Optimal Weighting Factors Design for Model Predictive Current Controller for Enhanced Dynamic Performance of PMSM Employing Deep Reinforcement Learning

This paper presents a novel control strategy employing a deep reinforcement learning (DRL) scheme for online selection of optimal weighting factors in cost functions of the finite control set model predictive current controller of a permanent magnet synchronous motor (PMSM). Indeed, when designing p...

Full description

Saved in:
Bibliographic Details
Main Authors: Muhammad Usama, Amine Salaje, Thomas Chevet, Nicolas Langlois
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/11/5874
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850128883271073792
author Muhammad Usama
Amine Salaje
Thomas Chevet
Nicolas Langlois
author_facet Muhammad Usama
Amine Salaje
Thomas Chevet
Nicolas Langlois
author_sort Muhammad Usama
collection DOAJ
description This paper presents a novel control strategy employing a deep reinforcement learning (DRL) scheme for online selection of optimal weighting factors in cost functions of the finite control set model predictive current controller of a permanent magnet synchronous motor (PMSM). Indeed, when designing predictive controllers for PMSMs’ phase currents, competing objectives appear, such as managing current convergence and switching transitions. These objectives result in an asymmetric cost function where they have to be balanced through weighting factors in order to enhance the inverter and motor performance. Leveraging the twin delayed deep deterministic policy gradient algorithm, the optimal weighting factor selection policy is obtained for online balancing of the choice between current deviation in the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>d</mi><mi>q</mi></mrow></semantics></math></inline-formula> frame and inverter commutations. For comparison, a metaheuristic-based artificial neural network is trained on static data obtained through a multi-objective genetic algorithm to predict the weights. The key performance markers, such as torque ripple, total harmonic distortion, switching frequency, steady-state, and dynamic performance, are provided through numerical simulations to verify the effectiveness of the proposed tuning scheme. The results of these simulations confirm that the proposed dynamic control scheme effectively resolves the challenges of weighting factor choice, meeting inverter performance requirements, and delivering better dynamic and steady-state performance.
format Article
id doaj-art-b0fcee898eb0489997e5e1356cbc5017
institution OA Journals
issn 2076-3417
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-b0fcee898eb0489997e5e1356cbc50172025-08-20T02:33:09ZengMDPI AGApplied Sciences2076-34172025-05-011511587410.3390/app15115874Optimal Weighting Factors Design for Model Predictive Current Controller for Enhanced Dynamic Performance of PMSM Employing Deep Reinforcement LearningMuhammad Usama0Amine Salaje1Thomas Chevet2Nicolas Langlois3ESIGELEC, IRSEEM, Université de Rouen Normandie, 76000 Rouen, FranceESIGELEC, IRSEEM, Université de Rouen Normandie, 76000 Rouen, FranceESIGELEC, IRSEEM, Université de Rouen Normandie, 76000 Rouen, FranceESIGELEC, IRSEEM, Université de Rouen Normandie, 76000 Rouen, FranceThis paper presents a novel control strategy employing a deep reinforcement learning (DRL) scheme for online selection of optimal weighting factors in cost functions of the finite control set model predictive current controller of a permanent magnet synchronous motor (PMSM). Indeed, when designing predictive controllers for PMSMs’ phase currents, competing objectives appear, such as managing current convergence and switching transitions. These objectives result in an asymmetric cost function where they have to be balanced through weighting factors in order to enhance the inverter and motor performance. Leveraging the twin delayed deep deterministic policy gradient algorithm, the optimal weighting factor selection policy is obtained for online balancing of the choice between current deviation in the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>d</mi><mi>q</mi></mrow></semantics></math></inline-formula> frame and inverter commutations. For comparison, a metaheuristic-based artificial neural network is trained on static data obtained through a multi-objective genetic algorithm to predict the weights. The key performance markers, such as torque ripple, total harmonic distortion, switching frequency, steady-state, and dynamic performance, are provided through numerical simulations to verify the effectiveness of the proposed tuning scheme. The results of these simulations confirm that the proposed dynamic control scheme effectively resolves the challenges of weighting factor choice, meeting inverter performance requirements, and delivering better dynamic and steady-state performance.https://www.mdpi.com/2076-3417/15/11/5874permanent magnet synchronous motorinverter performancemodel predictive current controlasymmetric cost functiondeep reinforcement learningmulti-objective optimization
spellingShingle Muhammad Usama
Amine Salaje
Thomas Chevet
Nicolas Langlois
Optimal Weighting Factors Design for Model Predictive Current Controller for Enhanced Dynamic Performance of PMSM Employing Deep Reinforcement Learning
Applied Sciences
permanent magnet synchronous motor
inverter performance
model predictive current control
asymmetric cost function
deep reinforcement learning
multi-objective optimization
title Optimal Weighting Factors Design for Model Predictive Current Controller for Enhanced Dynamic Performance of PMSM Employing Deep Reinforcement Learning
title_full Optimal Weighting Factors Design for Model Predictive Current Controller for Enhanced Dynamic Performance of PMSM Employing Deep Reinforcement Learning
title_fullStr Optimal Weighting Factors Design for Model Predictive Current Controller for Enhanced Dynamic Performance of PMSM Employing Deep Reinforcement Learning
title_full_unstemmed Optimal Weighting Factors Design for Model Predictive Current Controller for Enhanced Dynamic Performance of PMSM Employing Deep Reinforcement Learning
title_short Optimal Weighting Factors Design for Model Predictive Current Controller for Enhanced Dynamic Performance of PMSM Employing Deep Reinforcement Learning
title_sort optimal weighting factors design for model predictive current controller for enhanced dynamic performance of pmsm employing deep reinforcement learning
topic permanent magnet synchronous motor
inverter performance
model predictive current control
asymmetric cost function
deep reinforcement learning
multi-objective optimization
url https://www.mdpi.com/2076-3417/15/11/5874
work_keys_str_mv AT muhammadusama optimalweightingfactorsdesignformodelpredictivecurrentcontrollerforenhanceddynamicperformanceofpmsmemployingdeepreinforcementlearning
AT aminesalaje optimalweightingfactorsdesignformodelpredictivecurrentcontrollerforenhanceddynamicperformanceofpmsmemployingdeepreinforcementlearning
AT thomaschevet optimalweightingfactorsdesignformodelpredictivecurrentcontrollerforenhanceddynamicperformanceofpmsmemployingdeepreinforcementlearning
AT nicolaslanglois optimalweightingfactorsdesignformodelpredictivecurrentcontrollerforenhanceddynamicperformanceofpmsmemployingdeepreinforcementlearning