Simulation of a closed-loop dc-dc converter using a physics-informed neural network-based model

TL;DR

This paper introduces a physics-informed neural network model, specifically a BiLSTM-PINN, for fast and accurate simulation of a closed-loop dc-dc converter's time-domain response, outperforming traditional neural network models.

Contribution

The paper presents a novel BiLSTM-PINN model for power electronics simulation, demonstrating superior accuracy and consistency over existing neural network approaches.

Findings

BiLSTM-PINN outperforms FCNN by over 9 times in median RMSE.

BiLSTM-PINN has 2.6 times lower standard deviation than FCNN.

The proposed model is a promising alternative for power electronics simulation.

Abstract

The growing reliance on power electronics introduces new challenges requiring detailed time-domain analyses with fast and accurate circuit simulation tools. Currently, commercial time-domain simulation software are mainly relying on physics-based methods to simulate power electronics. Recent work showed that data-driven and physics-informed learning methods can increase simulation speed with limited compromise on accuracy, but many challenges remain before deployment in commercial tools can be possible. In this paper, we propose a physics-informed bidirectional long-short term memory neural network (BiLSTM-PINN) model to simulate the time-domain response of a closed-loop dc-dc boost converter for various operating points, parameters, and perturbations. A physics-informed fully-connected neural network (FCNN) and a BiLSTM are also trained to establish a comparison. The three methods are then compared using step-response tests to assess their performance and limitations in terms of accuracy. The results show that the BiLSTM-PINN and BiLSTM models outperform the FCNN model by more than 9 and 4.5 times, respectively, in terms of median RMSE. Their standard deviation values are more than 2.6 and 1.7 smaller than the FCNN's, making them also more consistent. Those results illustrate that the proposed BiLSTM-PINN is a potential alternative to other physics-based or data-driven methods for power electronics simulations.