Search

Predicting the phase precipitation of multicomponent alloys, especially the Ni-base superalloys, is a difficult task. In this work, we introduced a dependable and efficient way to establish the relationship between composition and detrimental phases in Ni-base superalloys, by integrating high throughput experiments and machine learning algorithms. 8371 sets of data about composition and phase information were obtained rapidly, and analyzed by machine learning to establish a high-confidence phase prediction model. Compared with the traditional methods, the proposed approach has remarkable advantage in acquiring and analyzing the experimental data, which can also be applied to other multicomponent alloys. IMPACT STATEMENT By integrating the high throughput experiments and machine learning algorithms, it is hopeful to facilitate the design of new Ni-base superalloys, and even other multicomponent alloys.

In this work, a diffusion multiple consist of Ni-base superalloys with complex compositions rather than simple metals or compounds is introduce, to discover the new Ni-base polycrystalline superalloys in combination with high strength and microstructure stability. Additionally, machine learning based image recognition has been use to characterize the microstructure, especially the γ′ precipitates. The microhardness is also utilized to rank the mechanical properties of Ni-base superalloys with different compositions. Thus, the composition, microstructure, and property are integrated by the high throughput experiment to discover novel superalloys, which can also be applied to discover other alloys with complex chemical components.

It becomes a common practice to adopt high-throughput experiments on superalloys, which can generate a large amount of data. To address this large amount of data, we designed a machine learning (ML) based model to automate the experimental analysis process. More specifically, we adopted the Unet algorithm to segment the precipitated phases from superalloy images and subsequently used a regression algorithm to predict the morphological parameters of the microstructure of the segmented precipitated phases according to their composition. The method proposed in this work may provide guidance for the future design of the superalloy composition.

DNA methylation is an important epigenetic marker that affects gene expression. Cell-free DNA methylation detection is a promising approach as abnormal distribution of DNA methylation is one of the hallmarks of many cancers and methylation changes occur early during carcinogenesis. This review summarizes the existing literature and reviews on the detection methods based on next generation sequencing for DNA methylation. The review also discusses the feasibility of detecting cfDNA methylation and the latest progress.

In this work, the high temperature creep properties of three newly developed P/M superalloys with fine grains were investigated under conditions of 650 °C/1100 MPa, 750 °C/690 MPa, and 815 °C/550 MPa. The creep behavior associated with microstructure were analyzed, considering the interactions of dislocation with grain boundaries and γ′ phase. The results indicated that the cracks were more likely to initiate at grain boundaries, resulting in intergranular cracking. Moreover, the dislocation movement in grains was strongly related with testing temperature and applied stress, which is explained by theoretical calculation on the composition-dependent critical stresses (CSs) to trigger various mechanisms, including dislocation shearing the γ′ phase by stacking faults (SFs) or APB coupled dislocation pairs, and dislocation climbing.

Knowledge of phase boundaries in multi-component system plays a critical role in exploring the alloy design space effectively and safely, which defines the roadmap to stabilize desirable phases and sidestep detrimental phases. In this work, a novel combinatorial approach was developed to determine the phase boundaries in multi-component nickel-based superalloys. In addition, a three-phase region was pinpointed and expected to enhance high-temperature properties. The results were further analyzed to evaluate the feasibility of CALPHAD and semi-empirical predictions, which provided clues for the improvement of the thermodynamic databases.

Oxides dispersion strengthened ferritic steels with bimodal-grains prepared by powder metallurgy (PM) have excellent strength-ductility synergy. However, the strengthening oxides can hardly be introduced into coarse grains by traditional PM methods, which limits the overall strength. In this work, to further enhance the mechanical property of PM ferritic steel, the face centered cubic e-Cu phase was precipitated in both fine and coarse grains via aging hardening, and its strengthening effects was evaluated.

Yield strength (YS) is a key factor during design and application of Ni-based superalloys with complex compositions, hence it is of great significance to evaluate the YS prior to manufacturing. In this work, alloy diffusion-multiple technology was employed as a high-throughput way to yield the hardness dataset. Based on the composition and other descriptors, Pearson correlation coefficients, stability selection and feature importance were used to select the efficient feature variables. Thereafter, six different machine learning models were applied to predict the YS. Finally, the individual and interaction effect of Co and Mo could be effectively detected by the Gaussian process regression (GPR) model. The optimum composition of Ni-based superalloys with the largest YS at room temperature was determined using the trained GPR model and genetic algorithm. This method can be extended to predict the YS in other multicomponent alloys, such as Ti alloys, Co-based alloys, and high entropy alloys.

The creep resistance of nickel-based superalloys at elevated temperature is inheritably correlated with interdiffusivity matrices, which are still difficult to be determined nowadays. In this work, the interdiffusion coefficient matrices of multicomponent nickel-based superalloys with seven alloying elements (i.e., Al, Ti, Cr, Co, Mo, Ta and W) at 1553 K were determined in a high-throughput way by employing the diffusion multiple technique and HitDIC software. The results showed that the main interdiffusion coefficients D ∼ A l A l N i and D ∼ W W N i over the investigated composition space were the highest and lowest, respectively. Moreover, it was found that Al + Ti is correlatedly accelerate the diffusion processes, while Mo + Ta + W has the tendency of decelerate the diffusion activities. Thereafter, the creep merit index of the concerned superalloys was evaluated using the measured interdiffusion coefficients, and the results showed the noticeable deviation from the experimental data in commercial superalloys. A great improvement can be then achieved by considering the effect of Re and Ru in the creep model. With the modified creep model, the composition of the superalloy with the optimal creep resistance can be finally chosen. It was proposed that increasing the contents of Ti, W and Mo to some extent may enhance the creep resistance of superalloys.