To achieve an effective design of additively manufacturable Ni superalloys with decent service performance, a hybrid computational design model has been developed, where the strategy to tailor local elemental segregations was integrated within a scheme of minimizing the cracking susceptibility. More specifically, the phase boundary of primary NbC / γ matrix was introduced into the design routine to tune the spatial distribution of critical solutes at an atomic scale, thereby inhibiting the formation of borides and segregation-induced cracking. Based on the output of the design, new grades of Ni superalloy have been developed with excellent additive manufacturability, as confirmed by the robustness of printing parameters in fabricating low-defect-density samples. The capability of the phase boundaries to evenly distribute boron atoms was validated experimentally, and the cracking induced by uncontrolled boron segregation at grain boundaries was effectively prevented. The newly designed alloys showed good tensile properties and decent oxidation resistance at different service temperatures, which are comparable to those of conventionally produced superalloys. The finding that phase boundaries can be employed to prevent undesirable clustering of boron atoms can be extended to manipulate the distributions of other critical elements, which provides a new path for designing novel Ni superalloys with balanced printability and mechanical properties.

In this research a machine learning model for predicting the rotating bending fatigue strength and the high-throughput design of fatigue resistant steels is proposed. In this transfer prediction framework, machine learning models are first trained to estimate tensile properties (yield strength, tensile strength and elongation) on the basis of composition and critical process conditions. Then, based on the predicted tensile properties, transfer models are trained to estimate fatigue strength. The results are compared with those of a similar model not having such a transfer layer. The transfer prediction framework shows high accuracy for fatigue strength prediction with a remarkably high tolerance to limitations in the amount of calibration data available for training. By combining the transfer prediction framework with evolutionary algorithms, a robust high-throughput alloy design model is achieved requiring only tens of fatigue data points to get a decent reliability. The newly designed steel showed the predicted high fatigue strength. The method as presented here might also be applicable to other alloy design challenges in which only a limited database for the property to be optimized is available.

Herein, the effect of Nb content on the phase transformation kinetics, microstructure, and mechanical properties of hot-rolled quenching and partitioning (Q&P) steel is investigated. The characteristics of three C–Mn–Si–Ti steels (0.18C, 2.0Si, 2.6Mn, and 0.015Ti) containing 0, 0.027, or 0.061 wt% Nb are compared. Results reveal that grain boundary pinning by precipitates and Nb solute drag effects refine the austenite grain size during the hot-rolling process; the microstructural refinement is carried over to the final microstructure subjected to the Q&P treatment. The remaining supersaturated Nb suppresses the bainite formation and decreases the final bainite fraction formed in the Q&P process. The microstructural evolution leads to an increase in the ultimate tensile strength (UTS) of the steel containing 0.027 wt% Nb from 1169 to 1228 MPa, while keeping the total elongation at 18%. When the Nb content is increased to 0.061 wt%, the UTS of the steel increases to 1313 MPa, but the elongation at break drops to 16%. The effect is due to the carbon consumption by the Nb precipitates, which causes a decrease in the stability of the retained austenite and reduces the strain hardening at high strain levels.

We present an electron backscattered diffraction (EBSD)-trained deep learning (DL) method integrating traditional material characterization informatics and artificial intelligence for a more accurate classification and quantification of complex microstructures using only regular scanning electron microscope (SEM) images. In this method, EBSD analysis is applied to produce accurate ground truth data for guiding the DL model training. An U-Net architecture is used to establish the correlation between SEM input images and EBSD ground truth data using only small experimental datasets. The proposed method is successfully applied to two engineering steels with complex microstructures, i.e., a dual-phase (DP) steel and a quenching and partitioning (Q&P) steel, to segment different phases and quantify phase content and grain size. Alternatively, once properly trained the method can also produce quasi-EBSD maps by inputting regular SEM images. The good generality of the trained models is demonstrated by using DP and Q&P steels not associated with the model training. Finally, the method is applied to SEM images with various states, i.e., different imaging modes, image qualities and magnifications, demonstrating its good robustness and strong application ability. Furthermore, the visualization of feature maps during the segmenting process is utilised to explain the mechanism of this method's good performance.

With the development of the materials genome philosophy and data mining methodologies, machine learning (ML) has been widely applied for discovering new materials in various systems including high-end steels with improved performance. Although recently, some attempts have been made to incorporate physical features in the ML process, its effects have not been demonstrated and systematically analysed nor experimentally validated with prototype alloys. To address this issue, a physical metallurgy (PM) -guided ML model was developed, wherein intermediate parameters were generated based on original inputs and PM principles, e.g., equilibrium volume fraction (V_f) and driving force (D_f) for precipitation, and these were added to the original dataset vectors as extra dimensions to participate in and guide the ML process. As a result, the ML process becomes more robust when dealing with small datasets by improving the data quality and enriching data information. Therefore, a new material design method is proposed combining PM-guided ML regression, ML classifier and a genetic algorithm (GA). The model was successfully applied to the design of advanced ultrahigh-strength stainless steels using only a small database extracted from the literature. The proposed prototype alloy with a leaner chemistry but better mechanical properties has been produced experimentally and an excellent agreement was obtained for the predicted optimal parameter settings and the final properties. In addition, the present work also clearly demonstrated that implementation of PM parameters can improve the design accuracy and efficiency by eliminating intermediate solutions not obeying PM principles in the ML process. Furthermore, various important factors influencing the generalizability of the ML model are discussed in detail.