AC drive control design with reinforcement learning techniques
38 viewsDOI:
https://doi.org/10.54939/1859-1043.j.mst.97.2024.33-40Keywords:
Reinforcement Learning; Actor-Critic; Induction Motor; Agent; DDPG.Abstract
Three-phase induction motors (IM) are widely known in industrial applications for their low cost and minimal maintenance. Control of AC induction motors based on Field-Oriented Control (FOC) and vector control with classic PID control laws are reliable techniques commonly used in industry. However, due to the nonlinear nature of electric machines and their susceptibility to external disturbances or parameter variations, conventional controllers often struggle to meet control requirements. Reinforcement Learning (RL) is an online learning technique, model-free, capable of handling parameter variations. These characteristics make reinforcement learning a potential candidate, acting as an adaptive controller that can replace conventional controllers.
This article proposes the design of a control system for three-phase induction motor drives based on reinforcement learning techniques. The proposed controller utilizes a reinforcement learning agent with the DDPG algorithm to replace the PI controllers of the current loop circuit in conventional FOC control. The performance of the controller has been validated under various operating conditions through computer simulations in MATLAB/SIMULINK
References
[1]. Kushwaha, Ashish and Gopal, Madan, “Reinforcement learning-based controller for field-oriented control of induction machine”, Soft Computing for Problem Solving, pp. 737—749, (2019).
[2]. Ayesha, Attaullah Y. Memon “Reinforcement Learning Based Field Oriented Control Of An Induction Motor” 2022 Third International Conference on Latest trends in Electrical Engineering and Computing Technologies, IEEE, pp. 315-343, (2022). DOI: 10.1109/INTELLECT55495.2022.9969403
[3]. S. A. A. Rizvi and Z. Lin, ”Output Feedback Optimal Tracking Control Using Reinforcement Q-Learning” 2018 Annual American Control Conference (ACC), pp. 3423-3428, (2018), doi: 10.23919/ACC.2018.8430997
[4]. Bhagat, Sarthak and Banerjee, Hritwick and Ren, Hongliang, “Deep Reinforcement Learning for Soft Robotic Applications: Brief Overview with Impending Challenges”, Preprints, (2018).
[5]. T. Pajchrowski , P. Siwek , and A. Wójcik, “Adaptive controller design for electric drive with variable parameters by Reinforcement Learning method” Bulletin of the Polish Academy of Sciences Technical Sciences, Vol. 68, No. 5, (2020). DOI: 10.24425/bpasts.2020.XXXX
[6]. C HUNHUA L IU, K. T. C HAU, C HRISTOPHER H. T. L EE, Z AIXIN S ONG, “Critical Review of Advanced Electric Machines and Control Strategies for Electric Vehicles” Proceedings of the IEEE | Vol. 109, no. 6, (2021).
[7]. Krishnan, R., “Electric Motor Drives: Modeling, Analysis, and Control”, Prentice Hall, (2001).
[8]. O’Rourke, Colm J. and Qasim, Mohammad M. and Overlin, Matthew R.and Kirtley, James L., “A Geometric Interpretation of Reference Frames and Transformations: dq0, Clarke, and Park”, IEEE Transactions on Energy Conversion, pp. 2070-2083, (2019).
[9]. Rushikesh Kamalapurkar • Patrick Walters Joel Rosenfeld • Warren Dixon “Reinforcement Learning for Optimal Feedback Control” Springer, (2018).
[10]. Memon, A.Y., “Sensorless Speed Control of Induction Motors Using Sliding Mode Control Strategy”, Michigan State University. Department of Electrical and Computer Engineering, (2004).
[11]. Chan, Tze Fun and Shi, Keli, “Applied intelligent control of induction motor drives”, John Wiley & Sons, (2011).
[12]. Bose, B.K., “Modern Power Electronics and AC Drives”, Prentice Hall PTR, (2002).