Journal of Propulsion Technology ›› 2001, Vol. 22 ›› Issue (1): 47-49.

Previous Articles     Next Articles

Leak fault identification of rocket engine using self organizing feature map network

  

  1. School of Energy Science and Engineering ,Harbin Inst. of Technology,Harbin 150001,China;School of Energy Science and Engineering ,Harbin Inst. of Technology,Harbin 150001,China;School of Energy Science and Engineering ,Harbin Inst. of Technology,Harbin 150001,China
  • Published:2021-08-15

应用自组织网络识别火箭发动机泄漏故障

于达仁,王建波,王广雄   

  1. 哈尔滨工业大学能源科学与工程学院!黑龙江哈尔滨150001;哈尔滨工业大学能源科学与工程学院!黑龙江哈尔滨150001;哈尔滨工业大学能源科学与工程学院!黑龙江哈尔滨150001
  • 基金资助:
    哈尔滨工业大学校管航天基金资助项目! (96 0 2 410 49)

Abstract: Some kinds of leak fault were analyzed in liquid rocket engine. The method of principle component analysis was used to reduce the dimension of the original samples, which can represent the leak. And then input the low dimension samples, the self organizing feature map network can identify the leak fault. The simulating results show that the approach is feasible and effective.

Key words: Liquid propellant rocket engine;Leak fault;Fault diagnosis;Artificial neural network

摘要: 以一个典型的泵压式液体火箭发动机 (LRE)为对象 ,针对发动机的几种泄漏故障 ,先用主成分分析法对泄漏故障的原始样本进行降维 ,然后利用降维的样本 ,用自组织网络对泄漏故障进行识别 ,仿真结果表明 ,这一方法能对泄漏故障进行很好的识别。

关键词: 液体推进剂火箭发动机,泄漏故障;故障诊断;人工神经元网络