Page 21 - Read Online

Zhou et al. J Mater Inf 2022;2:18 https://dx.doi.org/10.20517/jmi.2022.27 Page 15 of 21

Figure 14. Relationships between ML, alloy design and AM.

methods. Zhou et al. developed a universal and simplified model to predict the energy density suitable for
L-PBF of various metallic materials, including Ti and Ti alloys, Al alloys, Ni-based superalloys and steel,
[118]
based on the relationship between energy absorption and consumption during L-PBF . The proposed
[118]
model was proven to be applicable to single-phase HEAs (e.g., FeCoCrNiMn) . Compared with the
calculation method, ML can describe the relationship between the descriptors and desired properties
without considering the complex physical metallurgy process of AM. More importantly, AM, as a tool for
[119]
high-throughput experimentation, can provide sufficient data for ML . Thus, ML has been widely used in
AM for defect detection and visualization, predicting printability, optimizing processing parameters, and so
on [120-122] . This method is especially important for exploring the optimal AM processing parameters of new
materials, which cannot be easily obtained through only experimental work. Figure 14 summarizes the
relationships among ML, alloy design and AM. Both ML and AM can accelerate the development of new
alloys. In addition, the optimal AM processing parameters for these newly developed alloys can be
potentially obtained using ML. The harmonious integration of ML, alloy design and AM is expected to
significantly speed up scientific advances and promote the industrial applications of these alloys.

SUMMARY AND OUTLOOK
The concept of HEAs based on multicomponent elements offers an opportunity to design attractive new
alloys with desirable properties. Furthermore, AM, as a unique processing method, can maximize the
capability of HEAs. In this review, we have carefully summarized the new trend in AM of multiphase HEAs
and some of the applications of ML used in this aspect. The introduction of second phases to HEAs
significantly improves their tensile properties. Among them, the L1 phase, which is generally coherent with
2
the surrounding FCC matrix, is thought to be the most effective reinforcement to improve the strength
without sacrificing ductility. Different strengthening and toughening mechanisms are also reviewed for the
as-printed multiphase HEAs, including dislocation strengthening, grain refining strengthening, solid