This work aims to contribute to studies on the geometric optimization of thermoelectric generators through a combination of the reduced variables technique and supervised machine learning. The architecture of the thermoelectric generators studied, one conventional and the other segmented, was determined by calculating the cross-sectional area and length of the legs, and applying reduced variables approximation. With the help of a supervised machine learning algorithm, the values of the thermoelectric properties were predicted, as were those of the maximum electrical power for the other temperature values. This characteristic was an advantage that allowed us to obtain approximate results for the electrical power, adjusting the design of the when experimental values were not known. The proposed method also made it possible to determine the optimal values of various parameters of the legs, which were the ratio of the cross-sectional areas , the length of the legs , and the space between the legs . Aspects such as temperature-dependent thermoelectric properties (Seebeck coefficient, electrical resistivity, and thermal conductivity) and the metallic bridge that connects the legs were considered in the calculations for the design of the , obtaining more realistic models. In the training phase, the algorithm received the parameter and an operating temperature value as input data, to predict the corresponding value of the maximum power produced. This calculation was performed for conventional and segmented systems. Recent advances have opened up the possibility of applying an algorithm for designing conventional and segmented thermocouples based on the reduced variables approach and incorporating a supervised machine learning computational technique.
This chapter explores the impact of nanofluids – specifically TiO2, Fe3O4, Al2O3, and graphene – on heat transfer and thermoelectric power generation within a rectangular heat exchanger featuring internal winglets and an integrated thermoelectric generator. The use of both internal winglets and nanofluids aims to enhance convective heat transfer by modifying fluid flow and improving thermal properties. The study evaluates fluid dynamics and temperature distribution on the hot and cold sides of the thermoelectric system, focusing on five winglet geometries: semicircular, fishbone, rectangular, trapezoidal, and triangular. Results demonstrate that the Al2O3 nanofluid achieves a temperature differential approximately 1 °C higher than the alternatives, resulting in a 3% increase in average power output. Furthermore, the implementation of Al2O3 in combination with semicircular winglets enhances thermoelectric power generation by 10.68% compared to configurations using distilled water without winglets, due to the increased effective heat transfer area and the superior thermal properties of Al2O3.