PMSM MTPA-Control with Reinforcement Learning and CO2 Burden
Paper in proceeding, 2023

Electric machinery often needs to be accurately controlled for efficiency. Maximum Torque per Ampere (MTPA) approach gives rapid & precise control, while assuring the efficiency. To incorporate the MTPA approach, look-up tables (LuT) are populated based on physical principles, synthesizing current combinations in the D-Q plane. Especially for embedded systems like encountered in vehicles, parsing data from densely populated tensors like the LuT is rather resource intensive, which reflects itself in the CO 2 emissions. In this approach supervised learning will be used to devise a regression based surrogate model for LuT by means of Neural Networks (NN). Subsequently, principles of Reinforcement Learning (SARSA) based MTPA control will also be developped in an effort to reduce the training data needs. It will be shown that, the RL based approach provides a valid method for motor control. Finally, a CO 2e emission comparison for chosen approaches will also be reported.

embedded systems

CO2budget

Reinforcement Learning

AC motor

Machine Learning

MTPA

Neural networks

PMSM

Control Strategy

Author

Raik Orbay

Chalmers, Electrical Engineering, Electric Power Engineering

Volvo Car Corporation

Yijie Ren

Volvo Car Corporation

Joachim Härsjö

Volvo Car Corporation

Lukasz Sobieraj

Volvo Car Corporation

Martin Fabian

Chalmers, Electrical Engineering, Systems and control

Torbjörn Thiringer

Chalmers, Electrical Engineering, Electric Power Engineering

International Conference on Control, Automation and Systems

15987833 (ISSN)

1209-1214
978-89-93215-27-4 (ISBN)

International Conference on Control, Automation and Systems, ICCAS 2023
Yeosu, South Korea,

Driving Forces

Sustainable development

Areas of Advance

Transport

Energy

Subject Categories

Control Engineering

DOI

10.23919/ICCAS59377.2023.10316988

More information

Latest update

1/25/2024