Machine-Learning-Assisted Development and Theoretical Consideration for the Al₂Fe₃Si₃ Thermoelectric Material

Abstract

Chemical composition alteration is a general strategy to optimize the thermoelectric properties of a thermoelectric material to achieve high-efficiency conversion of waste heat into electricity. Recent studies show that the Al 2 Fe 3 Si 3 intermetallic compound with a relatively high power factor of ∼700 μW m −1 K −2 at 400 K is promising for applications in low-cost and nontoxic thermoelectric devices. To accelerate the exploration of the thermoelectric properties of this material in a mid-temperature range and to enhance its power factor, a machine-learning method was employed herein to assist the synthesis of off-stoichiometric samples (namely, Al 23.5+x Fe 36.5 Si 40−x ) of the Al 2 Fe 3 Si 3 compound by tuning the Al/Si ratio. The optimal Al/Si ratio for a high power factor in the mid-temperature range was found rapidly and efficiently, and the optimal ratio of the sample at x = 0.9 was found to increase the power factor at ∼510 K by about 40% with respect to that of the initial sample at x = 0.0. The possible mechanism for the enhanced power factor is discussed in terms of the precipitations of the metallic secondary phases in the Al 23.5+x Fe 36.5 Si 40−x samples. Furthermore, the maximum achievable thermal conductivity of Al 2 Fe 3 Si 3 estimated by the Slack model is ∼10 W m −1 K −1 at the Debye temperature. An avoided-crossing behavior of the acoustic and the low-lying optical modes along several crystallographic directions is found in the phonon dispersion of Al 2 Fe 3 Si 3 calculated by ab initio density functional theory method. These preliminary results suggest that Al 2 Fe 3 Si 3 can have a low thermal conductivity. The calculated formation energies of point defects suggest that the antisite defects between Al and Si are likely to cause the Al and Si off-stoichiometries in Al 2 Fe 3 Si 3 . The theoretically obtained insight provides additional information for the further understanding of Al 2 Fe 3 Si 3 .

Active learning for the power factor prediction in diamond-like thermoelectric materials

“…Active learning workflow A classic active learning strategy, Bayesian optimization, has been used many times to find materials with breakthrough properties. These works prove the effectiveness of active learning 20,21 . However, models in Bayesian optimization are limited to the probabilistic regression ones, excluding many other ML methods that also have outstanding performance, such as Support Vector Regression (SVR) 22 .…”

A Critical Review of Machine Learning of Energy Materials

“…Recent evidence shows that the PF can be improved by controlling the conduction type of Al 2 Fe 3 Si 3 , which is further dictated by the ratio of Al/Si. Hou et al have employed a GPR model to predict PF for unknown compositions from existing experimental data. The input features were composition x in Al 23.5+ x Fe 36.5 Si 40− x and temperature.…”

Machine learning approaches to identify and design low thermal conductivity oxides for thermoelectric applications

“…Oliynyk et al (2016) found that electron count of B and difference in the atomic sizes of A and B are the most influential parameters in AB 2 C type of compounds using random forest ML algorithm. Hou et al (2019) used ML-based methods to optimize the Al/Si ratio in off-stochiometric Al 23.5+x Fe 36.5 Si 40Àx compounds for achieving highest power factor. Miller et al (2017) used high-throughput computations to screen 735 oxide materials for their thermoelectric properties and identified SnO as a potential n-type TE material.…”