|Table of Contents|

Application of deep cross-hybrid genetic neural network to fault detection of liquid rocket engines(PDF)

《火箭推进》[ISSN:1672-9374/CN:CN 61-1436/V]

Issue:
2009年02期
Page:
41-45
Research Field:
测控与试验
Publishing date:

Info

Title:
Application of deep cross-hybrid genetic neural network to fault detection of liquid rocket engines
Author(s):
Yang Jinzhao; Huang Minchao
Institute of Aerospace and Material Engineering,National University of Defense Technology，Changsha 410073，China
Keywords:
genetic algorithm; back propagation neural network; fault detection; global optimization
PACS:
V434
DOI:
-
Abstract:
This paper proposes a new hybrid algorithm based on genetic algorithm and BP neural network．First，multi—point optimization of the BP neural network's weights and threshold values in GA algorithm is carried out，and some chromosomes that are random sampled in each generation perform single BP neural network training．The result gained above is returned to the chromosomes． Second，stable weights and threshold values are obtained after the evolution of some generations， then they ale used as the initial value to train the BP neural network by seeking along negative grads in error forward feedback algorithm，and finally the global optimum is gained．’11le proposed algorithm can avoid the deficiency of BP algorithm that may easily be steeped in local optimums，and can also overcome GA's shortcomings of long seeking time and low seeking due to the method of enumerating．，11le results of simulation indicates that the ability of convergence and diagnosis of the proposed algorithm is better than that of traditional BP neural network or only using GA，and the algorithm Can be effectively applied to the fault detection of liquid rocket engine．

References:

[l]陈明．神经网络模型[M]．大连：大连理工大学出版社，1995．
[2]钟珞，饶文碧，邹承明[M]．人工神经网络及其融合应用技术．北京：科学出版社，2007．
[3]王小平，曹立明·遗传算法——理论、应用与软件实现[M]．西安：西安交通大学出版社，2002·
[4]Yutaka Fukuoka，Hideo Matsuki，Hasuki，Hasruyuki MinamitaIli．et aI．A modified back-propagation method to avoid false local minima[J]．Neural networks，1998，(1 1)：1059_1072．

Memo

Memo:
-
Last Update: 1900-01-01