Fast real-time SDRE controllers using neural networks

被引：8

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 38 条

[21]

Korayem MH, 2014, RSI INT CONF ROBOT M, P13, DOI 10.1109/ICRoM.2014.6990769

[22] A family of model predictive control algorithms with artificial neural networks [J].

Lawrynczuk, Maciej .

INTERNATIONAL JOURNAL OF APPLIED MATHEMATICS AND COMPUTER SCIENCE, 2007, 17 (02) :217-232

[23]

Lenz I, 2015, ROBOTICS: SCIENCE AND SYSTEMS XI

[24] Real-time computational methods for SDRE nonlinear control of missiles [J].

Menon, PK ;

Lam, T ;

Crawford, LS ;

Cheng, VHL .

PROCEEDINGS OF THE 2002 AMERICAN CONTROL CONFERENCE, VOLS 1-6, 2002, 1-6 :232-237

[25] Nonlinear Optimal Control of Relative Rotational and Translational Motion of Spacecraft Rendezvous [J].

Navabi, M. ;

Akhloumadi, Mahdi R. .

JOURNAL OF AEROSPACE ENGINEERING, 2017, 30 (05)

[26]

Ng A., 2011, CS294A Lect. Notes, V29, P1, DOI DOI 10.1371/JOURNAL.PONE.0006098

[27] Agile Attitude Control and Singularity Avoidance/Escape by the SDRE Method Using a Biased State-Dependent Weighting Matrix [J].

Ozawa, Ryotaro ;

Takahashi, Masaki .

APPLIED SCIENCES-BASEL, 2018, 8 (01)

[28]

Pearson J.D., 1962, Int. J. Electron., V13, P453, DOI DOI 10.1080/00207216208937454

[29]

Qian SK, 2016, 2016 IEEE CHINESE GUIDANCE, NAVIGATION AND CONTROL CONFERENCE (CGNCC), P1939, DOI 10.1109/CGNCC.2016.7829086

[30] State-Dependent Riccati-Equation-Based Guidance Law for Impact-Angle-Constrained Trajectories [J].

Ratnoo, Ashwini ;

Ghose, Debasish .

JOURNAL OF GUIDANCE CONTROL AND DYNAMICS, 2009, 32 (01) :320-326

← 1 2 3 4 →