Skip to main navigation Skip to search Skip to main content

A reaching law based neural network terminal sliding-mode guidance law design

  • Beihang University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

A nonsingular terminal guidance law is proposed for dual-controlled missile with tails and reaction jets based on power rate reaching law and neural network terminal sliding mode control (TSMC). By combining nonsingular terminal sliding mode control (NTSMC) with power rate reaching law, the guidance law improves the reaching rate of system states to sliding surface with less control command. Also, it makes the line-of-sight (LOS) angular rate converge to zero in a finite time. The disturbance is compensated and monitored by using online learning neural network under consideration of model uncertainty and the effect of target maneuvering, the robustness of the control systems is therefore improved. Simulation results show that, the guidance law can make the system states converge to zero in a limited time, and can achieve better system performance in guaranteeing system robustness.

Original languageEnglish
Title of host publication2013 IEEE International Conference of IEEE Region 10, IEEE TENCON 2013 - Conference Proceedings
DOIs
StatePublished - 2013
Event2013 IEEE International Conference of IEEE Region 10, IEEE TENCON 2013 - Xi'an, Shaanxi, China
Duration: 22 Oct 201325 Oct 2013

Publication series

NameIEEE Region 10 Annual International Conference, Proceedings/TENCON
ISSN (Print)2159-3442
ISSN (Electronic)2159-3450

Conference

Conference2013 IEEE International Conference of IEEE Region 10, IEEE TENCON 2013
Country/TerritoryChina
CityXi'an, Shaanxi
Period22/10/1325/10/13

Keywords

  • guidance law
  • neural network
  • power rate reaching law
  • terminal sliding-mode control
  • uncertainty

Fingerprint

Dive into the research topics of 'A reaching law based neural network terminal sliding-mode guidance law design'. Together they form a unique fingerprint.

Cite this