Flux Weakening Control Method of Permanent Magnet Synchronous Motor-Based on Artificial Neural Network


The Problem:
Conventionally, an ECU uses standard control logic to match desired motor performance to actual motor performance. However, these conventional controls have limitations especially a higher RPMs of such a motor. A neural network is better able to meet the performance demands at these upper voltage and power limits by functioning as “intelligent” software in regulating these limits.

The Solution:
Researchers at The University of Alabama have developed an invention is a software scheme implemented on computer hardware to be used in an engine control unit (ECU). One practical benefit of this is that it can be fully parallelized due to its inherent parallel structure in order to be made compatible with the standard hardware interface for a conventional ECU. This neural network controller has been specifically designed for controlling an electric motor, but it is conceivable that it may adapted to have benefits for conventional combustion engines as well.

• Neural network controller can be fully parallelized due to its inherent parallel structure.
• Uses standard hardware interface- can make it compatible with conventional controller.
• A more rigorous system that an account for demands under strenuous load of a permanent magnet electric motor.

The University of Alabama Research Office of Innovation and Commercialization (OIC) is a non-profit corpo­ration that is responsible for commercializing University of Alabama technologies and for supporting University research. At OIC, we seek parties that are interested in learning more about our technologies and commercialization opportunities, and we welcome any inquiries you may have.



Contact Information

TTO Home Page: https://ua.technologypublisher.com

Name: Lynnette Scales

Title: Administrative Assistant

Department: Office for Innovation & Commercialization

Email: liscales@ua.edu

Phone: (205) 348-5433