Saved in:
Bibliographic Details
Main Authors: Colombo, Alessandro, Busetto, Riccardo, Breschi, Valentina, Forgione, Marco, Piga, Dario, Formentin, Simone
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.00673
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909560674975744
author Colombo, Alessandro
Busetto, Riccardo
Breschi, Valentina
Forgione, Marco
Piga, Dario
Formentin, Simone
author_facet Colombo, Alessandro
Busetto, Riccardo
Breschi, Valentina
Forgione, Marco
Piga, Dario
Formentin, Simone
contents Accurate speed estimation in sensorless brushless DC motors is essential for high-performance control and monitoring, yet conventional model-based approaches struggle with system nonlinearities and parameter uncertainties. In this work, we propose an in-context learning framework leveraging transformer-based models to perform zero-shot speed estimation using only electrical measurements. By training the filter offline on simulated motor trajectories, we enable real-time inference on unseen real motors without retraining, eliminating the need for explicit system identification while retaining adaptability to varying operating conditions. Experimental results demonstrate that our method outperforms traditional Kalman filter-based estimators, especially in low-speed regimes that are crucial during motor startup.
format Preprint
id arxiv_https___arxiv_org_abs_2504_00673
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle In-Context Learning for Zero-Shot Speed Estimation of BLDC motors
Colombo, Alessandro
Busetto, Riccardo
Breschi, Valentina
Forgione, Marco
Piga, Dario
Formentin, Simone
Systems and Control
Robotics
Accurate speed estimation in sensorless brushless DC motors is essential for high-performance control and monitoring, yet conventional model-based approaches struggle with system nonlinearities and parameter uncertainties. In this work, we propose an in-context learning framework leveraging transformer-based models to perform zero-shot speed estimation using only electrical measurements. By training the filter offline on simulated motor trajectories, we enable real-time inference on unseen real motors without retraining, eliminating the need for explicit system identification while retaining adaptability to varying operating conditions. Experimental results demonstrate that our method outperforms traditional Kalman filter-based estimators, especially in low-speed regimes that are crucial during motor startup.
title In-Context Learning for Zero-Shot Speed Estimation of BLDC motors
topic Systems and Control
Robotics
url https://arxiv.org/abs/2504.00673