@inproceedings{d6d17b6a8a274528a7b3e23b9363ec95,
title = "Data-Driven Predictive Speed Control and Disturbance Rejection for IPMSM",
abstract = "Interior permanent magnet synchronous machines (IPMSMs) are extensively used for EV applications owing to their high power and torque density with low maintenance requirements. Classical Field-oriented Control (FOC) approaches, while providing reliable control, are heavily dependent on accurate system models and motor parameters. This work proposes an Offset-free data-driven predictive speed control strategy for IPMSMs. Based on behavioral systems theory, the method leverages persistently exciting input-output data from a blackbox system model to predict future trajectories without requiring an explicit model. Offline simulations validate the effectiveness of the proposed approach, while the results of real-time Controller-Hardware-in-the-Loop (CHIL) experiments confirm the practical feasibility in practical drive applications.",
keywords = "Data-driven control, Data-driven Predictive Control (DeePC), Disturbance rejection, EV, IPMSM, Model Predictive Control, Speed Control",
author = "Sarbajit Basu and Patrick Johnson and Luis Herrera",
note = "Publisher Copyright: {\textcopyright} 2026 IEEE.; 2026 IEEE Transportation Electrification Conference and Expo and Electric Aircraft Technologies Symposium, ITEC+EATS 2026 ; Conference date: 10-06-2026 Through 12-06-2026",
year = "2026",
doi = "10.1109/ITECEATS66641.2026.11592826",
language = "English",
series = "2026 IEEE Transportation Electrification Conference and Expo and Electric Aircraft Technologies Symposium, ITEC+EATS 2026",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2026 IEEE Transportation Electrification Conference and Expo and Electric Aircraft Technologies Symposium, ITEC+EATS 2026",
address = "United States",
}