Doctoral Dissertations


“This research investigates the application of adaptive dynamic programming (ADP) methods for the current control of switched reluctance motors (SRM). Since the traditional current controllers have large current ripples that increase torque ripples and acoustic noise, optimal tracking controllers using reinforcement learning (RL) approaches are introduced as an alternative adaptive technique for SRM drives. The proposed optimal tracking controllers can minimize current ripples and cope with uncertainties within the inductance profile of the SRM. The work is composed of three papers. In the first paper, a novel Q-learning scheduling method for the current controller of a switched reluctance motor (SRM) drive is presented. This paper introduces a new scheduled Q-learning algorithm that utilizes a table of Q-cores that lie on the nonlinear surface of an SRM model to track the reference current trajectory by scheduling the infinite horizon linear quadratic trackers (LQT) handled by Q-learning algorithms. Additionally, a linear interpolation algorithm is proposed to improve and ensure a smooth transition between the trained Q-cores of the LQT. In the second paper, an actor-critic structure based RL method has been implemented to learn and track the current reference by finding the optimal solution for the nonlinear tracking Hamilton Jacobi-Bellman (HJB) equation. Two neural networks (NNs) were trained online separately to provide the optimal phase voltage to achieve tracking performance for the current. In the third paper, a robust switching H-infinity controller for tracking the current of SRM is introduced. This controller is equipped with a linear interpolation algorithm as well to provide a smooth switching between H matrices”--Abstract, page iv.


Shamsi, Pourya
Ferdowsi, Mehdi

Committee Member(s)

Bo, Rui
Huang, Jie
Sherizadeh, Taghi


Electrical and Computer Engineering

Degree Name

Ph. D. in Electrical Engineering


The author would like to thank the Saudi Arabian Cultural Mission (SACM) for providing financial assistance.


Missouri University of Science and Technology

Publication Date

Spring 2021

Journal article titles appearing in thesis/dissertation

  • Optimal tracking current control of switched reluctance motor drives using reinforcement Q-learning scheduling
  • Reinforcement actor-critic structure for tracking current control of switched reluctance motor drive
  • Switching optimal tracking h-infinity current control of switched reluctance motor drive


xii, 106 pages

Note about bibliography

Includes bibliographic references.


© 2021 Hamad Alharkan, All rights reserved.

Document Type

Dissertation - Open Access

File Type




Thesis Number

T 11995