Robust neural-network-based quasi-sliding-mode control for spacecraft-attitude maneuvering with prescribed performance

Jingbo Fu; Ming Liu; Xibin Cao; Ang Li

doi:10.1016/j.ast.2021.106667

Robust neural-network-based quasi-sliding-mode control for spacecraft-attitude maneuvering with prescribed performance

Jingbo Fu
, Ming Liu^*
, Xibin Cao
, Ang Li

^*Corresponding author for this work

School of Astronautics

Harbin Institute of Technology
Imperial College London

Research output: Contribution to journal › Article › peer-review

47 Scopus citations

Abstract

This paper investigates the robust tracking control problem for spacecraft attitude maneuvering with prescribed performance. Firstly, a control scheme is studied based on a quasi-sliding-mode approach which can simultaneously restrict the convergence speed and the steady-state error of both Euler angle and relative angular velocity. Then, to reduce actuators' energy consumption, a three-layer back-propagation neural network is combined with the above control law to auto-tune the control gains. Finally, the performance and effectiveness of the control approach are demonstrated by numerical simulation.

Original language	English
Article number	106667
Journal	Aerospace Science and Technology
Volume	112
DOIs	https://doi.org/10.1016/j.ast.2021.106667
State	Published - May 2021

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

Neural network
Prescribed performance control
Quasi sliding mode control
Spacecraft attitude maneuver

Access to Document

10.1016/j.ast.2021.106667

Cite this

@article{16ce03b79fe344b5a15e9b8d415234a5,

title = "Robust neural-network-based quasi-sliding-mode control for spacecraft-attitude maneuvering with prescribed performance",

abstract = "This paper investigates the robust tracking control problem for spacecraft attitude maneuvering with prescribed performance. Firstly, a control scheme is studied based on a quasi-sliding-mode approach which can simultaneously restrict the convergence speed and the steady-state error of both Euler angle and relative angular velocity. Then, to reduce actuators' energy consumption, a three-layer back-propagation neural network is combined with the above control law to auto-tune the control gains. Finally, the performance and effectiveness of the control approach are demonstrated by numerical simulation.",

keywords = "Neural network, Prescribed performance control, Quasi sliding mode control, Spacecraft attitude maneuver",

author = "Jingbo Fu and Ming Liu and Xibin Cao and Ang Li",

note = "Publisher Copyright: {\textcopyright} 2021 Elsevier Masson SAS",

year = "2021",

month = may,

doi = "10.1016/j.ast.2021.106667",

language = "英语",

volume = "112",

journal = "Aerospace Science and Technology",

issn = "1270-9638",

publisher = "Elsevier Masson s.r.l.",

}

TY - JOUR

T1 - Robust neural-network-based quasi-sliding-mode control for spacecraft-attitude maneuvering with prescribed performance

AU - Fu, Jingbo

AU - Liu, Ming

AU - Cao, Xibin

AU - Li, Ang

PY - 2021/5

Y1 - 2021/5

N2 - This paper investigates the robust tracking control problem for spacecraft attitude maneuvering with prescribed performance. Firstly, a control scheme is studied based on a quasi-sliding-mode approach which can simultaneously restrict the convergence speed and the steady-state error of both Euler angle and relative angular velocity. Then, to reduce actuators' energy consumption, a three-layer back-propagation neural network is combined with the above control law to auto-tune the control gains. Finally, the performance and effectiveness of the control approach are demonstrated by numerical simulation.

AB - This paper investigates the robust tracking control problem for spacecraft attitude maneuvering with prescribed performance. Firstly, a control scheme is studied based on a quasi-sliding-mode approach which can simultaneously restrict the convergence speed and the steady-state error of both Euler angle and relative angular velocity. Then, to reduce actuators' energy consumption, a three-layer back-propagation neural network is combined with the above control law to auto-tune the control gains. Finally, the performance and effectiveness of the control approach are demonstrated by numerical simulation.

KW - Neural network

KW - Prescribed performance control

KW - Quasi sliding mode control

KW - Spacecraft attitude maneuver

UR - https://www.scopus.com/pages/publications/85103104319

U2 - 10.1016/j.ast.2021.106667

DO - 10.1016/j.ast.2021.106667

M3 - 文章

AN - SCOPUS:85103104319

SN - 1270-9638

VL - 112

JO - Aerospace Science and Technology

JF - Aerospace Science and Technology

M1 - 106667

ER -

Robust neural-network-based quasi-sliding-mode control for spacecraft-attitude maneuvering with prescribed performance

Abstract

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this