Multiconstrained Real-Time Entry Guidance Using Deep Neural Networks

In this article, an intelligent predictor-corrector entry guidance approach for lifting hypersonic vehicles is proposed to achieve real-time and safe control of entry flights by leveraging the deep neural network (DNN) and constraint management techniques. First, the entry trajectory planning proble...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transactions on aerospace and electronic systems Ročník 57; číslo 1; s. 325 - 340
Hlavní autori: Cheng, Lin, Jiang, Fanghua, Wang, Zhenbo, Li, Junfeng
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York IEEE 01.02.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
Aerodynamics
Algorithms
Approximation algorithms
Artificial neural networks
Constraint management
deep neural networks (DNNs)
Earth
entry guidance
Hypersonic vehicles
lateral heading control
Neural networks
numerical predictor–corrector guidance (NPCG)
Prediction algorithms
Predictor-corrector methods
Real time
Real-time systems
Terminal constraints
Trajectory
Trajectory planning
Vehicle dynamics
ISSN:0018-9251, 1557-9603
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:In this article, an intelligent predictor-corrector entry guidance approach for lifting hypersonic vehicles is proposed to achieve real-time and safe control of entry flights by leveraging the deep neural network (DNN) and constraint management techniques. First, the entry trajectory planning problem is formulated as a univariate root-finding problem based on a compound bank angle corridor, and two constraint management algorithms are presented to enforce the satisfaction of both path and terminal constraints. Second, a DNN is developed to learn the mapping relationship between the flight states and ranges, and experiments are conducted to verify its high approximation accuracy. Based on the DNN-based range predictor, an intelligent, multiconstrained predictor-corrector guidance algorithm is developed to achieve real-time trajectory correction and lateral heading control with a determined number of bank reversals. Simulations are conducted through comparing with the state-of-the-art predictor-corrector algorithms, and the results demonstrate that the proposed DNN-based entry guidance can achieve the trajectory correction with an update frequency of 20 Hz and is capable of providing high-precision, safe, and robust entry guidance for hypersonic vehicles.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0018-9251
1557-9603
DOI:10.1109/TAES.2020.3015321