Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

A Study on Aero-Engine Direct Thrust Control with Nonlinear Model Predictive Control Based on Deep Neural Network

A Study on Aero-Engine Direct Thrust Control with Nonlinear Model Predictive Control Based on... For enhancing engine response ability, a novel nonlinear model predictive control (NMPC) method for aero-engine direct thrust control is proposed. The control objective of the proposed method is the thrust instead of the measurable parameters. The online-sliding window deep neural network (OL-SW-DNN) is proposed as predictive model. The OL-SW-DNN adopts deep-learning structure to increase the model accuracy and selects the nearest point data of certain length as training data which will reduce the sensitivity for the noise of training data. The direct thrust simulations of the popular NMPC based on extended Kalman filler (EKF) and the proposed one are conducted, respectively. The simulations demonstrate that compared with the popular NMPC, the proposed NMPC decreases the acceleration time by 0.425 s and increases response speed about 1.14 times. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png International Journal of Aeronautical & Space Sciences Springer Journals

A Study on Aero-Engine Direct Thrust Control with Nonlinear Model Predictive Control Based on Deep Neural Network

Loading next page...
 
/lp/springer-journals/a-study-on-aero-engine-direct-thrust-control-with-nonlinear-model-tifNyBXcrK

References (26)

Publisher
Springer Journals
Copyright
Copyright © 2019 by The Korean Society for Aeronautical & Space Sciences
Subject
Engineering; Aerospace Technology and Astronautics; Fluid- and Aerodynamics
ISSN
2093-274X
eISSN
2093-2480
DOI
10.1007/s42405-019-00191-4
Publisher site
See Article on Publisher Site

Abstract

For enhancing engine response ability, a novel nonlinear model predictive control (NMPC) method for aero-engine direct thrust control is proposed. The control objective of the proposed method is the thrust instead of the measurable parameters. The online-sliding window deep neural network (OL-SW-DNN) is proposed as predictive model. The OL-SW-DNN adopts deep-learning structure to increase the model accuracy and selects the nearest point data of certain length as training data which will reduce the sensitivity for the noise of training data. The direct thrust simulations of the popular NMPC based on extended Kalman filler (EKF) and the proposed one are conducted, respectively. The simulations demonstrate that compared with the popular NMPC, the proposed NMPC decreases the acceleration time by 0.425 s and increases response speed about 1.14 times.

Journal

International Journal of Aeronautical & Space SciencesSpringer Journals

Published: Jul 3, 2019

There are no references for this article.