Fast real-time SDRE controllers using neural networks

被引：6

作者：

Costa, Romulo Fernandes da ^{[1
]}

Saotome, Osamu ^{[2
]}

Rafikova, Elvira ^{[3
]}

Machado, Renato ^{[4
]}

机构：

[1] Aeronaut Inst Technol ITA, Grad Program Elect & Comp Engn Elect Devices & Sy, Elect Engn Div, 50 Praca Marechal Eduardo Gomes, BR-12228900 Sao Jose Dos Campos, SP, Brazil

[2] Aeronaut Inst Technol ITA, Dept Appl Elect, Elect Engn Div, 50 Praca Marechal Eduardo Gomes, BR-12228900 Sao Jose Dos Campos, SP, Brazil

[3] Fed Univ ABC UFABC, Engn Modeling & Appl Social Sci Ctr, 5001 Ave Estados, BR-09210580 Santo Andre, SP, Brazil

[4] Aeronaut Inst Technol ITA, Dept Telecommun, Elect Engn Div, 50 Praca Marechal Eduardo Gomes, BR-12228900 Sao Jose Dos Campos, SP, Brazil

来源：

ISA TRANSACTIONS | 2021年 / 118卷

关键词：

SDRE control; Deep learning; Neural control; Stacked denoising autoencoders; Satellite attitude control; FEEDFORWARD NETWORKS;

D O I：

10.1016/j.isatra.2021.02.019

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper describes the implementation of fast state-dependent Riccati equation (SDRE) control algorithms through the use of shallow and deep artificial neural networks (ANN). Several ANNs are trained to replicate an SDRE controller developed for a satellite attitude dynamics simulator (SADS) to display the technique's efficacy. The neural controllers have reduced computational complexity compared with the original SDRE controller, allowing its execution at a significantly higher rate. One of the neural controllers was validated using the SADS in a practical experiment. The experimental results indicate that the training error is sufficiently small for the neural controller to perform equivalently to the original SDRE controller. (c) 2021 ISA. Published by Elsevier Ltd. All rights reserved.

引用

页码：133 / 143

页数：11

共 50 条

[1] Real-time flood forecasting using neural networks
Thirumalaiah, K.
Deo, M.C.
[J]. Computer-Aided Civil and Infrastructure Engineering, 1998, 13 (02): : 101 - 111
[2] Real-time excitation controller using neural networks
Fan, S
Mao, CX
Lu, JM
[J]. ENGINEERING INTELLIGENT SYSTEMS FOR ELECTRICAL ENGINEERING AND COMMUNICATIONS, 2003, 11 (03): : 151 - 156
[3] Real-time flow control using neural networks
Chan, HL
Rad, AB
[J]. ISA TRANSACTIONS, 2000, 39 (01) : 93 - 101
[4] Real-time condition monitoring using neural networks
Marzi, H
[J]. ADVANCES IN MANUFACTURING TECHNOLOGY - XV, 2001, : 383 - 388
[5] Fast heuristic scheduling based on neural networks for real-time systems
[J]. Thawonmas, Ruck, 1600, Kluwer Academic Publishers, Dordrecht, Netherlands (09):
[6] FAST HEURISTIC SCHEDULING BASED ON NEURAL NETWORKS FOR REAL-TIME SYSTEMS
THAWONMAS, R
CHAKRABORTY, G
SHIRATORI, N
[J]. REAL-TIME SYSTEMS, 1995, 9 (03) : 289 - 304
[7] Genetic design of real-time neural network controllers
A. Hunter
G. Hare
K. Brown
[J]. Neural Computing & Applications, 1997, 6 : 12 - 18
[8] Genetic design of real-time neural network controllers
Hunter, A
Hare, G
Brown, K
[J]. NEURAL COMPUTING & APPLICATIONS, 1997, 6 (01): : 12 - 18
[9] Virtualization of Industrial Real-Time Networks for Containerized Controllers
Lee, Sang-Hun
Kim, Jong-Seo
Seok, Jong-Soo
Jin, Hyun-Wook
[J]. SENSORS, 2019, 19 (20)
[10] Real-time construction of neural networks
Li, Kang
Peng, Jian Xun
Fei, Minrui
[J]. ARTIFICIAL NEURAL NETWORKS - ICANN 2006, PT 1, 2006, 4131 : 140 - 149

← 1 2 3 4 5 →