Date of Graduation

5-2025

Document Type

Thesis

Degree Name

Master of Science in Electrical Engineering (MSEE)

Degree Level

Graduate

Department

Electrical Engineering and Computer Science

Advisor/Mentor

McCann, Roy A.

Committee Member

Balda, Juan C.

Second Committee Member

Wu, Jingxian

Keywords

AC Motor; Genetic Algorithm; Machine Learning; PID

Abstract

The most common control method that is utilized by all industries across the world is the proportional-integrative-derivative controller (PID) due the relatively low cost and complexity of the system. However, there are draw-backs with PIDs, it is not adaptative to a changing system, so it works on nominal systems, and it starts breaking down when a system begins to have a non-linear response. The method chosen to overcome both is the utilization of machine learning with the use of genetic algorithms.

This method allows any PID system to be capable of adapting in real-time, while not adding significant additional cost and not requiring specialized equipment. In this paper a PMSM AC motor was set-up with a simplistic calculation on settling time, % overshoot and % error programmed in Python with PyTorch. With MATLAB being utilized to plot the results and provide additional analysis. The purpose of this is not to generate a 1-1 realistic motor but to demonstrate that if a system is able to output settling time, error, and overshoot parameters the algorithm attempts to drive it down to 0 while outputting the up-to-date PID values.

Download

Share

COinS