Thermoelectric maximum power point tracking by artificial neural networks

When thermoelectric generators can be used to convert heat into power, the efficiency of this process is low. The efficiency with which TEGs convert energy is improved via a new method called maximum power point tracking (MPPT). This study aims to examine the possibility of utilizing an artificial neural network (ANN) to monitor the amount of data that can be stored in PowerPoint. The neural network is trained using the error backpropagation method. One of the benefits of using a neural network is its speed and accuracy while tracking the Maximum PowerPoint. In order to test the suggested MPPT technique, MATLAB/SIMULINK software was used to simulate the TEG mode's performance. MPPT was developed and used to regulate SEPIC converter switching technology. The temperature is used as an input variable in this technique. Under a variety of temperature conditions, the proposed methodology for studying dynamic responses to track the TEG system's maximum power point and power generated. We found that the intelligent technique's output has high tracking speed, tracking accuracy, and minimized oscillation around the maximum power point (MPP).

Automated summary

This study explores the use of an artificial neural network (ANN) to monitor the efficiency of thermoelectric generators (TEGs) through maximum power point tracking (MPPT) method.