|Table of Contents|

RVM-based fault prediction method for liquid rocket engine test stand(PDF)

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

Issue:
2015年03期
Page:
80-86
Research Field:
测控与试验
Publishing date:

Info

Title:
RVM-based fault prediction method for liquid rocket engine test stand
Author(s):
MA Jun-qiang;  YANG Si-feng;  DAI Fang-li
Beijing Institute of Aerospace Testing Technology, Beijing 100074, China
Keywords:
liquid rocket engine test standRVMfault prediction
PACS:
V434-34
DOI:
-
Abstract:
The fault prediction of liquid rocket engine test stand is actually the prediction of parameters associated with the test rig. By predicting the variation trends of those parameters, whether the test rig will get fault at a certain time in the future can be judged. As liquid rocket engine test-stand system is complex and difficult to model, a model based on relevance vector machine (RVM) is proposed in this paper. At the training stage of the model, the single-parameter method, phase space reconstruction method and multi-parameter method are used respectively to train the model according to the features of the data sequence, and then the trend of overall health degree and start-up thrust of the test stand is predicted by the trained model. The prediction result shows that this method based on RVM can effectively predict the possible fault and its trend.

References:

[1] 郭宵峰, 李耀华, 陈鸿彦, 等. 液体火箭发动机试验[M]. 北京: 宇航出版社, 1990.
[2] 张恒喜, 郭基联, 朱家元, 等. 小样本多元数据分析及应用[M]. 西安: 西北工业大学出版社, 2002.
[3] 范庚, 马登武, 张继军. 一种基于小样本数据的装备故障预测方法[J]. 弹箭与制导学报, 2012, 32(2): 225-228.
[4] BISHOP C M, TIPPING M E. Variational relevance vector machines[C]// Proceedings of Uncertainty in Artificial Intelligence. USA: Morgan Kaufmann, 2000: 46-53.

[5] TIPPING M E. Baseline Matlab implementation of “Sparse Bayesian” model estimation [EB/OL]. [2009-02-22]. http://miketipping.com/papers.htm.

[6] TIPPING M E. Bayesian inference: an introduction to principle and practice in machine learning [EB/OL]. [2006-06- 26]. http://miketipping.com/papers.htm.
[7] TIPPING M E, FAUL A C. Fast marginal likelihood maximisation for sparse Bayesian model [EB/OL]. [2006-06- 26]. http://www.miketipping. com/papers. htm.
[8] 李刚, 邢书宝, 薛惠锋. 基于RBF核的SVM及RVM模式分析性能比较[J]. 计算机应用研究, 2009, 26(5): 1782- 1784.
[9] 范庚, 马登武, 邓力, 等. 基于灰色相关向量机的故障预测模型[J]. 系统工程与电子技术, 2012, 34(2): 424-428．
[10] 郭阳明, 蔡小斌, 张宝珍, 等. 故障预测与健康状态管理技术综述[J]. 计算机测量与控制, 2008, 16(9): 1213- 1219.
[11] 林左鸣, 谭瑞松. 航空故障诊断与健康管理技术[M]. 北京: 航空工业出版社, 2013.
[12] 李夕海, 刘代志, 张斌, 等. 基于重采样的混沌时间序列相空间重构研究[J]. 信号处理, 2006, 22(2): 248-251.
[13] 刘孝贤, 冯晨. 相空间重构中的K_L变换[J]. 山东大学学报(工学版), 2004, 34(6): 41-46.
[14] 廉建鑫. 基于RVM和混合优化算法的变压器故障诊断与预测应用研究[D]. 太原: 太原理工大学, 2012.
[15] 田干, 张炜, 杨正伟, 等. SVM方法在液体火箭发动机故障预测中的应用研究[J]. 2010, 24(1): 1-9.
[16] 杨淑莹. 模式识别与智能计算-Matlab技术实现. 2版[M]. 北京: 电子工业出版社, 2011.

Memo

Memo:
-
Last Update: 1900-01-01