Learning and Current Prediction of PMSM Drive via Differential Neural Networks

TL;DR

This paper introduces a differential neural network approach to model and predict the current trajectories of PMSMs, demonstrating high accuracy and robustness under various conditions, with potential applications in multiple fields.

Contribution

The study presents a novel differential neural network method specifically designed for modeling and predicting PMSM dynamics, enhancing accuracy and robustness over existing techniques.

Findings

Effective reconstruction of PMSM dynamics under disturbances

Strong short-term and long-term prediction performance

Robustness demonstrated across different load conditions

Abstract

Learning models for dynamical systems in continuous time is significant for understanding complex phenomena and making accurate predictions. This study presents a novel approach utilizing differential neural networks (DNNs) to model nonlinear systems, specifically permanent magnet synchronous motors (PMSMs), and to predict their current trajectories. The efficacy of our approach is validated through experiments conducted under various load disturbances and no-load conditions. The results demonstrate that our method effectively and accurately reconstructs the original systems, showcasing strong short-term and long-term prediction capabilities and robustness. This study provides valuable insights into learning the inherent dynamics of complex dynamical data and holds potential for further applications in fields such as weather forecasting, robotics, and collective behavior analysis.