Evaluation of Ti–Mn Alloys for Additive Manufacturing Using High-Throughput Experimental Assays and Gaussian Process Regression

Abstract

Compositionally graded cylinders of Ti–Mn alloys were produced using the Laser Engineered Net Shaping (LENS™) technique, with Mn content varying from 0 to 12 wt.% along the cylinder axis. The cylinders were subjected to different post-build heat treatments to produce a large sample library of a–b microstructures. The microstructures in the sample library were studied using back-scattered electron (BSE) imaging in a scanning electron microscope (SEM), and their mechanical properties were evaluated using spherical indentation stress–strain protocols. These protocols revealed that the microstructures exhibited features with averaged chord lengths in the range of 0.17–1.78 mm, and beta content in the range of 20–83 vol.%. The estimated values of the Young’s moduli and tensile yield strengths from spherical indentation were found to vary in the ranges of 97–130 GPa and 828–1864 MPa, respectively. The combined use of the LENS technique along with the spherical indentation protocols was found to facilitate the rapid exploration of material and process spaces. Analyses of the correlations between the process conditions, several key microstructural features, and the measured material properties were performed via Gaussian process regression (GPR). These data-driven statistical models provided valuable insights into the underlying correlations between these variables.

A review on high-throughput development of high-entropy alloys by combinatorial methods

“…This mixture forms a compositional gradient in the laser scan plane when the powder bed is deposited. Thus, a horizontal compositional gradient forms rather than the typical vertical gradients achieved in DED combinatorial studies [168][169][170] . Wen et al used CoCrFe medium entropy alloy and Inconel 718 as the feedstock powders to prove this new technique's concept.…”

Machine Learning in Chemical Product Engineering: The State of the Art and a Guide for Newcomers

“…As such, one of the great advantages of this method is its rigorous treatment of uncertainty, which helps in avoiding overfitting problems [177]. Its inherent preference to smooth functions is an additional factor that increases its generalization capacity, as fitting artifacts are avoided [176].…”

“…Consequently, GPs are employed in numerous applications, in addition to typical regression problems, such as surrogate model identification, dynamic experimental design and manifold learning-based modeling [177][178][179]. On the other hand, a major drawback in the application of GPs is their high computational demands when dealing with large data sets [10,177,180].…”

“…Consequently, GPs are employed in numerous applications, in addition to typical regression problems, such as surrogate model identification, dynamic experimental design and manifold learning-based modeling [177][178][179]. On the other hand, a major drawback in the application of GPs is their high computational demands when dealing with large data sets [10,177,180]. In fact, as the implementation of the method requires the continuous manipulation of the covariance matrix, whose size is directly proportional to the size of the data set, the computational cost increases.…”

Empowering Materials Processing and Performance from Data and AI

“…Gong et al [ 2 ] explored the material behavior of additive Ti-Mn samples, produced via the Laser Engineered Net Shaping (LENS™) technique and subsequent post-build heat treatment. In this work, novel cost-effective high-throughput experimental assays have been proposed and the feasibility of employing Gaussian process regression (GPR) for in-depth statistical analysis of these data has been shown.…”