Predicting DC-Link Capacitor Current Ripple in AC-DC Rectifier Circuits Using Fine-Tuned Large Language Models

TL;DR

This paper demonstrates how fine-tuned large language models can predict DC-link capacitor ripple currents in AC-DC rectifiers using minimal hardware data, aiding in component degradation monitoring and extending to other nonlinear power electronics applications.

Contribution

It introduces a novel application of fine-tuned LLMs for predicting capacitor ripple currents in power converters using minimal measurements, enabling non-invasive health monitoring.

Findings

LLMs can predict ripple currents with near-accuracy using limited data

The approach reduces the need for extensive sensors in power electronics

Framework can be extended to estimate ESR and other nonlinear functions

Abstract

Foundational Large Language Models (LLMs) such as GPT-3.5-turbo allow users to refine the model based on newer information, known as ``fine-tuning''. This paper leverages this ability to analyze AC-DC converter behaviors, focusing on the ripple current in DC-link capacitors. Capacitors degrade faster under high ripple currents, complicating life monitoring and necessitating preemptive replacements. Using minimal invasive noisy hardware measurements from a full bridge rectifier and 90W Power Factor Correction (PFC) boost converter, an LLM-based models to predict ripple content in DC-link currents was developed which demonstrated the LLMs' ability for near-accurate predictions. This study also highlights data requirements for precise nonlinear power electronic circuit parameter predictions to predict component degradation without any additional sensors. Furthermore, the proposed framework could be extended to any non-linear function mapping problem as well as estimating the capacitor Equivalent Series Resistance (ESR).