PE-GPT: A Physics-Informed Interactive Large Language Model for Power Converter Modulation Design

TL;DR

PE-GPT is a specialized large language model that leverages physics-informed neural networks to assist in power converter modulation design through interactive text-based guidance, validated by practical experiments.

Contribution

This work introduces PE-GPT, the first physics-informed large language model tailored for power converter modulation design, integrating in-context learning and neural networks for practical guidance.

Findings

PE-GPT effectively guides power converter modulation design.

Hardware experiments validate PE-GPT's recommendations.

Enhanced accessibility and explainability in power electronics design.

Abstract

This paper proposes PE-GPT, a custom-tailored large language model uniquely adapted for power converter modulation design. By harnessing in-context learning and specialized tiered physics-informed neural networks, PE-GPT guides users through text-based dialogues, recommending actionable modulation parameters. The effectiveness of PE-GPT is validated through a practical design case involving dual active bridge converters, supported by hardware experimentation. This research underscores the transformative potential of large language models in power converter modulation design, offering enhanced accessibility, explainability, and efficiency, thereby setting a new paradigm in the field.