[16a-A33-1~11] FS.1 Focused Session "AI Electronics"

9:30 AM - 9:45 AM JST(12:30 AM - 12:45 AM UTC)Presentation by Applicant for JSAP Young Scientists Presentation AwardEnglish Presentation

[16a-A33-3] Online training of the energy harvester by using extreme learning machine

〇(M2C)Yuxiang Wen¹, Takeaki Yajima¹ (1.Kyushu Univ.)

Keywords:

Extreme Learning Machine,Machine Learning,AI

This research presents an innovative approach to power maximization for thermoelectric generators (TEG) utilizing an Extreme Learning Machine (ELM) and online training with Recursive Least Squares (RLS). The proposed system integrates a power management circuit capable of dynamically adjusting its switching frequency to optimize power output. The ELM is trained to predict the output power of the power management circuit, enabling us to control the switching frequency for maximizing output power. This method allows for the adaptive tuning of the circuit's behavior to the varying conditions of the environment, ensuring efficient energy harvesting.