Deep Learning-Based Hardness Prediction of Novel Refractory High-Entropy Alloys with Experimental Validation

Abstract

Hardness is an essential property in the design of refractory high entropy alloys (RHEAs). This study shows how a neural network (NN) model can be used to predict the hardness of a RHEA, for the first time. We predicted the hardness of several alloys, including the novel C0.1Cr3Mo11.9Nb20Re15Ta30W20 using the NN model. The hardness predicted from the NN model was consistent with the available experimental results. The NN model prediction of C0.1Cr3Mo11.9Nb20Re15Ta30W20 was verified by experimentally synthesizing and investigating its microstructure properties and hardness. This model provides an alternative route to determine the Vickers hardness of RHEAs.

Magnetic properties, electrical resistivity, and hardness of high-entropy alloys FeCoNiPd and FeCoNiPt

“…The result of refractory bcc HEAs with VEC:4.14∼5.65 is also shown [46,47,48,49,50] and seems to be connected to the guideline. In addition, a deep learning study of the hardness of refractory HEAs with the VEC: 4∼6 also supports the positive correlation between the hardness and VEC in that VEC range [51]. The VEC of FeCoNiPd or FeCoNiPt is 9.25, and the hardness of 188 HV obtained at 4.9030 N load is employed because the hardness at a higher load is usually employed.…”

Bio-high entropy alloys: Progress, challenges, and opportunities

“…The research mainly focuses on machine learning to accurately predict the strength and hardness properties of new alloys and to guide the design of alloy compositions based on the property prediction results. Klimenko ( Klimenko et al, 2021 ) and Bhandari ( Bhandari et al, 2021 ) et al developed support vector machine and random forest machine learning models for accurate prediction of yielding of HEAs with an accuracy of more than 95% based on a sample of high-entropy alloy data with characteristic parameters such as composition, modulus, density, mixing entropy, and atomic radius difference of HEAs as inputs. Several well-known machine learning models, including a radial basis function kernel (svr.…”

Superconductivity and hardness of the equiatomic high-entropy alloy HfMoNbTiZr

“…The hardness of bcc HEA superconductors tends to increase with increasing VEC, and the plot might be connected to the guideline, indicating the universal relation between the VEC and the hardness. In addition, a deep learning study of the hardness of refractory HEAs with the VEC ranging from 4 to 6 also indicates that the hardness increases as the VEC is increased [65]. In Figure 8(b), the dotted line represents the VEC dependence of T c for typical quinary bcc HEA superconductors, which are mostly non-equiatomic.…”