Control of matrix converters using machine learning
Abstract
A method of controlling a matrix converter system is provided. The method includes receiving an operating condition and consulting a trained Q-data structure for reward values associated with respective switching states of the switching matrix for an operating state that corresponds to the operating condition. The Q-data structure is trained using Q-learning to map a reward value predicted for respective switching states to respective discrete operating states. The method further includes sorting the reward values predicted for the respective switching states mapped to the operating state that corresponds to the operating condition, selecting a subset of the set of the mappings as a function of a result of sorting the reward values associated with the switching states of the operating state, evaluating each switching state included in the subset, and selecting an optimal switching state for the operating condition based on a result of evaluating the switching states of the subset.
- Inventors:
- Issue Date:
- Research Org.:
- Hamilton Sundstrand Corporation, Charlotte, NC (United States)
- Sponsoring Org.:
- USDOE Advanced Research Projects Agency - Energy (ARPA-E)
- OSTI Identifier:
- 2222182
- Patent Number(s):
- 11733680
- Application Number:
- 16/826,635
- Assignee:
- Hamilton Sundstrand Corporation (Charlotte, NC)
- Patent Classifications (CPCs):
-
G - PHYSICS G05 - CONTROLLING G05B - CONTROL OR REGULATING SYSTEMS IN GENERAL
G - PHYSICS G06 - COMPUTING G06N - COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
- DOE Contract Number:
- AR00000891; FOA-1727-1510
- Resource Type:
- Patent
- Resource Relation:
- Patent File Date: 03/23/2020
- Country of Publication:
- United States
- Language:
- English
Citation Formats
Chamie, Mahmoud El, and Blasko, Vladimir. Control of matrix converters using machine learning. United States: N. p., 2023.
Web.
Chamie, Mahmoud El, & Blasko, Vladimir. Control of matrix converters using machine learning. United States.
Chamie, Mahmoud El, and Blasko, Vladimir. Tue .
"Control of matrix converters using machine learning". United States. https://www.osti.gov/servlets/purl/2222182.
@article{osti_2222182,
title = {Control of matrix converters using machine learning},
author = {Chamie, Mahmoud El and Blasko, Vladimir},
abstractNote = {A method of controlling a matrix converter system is provided. The method includes receiving an operating condition and consulting a trained Q-data structure for reward values associated with respective switching states of the switching matrix for an operating state that corresponds to the operating condition. The Q-data structure is trained using Q-learning to map a reward value predicted for respective switching states to respective discrete operating states. The method further includes sorting the reward values predicted for the respective switching states mapped to the operating state that corresponds to the operating condition, selecting a subset of the set of the mappings as a function of a result of sorting the reward values associated with the switching states of the operating state, evaluating each switching state included in the subset, and selecting an optimal switching state for the operating condition based on a result of evaluating the switching states of the subset.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2023},
month = {8}
}
Save to My Library
You must Sign In or Create an Account in order to save documents to your library.
Works referenced in this record:
Predictive voltage control of direct matrix converter with reduced number of sensors for the renewable energy and microgrid applications
conference, October 2017
- Zhang, Jianwei; Li, Li; Malekjamshidi, Zahra
- 2017 IEEE Energy Conversion Congress and Exposition (ECCE)
Matrix converter operation in current control mode with regulation of output voltage vector
patent, March 2020
- Blasko, Vladimir
- US Patent Document 10,587,214
Model Predictive Control for Matrix Converter Operating in Current Control Mode with Load Current Estimation
patent-application, October 2020
- Blasko, Vladimir
- US Patent Application 16/381947; 20200328709
Matrix converter system with current control mode operation
patent, June 2019
- Blasko, Vladimir
- US Patent Document 10,320,306
Improved Sensorless Vector Control for Induction Motor Drives Fed by a Matrix Converter Using Nonlinear Modeling and Disturbance Observer
journal, March 2006
- Lee, K. -B.; Blaabjerg, F.
- IEEE Transactions on Energy Conversion, Vol. 21, Issue 1
Model predictive control for matrix converter operating in current control mode with load current estimation
patent, March 2022
- Blasko, Vladimir
- US Patent Document 11,290,023
Model predictive control optimization for power electronics
patent, October 2019
- Blasko, Vladimir
- US Patent Document 10,459,472
Model predictive control optimization for power electronics
patent-application, June 2017
- Blasko, Vladimir
- US Patent Application 14/961030; 20170160760
Matrix converter operating in current control mode using feed forward signals
patent, March 2020
- Blasko, Vladimir
- US Patent Document 10,594,227
Method and apparatus for improved reward-based learning using adaptive distance metrics
patent, March 2016
- Tesauro, Gerald J.; Weinberger, Kilian Quirin
- US Patent Document 9,298,172