Neural Networks Based Real-Time Fault Detection for A Liquid Rocket Propulsion System

Erfu Yang, Hongjun Xiang, Zhenpeng Zhang

Research output: Contribution to conferenceProceeding

Abstract

The real-time fault detection is very crucial in developing the online health monitoring techniques for rocket propulsion systems,particularly when the manned space missions are accompanied. The neural networks based approach provides an alternative solution to the design of model-based fault detection methods for detecting the potential failures of propulsion systems. The design approach consists of system modeling, residual generation and fault detection. First, feed-forward neural networks are used to model the complicated dynamics of propulsion system for simplifying the modeling process and improving the real-time performance of model-based fault detection. Second, a real time fault detection architecture using the established neural networks approximator is designed. By using real measurements from ground firing test, an example is provided for demonstrating the effectiveness of the proposed approach to the real time fault detection of a liquid rocket propulsion system.

Conference

ConferenceThe 23rd Chinese Control Conference (International, CCC04), Wuxi, China, August 10-13, 2004
CountryChina
CityWuxi
Period10/08/0413/08/04

Fingerprint

Rockets
Fault detection
Propulsion
Neural networks
Liquids
Feedforward neural networks
Health
Monitoring

Keywords

  • liquid propellant rocket propulsion systems
  • fault diagnosis,
  • computer simulation
  • pattern recognition
  • neural networks
  • process modeling

Cite this

Yang, E., Xiang, H., & Zhang, Z. (2004). Neural Networks Based Real-Time Fault Detection for A Liquid Rocket Propulsion System. 1003–1007. The 23rd Chinese Control Conference (International, CCC04), Wuxi, China, August 10-13, 2004, Wuxi, China.
Yang, Erfu ; Xiang, Hongjun ; Zhang, Zhenpeng. / Neural Networks Based Real-Time Fault Detection for A Liquid Rocket Propulsion System. The 23rd Chinese Control Conference (International, CCC04), Wuxi, China, August 10-13, 2004, Wuxi, China.5 p.
@conference{268365af88844041a2de90e69439f0d4,
title = "Neural Networks Based Real-Time Fault Detection for A Liquid Rocket Propulsion System",
abstract = "The real-time fault detection is very crucial in developing the online health monitoring techniques for rocket propulsion systems,particularly when the manned space missions are accompanied. The neural networks based approach provides an alternative solution to the design of model-based fault detection methods for detecting the potential failures of propulsion systems. The design approach consists of system modeling, residual generation and fault detection. First, feed-forward neural networks are used to model the complicated dynamics of propulsion system for simplifying the modeling process and improving the real-time performance of model-based fault detection. Second, a real time fault detection architecture using the established neural networks approximator is designed. By using real measurements from ground firing test, an example is provided for demonstrating the effectiveness of the proposed approach to the real time fault detection of a liquid rocket propulsion system.",
keywords = "liquid propellant rocket propulsion systems, fault diagnosis,, computer simulation, pattern recognition, neural networks, process modeling",
author = "Erfu Yang and Hongjun Xiang and Zhenpeng Zhang",
year = "2004",
month = "8",
day = "10",
language = "English",
pages = "1003–1007",
note = "The 23rd Chinese Control Conference (International, CCC04), Wuxi, China, August 10-13, 2004 ; Conference date: 10-08-2004 Through 13-08-2004",

}

Yang, E, Xiang, H & Zhang, Z 2004, 'Neural Networks Based Real-Time Fault Detection for A Liquid Rocket Propulsion System' The 23rd Chinese Control Conference (International, CCC04), Wuxi, China, August 10-13, 2004, Wuxi, China, 10/08/04 - 13/08/04, pp. 1003–1007.

Neural Networks Based Real-Time Fault Detection for A Liquid Rocket Propulsion System. / Yang, Erfu; Xiang, Hongjun; Zhang, Zhenpeng.

2004. 1003–1007 The 23rd Chinese Control Conference (International, CCC04), Wuxi, China, August 10-13, 2004, Wuxi, China.

Research output: Contribution to conferenceProceeding

TY - CONF

T1 - Neural Networks Based Real-Time Fault Detection for A Liquid Rocket Propulsion System

AU - Yang, Erfu

AU - Xiang, Hongjun

AU - Zhang, Zhenpeng

PY - 2004/8/10

Y1 - 2004/8/10

N2 - The real-time fault detection is very crucial in developing the online health monitoring techniques for rocket propulsion systems,particularly when the manned space missions are accompanied. The neural networks based approach provides an alternative solution to the design of model-based fault detection methods for detecting the potential failures of propulsion systems. The design approach consists of system modeling, residual generation and fault detection. First, feed-forward neural networks are used to model the complicated dynamics of propulsion system for simplifying the modeling process and improving the real-time performance of model-based fault detection. Second, a real time fault detection architecture using the established neural networks approximator is designed. By using real measurements from ground firing test, an example is provided for demonstrating the effectiveness of the proposed approach to the real time fault detection of a liquid rocket propulsion system.

AB - The real-time fault detection is very crucial in developing the online health monitoring techniques for rocket propulsion systems,particularly when the manned space missions are accompanied. The neural networks based approach provides an alternative solution to the design of model-based fault detection methods for detecting the potential failures of propulsion systems. The design approach consists of system modeling, residual generation and fault detection. First, feed-forward neural networks are used to model the complicated dynamics of propulsion system for simplifying the modeling process and improving the real-time performance of model-based fault detection. Second, a real time fault detection architecture using the established neural networks approximator is designed. By using real measurements from ground firing test, an example is provided for demonstrating the effectiveness of the proposed approach to the real time fault detection of a liquid rocket propulsion system.

KW - liquid propellant rocket propulsion systems

KW - fault diagnosis,

KW - computer simulation

KW - pattern recognition

KW - neural networks

KW - process modeling

UR - http://www.cnki.net/kcms/detail/detail.aspx?dbname=cpfd2004&filename=KZLL200408002037&dbcode=cpfd&v=MDAwNDE3cVFLcmlmWnVOdkVDdmlVcnpJSlZ3Y0xqZkhZckc0SHRYTXA0OUZadXNNQ3hNNHptVVdtVDhJVGdyZ3F4TkdE

UR - http://ccc.amss.ac.cn/

M3 - Proceeding

SP - 1003

EP - 1007

ER -

Yang E, Xiang H, Zhang Z. Neural Networks Based Real-Time Fault Detection for A Liquid Rocket Propulsion System. 2004. The 23rd Chinese Control Conference (International, CCC04), Wuxi, China, August 10-13, 2004, Wuxi, China.