Steady-State Error Reduction of Reinforcement Learning based Indirect Current Control of Permanent Magnet Synchronous Machines

Tobias Schindler, Lara Broghammer, Dennis Hufnagel, Nina Diringer, Benedikt Hofmann, Armin Dietz, Petros Karamanakos, Ralph Kennel

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Deep reinforcement learning (DRL) can achieve favorable dynamic performance compared to conventional control methods. However, steady-state errors are often present. This paper investigates the reduction of steady-state error in DRL-based current control of permanent magnet synchronous machines (PMSMs) by augmenting the integrated tracking error to the observation vector. More specifically, this paper assesses the performance of a DRL-based method under nominal and adverse operating conditions by considering PMSMs with linear and nonlinear magnetic circuits, which exhibit saturation, cross-coupling, and spatial harmonics. The latter include parameter mismatches between the training model and the physical system and misalignment of the dq-frame with respect to the identified position of the d-axis. As shown with the presented experimental results, the DRL-based control method can successfully operate the drive system under all operating conditions, with the steady-state and dynamic performance being similar to that of field-oriented control.

Original languageEnglish
Title of host publicationInternational Exhibition and Conference for Power Electronics, Intelligent Motion, Renewable Energy and Energy Management, PCIM Europe 2024
PublisherMesago PCIM GmbH
Pages140-149
Number of pages10
ISBN (Electronic)9783800762620
DOIs
StatePublished - 2024
Event2024 International Exhibition and Conference for Power Electronics, Intelligent Motion, Renewable Energy and Energy Management, PCIM Europe 2024 - Nuremberg, Germany
Duration: 11 Jun 202413 Jun 2024

Publication series

NamePCIM Europe Conference Proceedings
Volume2024-June
ISSN (Electronic)2191-3358

Conference

Conference2024 International Exhibition and Conference for Power Electronics, Intelligent Motion, Renewable Energy and Energy Management, PCIM Europe 2024
Country/TerritoryGermany
CityNuremberg
Period11/06/2413/06/24

Fingerprint

Dive into the research topics of 'Steady-State Error Reduction of Reinforcement Learning based Indirect Current Control of Permanent Magnet Synchronous Machines'. Together they form a unique fingerprint.

Cite this