Improvement of PMSM Control Using Reinforcement Learning Deep Deterministic Policy Gradient Agent

ABSTRACT:

PMSM Control Based on the advantage of using the reinforcement learning on process control, provided by the fact that it is not necessary to know the exact mathematical model and the structure of its uncertainties, this article approaches the possibility of improving the performances of the Permanent Magnet Synchronous Motor (PMSM) control system based on the Field Oriented Control (FOC) type control strategy

DDPG

By using the correction signals provided by a trained reinforcement learning agent, which will be added to the control signals ud, uq, and iqref . The type of reinforcement learning used is the Deep Deterministic Policy Gradient (DDPG). The combination possibilities of these control structures are presented, and their superiority over the FOC type control strategy is validated by numerical simulations.

KEYWORDS:

  1. Permanent magnet motors
  2. Field oriented control
  3. Reinforcement learning
  4. Intelligent agent
  5. Deep neural networks

SOFTWARE: MATLAB/SIMULINK

BLOCK DIAGRAM:

Fig. 1. Block diagram for FOC-type control of the PMSM based on reinforcement learning.

EXPECTED SIMULATION RESULTS:

Fig. 2. Time evolution for the numerical simulation of the PMSM control system based on the FOC-type strategy.

Fig. 3. Time evolution for the numerical simulation of the PMSM control system based on TD3 agent for the correction of udref and uqref .

Fig. 4. Time evolution for the numerical simulation of the PMSM control system based on TD3 agent for the correction of iqref.

Fig. 5. Time evolution for the numerical simulation of the PMSM control system based on TD3 agent for the correction of udref, uqref and iqref.

CONCLUSION:

PMSM Control This article presents the FOC-type control structure of a PMSM, which is improved in terms of performance by using a reinforcement learning technique. Thus, the comparative results are presented for the case where the reinforcement learning agent is properly trained and provides correction signals that will be added to the control signals ud, uq, and iqref.

PMSM

PMSM Control Numerical simulations are used to demonstrate the superiority of the control system that uses the reinforcement learning, and the following papers will study the possibilities for optimization in terms of the implementation of the reinforcement learning in the PMSM control.           

REFERENCES:

[1] B. Wu and M. Narimani, Control of Synchronous Motor Drives, in High-Power Converters and AC Drives , Wiley-IEEE Press, 2017, pp.353-391.

[2] B. K. Bose, Modern power electronics and AC drives, Prentice Hall, Knoxville, Tennessee, USA, 2002.

[3] H. Wang and J. Leng, “Summary on development of permanent magnet synchronous motor,” Chinese Control And Decision Conference (CCDC), Shenyang, China, 2018, pp. 689-693.

[4] Z. Liu, Y. Li, and Z. Zheng, “A review of drive techniques for multiphase machines,” in CES Transactions on Electrical Machines and Systems, vol. 2, pp. 243-251, June 2018.

[5] S. Sakunthala, R. Kiranmayi, and P. N. Mandadi, “A Review on Speed Control of Permanent Magnet Synchronous Motor Drive Using Different Control Techniques,”International Conference on Power, Energy, Control and Transmission Systems (ICPECTS), Chennai, China , 2018, pp. 97-102.

Leave a Reply

Your email address will not be published.