Deep neural networks for quick and precise geometry optimization of segmented thermoelectric generators

Chika Maduabuchi, Chibuoke Eneh, Abdulrahman Abdullah Alrobaian, Mohammad Alkhedher

Abstract: Highlights•AI driven geometry optimization of STEG thermo-mechanical performance using DNN.•3D FEM considers 16 STEG geometry parameters that were previously neglected.•AI fixes shortcomings of conventional FEM method in optimizing STEG performance.•DNN forecasted device performance in just 10s, 2880 times faster than FEM.•Optimized STEG is 78% more efficient than conventional STEG, reduces failure by 73%.

External IDs:doi:10.1016/j.energy.2022.125889