Fe–Al–Si Thermoelectric (FAST) Materials and Modules: Diffusion Couple and Machine-Learning-Assisted Materials Development

To lower the introduction and maintenance costs of autonomous power supplies for driving Internet-of-things (IoT) devices, we have developed low-cost Fe–Al–Si-based thermoelectric (FAST) materials generation modules. Our development approach combines computational science, experiments, mapping measurements, machine learning (ML). FAST a good balance mechanical properties excellent chemical stability, superior to that conventional Bi–Te-based materials. However, it remains challenging enhance factor (PF) thermal conductivity develop reliable devices. This forum paper describes current status based on experiments ML with limited data, together module fabrication related view commercialization. Combining bulk combinatorial methods diffusion couple measurements could accelerate search PF We report prediction is powerful tool finding unexpected off-stoichiometric compositions Fe–Al–Si system dopant concentrations fourth element PF, i.e., Co substitution Fe atoms in