High throughput experiment assisted discovery of new Ni-base superalloys

Wang, Zi; Zhang, Lina; Li, Weifu; Qin, Zijun; Wang, Zexin; Li, Zihang; Tan, Liming; Zhu, Lilong; Liu, Feng; Han, Hua; Jiang, Liang

doi:10.1016/j.scriptamat.2019.11.019

Cited by 45 publications

(6 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A high throughput method was applied to obtain adequate microstructural information. As a typical high throughput sample with gradient composition, multicomponent diffusion multiple (MCDM) was designed and employed to obtain a composition-dependent microstructure [21]. Taking W1-W3-W4 (designed as NiX-6W-6Mo) diffusion triple as an example to illustrate the steps for MCDM preparation and characterization, as shown in Figure 1a, the MCDM was obtained through assembling alloys with different compositions, as listed in Table 1, followed by electron-beam welding, hot isostatic pressing, and heat treatment.…”

Section: Methodsmentioning

confidence: 99%

Deep Transfer Learning for Ni-Based Superalloys Microstructure Recognition on γ′ Phase

Qin

et al. 2022

Materials

Self Cite

View full text Add to dashboard Cite

Ni-based superalloys are widely used to manufacture the critical hot-end components of aviation jet engines and various industrial gas turbines. The analysis of Ni-based superalloys microstructures is an important research task during the design and development of superalloys. The material microstructure information can only be understood by experts in the long history. Image segmentation and recognition are developing techniques for accelerating the microstructure analysis automatically. Although deep learning techniques have achieved satisfactory performance, they usually suffer from generalization, i.e., performing worse on a new dataset. In this paper, a deep transfer learning method which just needs a small number of labeled images is proposed to perform the microstructure recognition on γ′ phase. To evaluate the effectiveness, we homely prepare two Ni-based superalloys at temperatures 900 °C and 1000 °C, and manually annotate two datasets named as W-900 and W-1000. Experimental results demonstrate that the proposed method only needs 3 and 5 labeled images to achieve state-of-the-art segmentation accuracy during the transfer from W-900 to W-1000 and the transfer from W-1000 to W-900, while enjoying the advantage of fast convergence. In addition, a simple and effective software for the Ni-based superalloys microstructure recognition on γ′ phase is developed to improve the efficiency of materials experts, which will greatly facilitate the design of new Ni-base superalloys and even other multicomponent alloys.

show abstract

Section: Methodsmentioning

confidence: 99%

Deep Transfer Learning for Ni-Based Superalloys Microstructure Recognition on γ′ Phase

Qin

et al. 2022

Materials

Self Cite

View full text Add to dashboard Cite

show abstract

“…From these, Al35Cr35Mn8Mo5Ti17(at %) which was chosen for experimental validation presented the highest known Vickers hardness of 6.45 GPa (658 HV) for a material with a density below 5.5 g/cm 3 . Wang et al [36] also used thermodynamics modelling to design new Ni-base alloys in a fast throughput manner. The use of ML in this work focussed primarily on image recognition for the characterisation of the microstructure as opposed to modelling approach for materials design.…”

Section: Alloy Design Modellingmentioning

confidence: 99%

Machine learning for design, phase transformation and mechanical properties of alloys

Durodola

2022

Progress in Materials Science

View full text Add to dashboard Cite

“…On the other hand, thanks to the rapid improvement of computer technology in recent decades, atomic simulation methods have been widely used to explore the performance of Ni-based superalloys, for instance, first-principles, molecular dynamics (MD), Monte Carlo (MC), phase field crystal (PFC), and machine learning [ 17 , 18 , 19 , 20 , 21 ]. In these methods, MD simulation can provide an accurate representation of the demonstration of material deformation at the nanoscale.…”

Section: Introductionmentioning

confidence: 99%

Effect of Void Defects on the Indentation Behavior of Ni/Ni3Al Crystal

Yang

Sun

2023

Nanomaterials

View full text Add to dashboard Cite

Inconel 718 (IN 718) superalloys are widely used as engineering materials owing to their superior mechanical performance. And voids are unavoidable defects in IN 718 superalloy preparation, which dramatically affect the mechanical properties of IN 718 superalloys. In this work, the effects of void radius, distance from the top of the void to the substrate surface, and substrate temperature on the mechanical properties of the Ni/Ni3Al crystal are systematically investigated. It is shown that voids affect the formation of stair-rod dislocations and Shockley dislocations in the substrate, which in turn determines the mechanical properties. Thus, with the increase in void radius, Young’s modulus and hardness gradually decrease. With the increase in void distance, Young’s modulus and hardness increase and finally tend to be stable. In addition, the increase in substrate temperature leads to the interphase boundary becoming irregular and increases the defects in the γ and γ″ phases. As a result, Young’s modulus and hardness of the substrate decrease. This work aims to provide a guideline for investigating the indentation properties of Ni-based superalloys using MD.

show abstract

High throughput experiment assisted discovery of new Ni-base superalloys

Cited by 45 publications

References 27 publications

Deep Transfer Learning for Ni-Based Superalloys Microstructure Recognition on γ′ Phase

Deep Transfer Learning for Ni-Based Superalloys Microstructure Recognition on γ′ Phase

Machine learning for design, phase transformation and mechanical properties of alloys

Effect of Void Defects on the Indentation Behavior of Ni/Ni3Al Crystal

Contact Info

Product

Resources

About