Development of new materials for electrothermal metals using data driven and machine learning.

After adopting a combined approach of data-driven methods and machine learning, the prediction of material performance and the optimization of composition design can significantly reduce the development time of materials at a lower cost. In this research, we employed four machine learning algorithms, including linear regression, ridge regression, support vector regression, and backpropagation neural networks, to develop predictive models for the electrical performance data of titanium alloys. Our focus was on two key objectives: resistivity and the temperature coefficient of resistance (TCR). Subsequently, leveraging the results of feature selection, we conducted an analysis to discern the impact of alloying elements on these two electrical properties.The prediction results indicate that for the resistivity data prediction task, the radial basis function kernel-based support vector machine model performs the best, with a correlation coefficient above 0.995 and a percentage error within 2%, demonstrating high predictive capability. For the TCR data prediction task, the best-performing model is a backpropagation neural network with two hidden layers, also with a correlation coefficient above 0.995 and a percentage error within 3%, demonstrating good generalization ability. The feature selection results using random forest and Xgboost indicate that Al and Zr have a significant positive effect on resistivity, while Al, Zr, and V have a significant negative effect on TCR. The conclusion of the composition optimization design suggests that to achieve both high resistivity and TCR, it is recommended to set the Al content in the range of 1.5% to 2% and the Zr content in the range of 2.5% to 3%.

Effects of Temperature and Pressure of Hot Isostatic Pressing on the Grain Structure of Powder Metallurgy Superalloy.

The microstructure with homogeneously distributed grains and less prior particle boundary (PPB) precipitates is always desired for powder metallurgy superalloys after hot isostatic pressing (HIPping). In this work, we studied the effects of HIPping parameters, temperature and pressure on the grain structure in PM superalloy FGH96, by means of scanning electron microscope (SEM), electron backscatter diffraction (EBSD), transmission electron microscope (TEM) and Time-of-flight secondary ion spectrometry (ToF-SIMS). It was found that temperature and pressure played different roles in controlling PPB precipitation and grain structure during HIPping, the tendency of grain coarsening under high temperature could be inhibited by increasing HIPping pressure which facilitates the recrystallization. In general, relatively high temperature and pressure of HIPping were preferred to obtain an as-HIPped superalloy FGH96 with diminished PPB precipitation and homogeneously refined grains.

Strain Amount Dependent Grain Size and Orientation Developments during Hot Compression of a Polycrystalline Nickel Based Superalloy.

Controlling grain size in polycrystalline nickel base superalloy is vital for obtaining required mechanical properties. Typically, a uniform and fine grain size is required throughout forging process to realize the superplastic deformation. Strain amount occupied a dominant position in manipulating the dynamic recrystallization (DRX) process and regulating the grain size of the alloy during hot forging. In this article, the high-throughput double cone specimen was introduced to yield wide-range strain in a single sample. Continuous variations of effective strain ranging from 0.23 to 1.65 across the whole sample were achieved after reaching a height reduction of 70%. Grain size is measured to be decreased from the edge to the center of specimen with increase of effective strain. Small misorientation tended to generate near the grain boundaries, which was manifested as piled-up dislocation in micromechanics. After the dislocation density reached a critical value, DRX progress would be initiated at higher deformation region, leading to the refinement of grain size. During this process, the transformations from low angle grain boundaries (LAGBs) to high angle grain boundaries (HAGBs) and from subgrains to DRX grains are found to occur. After the accomplishment of DRX progress, the neonatal grains are presented as having similar orientation inside the grain boundary.