due to their excellent comprehensive performance. Alloying/microalloying and post-solidification heat treatments are the most common measures to tune the microstructure for enhancing their mechanical properties. However, it is very challenging to achieve accurate and efficient development of novel casting aluminum alloys using the traditional trial-and-error method. With the rapid development of computer technology, the computational thermodynamics (CT) in the framework of the CALculation of PHAse Diagram approach, the data-driven machine learning (ML) technique, and also their combinations have been proved to be effective approaches for the design of casting aluminum alloys. In this review, the state-of-the-art computational alloy design approaches driven by CT and ML techniques, as well as their combinations, were comprehensively summarized. The current status of the thermodynamic database for aluminum alloys, as the core for CT, was also briefly introduced. After that, a variety of successful case studies on the design of different casting aluminum alloys driven by CT, ML, and their combinations were demonstrated, including common applications, CT-driven design of Sc-additional Al-Si-Mg series casting alloys, and design of Srmodified A356 alloys driven by combing CT and ML. Finally, the conclusions of this review were drawn, and perspectives for boosting the computational design approach driven by combining CT and ML techniques were pointed out.

show abstract

Section: Design Of Sr-modified Casting A356 Alloys Driven By Combining Ct and MLmentioning

confidence: 60%

Section: Figure 14mentioning

confidence: 99%

Boosting for concept design of casting aluminum alloys driven by combining computational thermodynamics and machine learning techniques

Wang¹,

Liu²,

Gao³

et al. 2021

JMI

Self Cite

View full text Add to dashboard Cite

show abstract

“…Up to now, only about 10 groups of researchers have performed experimental measurement of phase equilibria of the binary Nb-Sn system [ 12 , 13 , 14 , 15 , 16 , 17 , 18 , 19 , 20 ]. Based on the limited experimental phase equilibrium information, Toffolon [ 18 ] performed a CALPHAD (CALculation of PHAse Diagram) [ 21 ] thermodynamic assessment of Nb-Sn system in 1998. During the assessment, Toffolon [ 18 ] adopted the conclusion of Massalski [ 17 ] and Shunk [ 22 ] that Nb 3 Sn would not be stable below 796 °C.…”

Section: Introductionmentioning

confidence: 99%

“…Up to now, only about 10 groups of researchers have performed experimental measurement of phase equilibria of the binary Nb-Sn system [12][13][14][15][16][17][18][19][20]. Based on the limited experimental phase equilibrium information, Toffolon [18] performed a CALPHAD (CALculation of PHAse Diagram) [21] thermodynamic assessment of Nb-Sn system in 1998. During the assessment, Toffolon [18] adopted the conclusion of Massalski [17] and Shunk [22] that Nb 3 Sn would not be stable below 796 • C. However, on account of the enthalpy of formation of Nb 3 Sn determined by drop calorimetry and other new literature data [13][14][15], it was believed that Nb 3 Sn can exist stably down to the room temperature.…”

Section: Introductionmentioning

confidence: 99%

Nb/Sn Liquid-Solid Reactive Diffusion Couples and Their Application to Determination of Phase Equilibria and Interdiffusion Coefficients of Nb-Sn Binary System

Zhang

Zhong

et al. 2021

Materials

Self Cite

View full text Add to dashboard Cite

Nb3Sn plays an irreplaceable role in superconducting parts due to its stable performance under high field conditions. Accurate phase equilibria and interdiffusion coefficients are of great significance for designing novel Nb3Sn superconductors. However, the related experimental information is still in a state of scarcity because of the difficulty in fabrication of Nb-Sn alloys caused by the large difference in melting points of Nb and Sn. In this paper, a simple but pragmatic approach was first proposed to prepare the Nb/Sn liquid-solid reactive diffusion couples (LSDCs) at 1100 °C and 1200 °C, of which the phase identification of the formed layer and the measurement of composition-distance profiles were conducted. The formed layer in Nb/Sn LSDCs was confirmed to be Nb3Sn compound. While the measured composition profiles were employed to determine the phase equilibria according to the local equilibrium hypothesis and the interdiffusion coefficients with an aid of the latest version of HitDIC software. The determined phase equilibria of Nb3Sn, (Nb) and liquid show good agreement with the assessed phase diagram. While the calculated interdiffusion coefficients and activation energy for diffusion in Nb3Sn are consistent with both experimental and theoretical data in the literature. Moreover, the growth of the formed Nb3Sn layer in Nb/Sn LSDCs was also found to be diffusion controlled. All the obtained phase equilibria and interdiffusion coefficients are of great value for further thermodynamic and kinetic modeling of the Nb-Sn system. Furthermore, it is anticipated that the presently proposed approach of fabricating liquid-solid reactive diffusion couple should serve as a general one for various alloy systems with large differences in melting points.

show abstract

“…Mylnikov presented the problem of production scheduling and production volume planning in relation to the projects' flow and characteristics (Mylnikov, 2021). Gao et al (2021) used machine learning to improve a task management system in designing high-performance materials as it requires high-throughput calculations and simulations. Machine learning was used to densify the output data, reducing the amount of calculation and accelerating high throughput calculations.…”

Section: Introductionmentioning

confidence: 99%

Smart work – production tasks management system

Chojnacki¹,

Walaszczyk²,

Markowska³

et al. 2021

Informatyka Ekonomiczna

View full text Add to dashboard Cite

The intensive development of Enterprise Resource Planning (ERP) is caused by huge competition on the production market and thus the need to optimize costs, efficiency and production time. However, the integration problem is still unresolved. One of the main Krzysztof Chojnacki, Ewa Walaszczyk, Aleksandra Markowska i in.problems is related to monitoring the realisation of production. In many ERP systems, this issue is very weakly performed. Data from different sub-systems are not fully integrated, therefore the process of decision-making is very difficult. The main purpose of the research described in this paper was to develop a prototype of a module for the settlement of production tasks in an integrated ERP-class system. The problems related to the module of the settlement of tasks of production workers, and online presentation of employee performance and machine condition was analysed.

show abstract

A machine learning accelerated distributed task management system (Malac-Distmas) and its application in high-throughput CALPHAD computation aiming at efficient alloy design

Cited by 17 publications

References 75 publications

Boosting for concept design of casting aluminum alloys driven by combining computational thermodynamics and machine learning techniques

Boosting for concept design of casting aluminum alloys driven by combining computational thermodynamics and machine learning techniques

Nb/Sn Liquid-Solid Reactive Diffusion Couples and Their Application to Determination of Phase Equilibria and Interdiffusion Coefficients of Nb-Sn Binary System

Smart work – production tasks management system

Contact Info

Product

Resources

About