Volume 14 Number 8 (Aug. 2019)
Home > Archive > 2019 > Volume 14 Number 8 (Aug. 2019) >
JSW 2019 Vol.14(8): 380-387 ISSN: 1796-217X
doi: 10.17706/jsw.14.8.380-387

Fault Detection in Liquid-Propellant Rocket Engines Based on Improved PSO-BP Neural Network

Ningning Li1,2, Wei Xue2, Xiang Guo3, Liang Xu1*, Yuyang Wu1, Yuan Yao1

1Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems, and School of Electrical and Electronic Engineering, Tianjin University of Technology, Tianjin, 300384, China
2Beijing Aerospace Propulsion Institute, Beijing 100076, China.
3Big data Center, PICC Property and Casualty Company Limited, Beijing 100022, China.


Abstract—A method that uses an improved particle swarm optimization (PSO) algorithm combined with a backpropagation (BP) neural network is proposed to solve the problem of liquid-propellant rocket engine (LRE) failure detection. In the improved PSO algorithm, the global extremum is randomly perturbed by adding disturbance factor using the degree of particle aggregation around the global optimal value, and the individual extremum is randomly perturbed by adding disturbance factor using the number of particle extreme stagnation steps, disturbance factors are randomly added to individual extremum to diturb the particle’s current search path, increasing the probability of particles jumping out of local extremum, avoiding the occurrence of local extremum, premature convergence or stagnation. In this paper, the improved algorithm is applied to the fault detection of a typical liquid rocket engine in steady state process. The simulation results show that, under the same conditions, the convergence speed of this PSO-BP method is obviously higher than that of BP neural network, and it does not fall into the local extreme value. The accuracy of fault detection is also improved significantly.

Index Terms—Liquid-propellant rocket engine, fault detection, particle swarm optimization (PSO), randomly perturbed.

[PDF]

Cite: Ningning Li, Wei Xue, Xiang Guo, Liang Xu, Yuyang Wu, Yuan Yao, "Fault Detection in Liquid-Propellant Rocket Engines Based on Improved PSO-BP Neural Network," Journal of Software vol. 14, no. 8, pp. 380-387, 2019.

General Information

ISSN: 1796-217X (Online)
Frequency:  Quarterly
Editor-in-Chief: Prof. Antanas Verikas
Executive Editor: Ms. Yoyo Y. Zhou
Abstracting/ Indexing: DBLP, EBSCO, CNKIGoogle Scholar, ProQuest, INSPEC(IET), ULRICH's Periodicals Directory, WorldCat, etc
E-mail: jsweditorialoffice@gmail.com
  • Mar 01, 2024 News!

    Vol 19, No 1 has been published with online version    [Click]

  • Apr 26, 2021 News!

    Vol 14, No 4- Vol 14, No 12 has been indexed by IET-(Inspec)     [Click]

  • Nov 18, 2021 News!

    Papers published in JSW Vol 16, No 1- Vol 16, No 6 have been indexed by DBLP   [Click]

  • Jan 04, 2024 News!

    JSW will adopt Article-by-Article Work Flow

  • Nov 02, 2023 News!

    Vol 18, No 4 has been published with online version   [Click]