一种基于小样本数据的装备故障预测方法

范庚; 马登武; 张继军

doi:10.15892/j.cnki.djzdxb.2012.04.028

2012 , Vol. 32 >Issue 4: 225 - 228

DOI: https://doi.org/10.15892/j.cnki.djzdxb.2012.04.028

摘要

针对目前装备故障预测面临的数据小样本问题以及现有数据驱动方法的不足,提出了一种基于相关向量机的装备故障预测方法,并通过故障预测仿真实例验证了方法的有效性和合理性。理论分析及应用结果表明:与神经网络、支持向量机等方法相比,该方法在保持较高预测精度的同时,在输出形式、参数设置等方面具有优势,应用前景广阔。

关键词： 小样本; 故障预测; 支持向量机; 相关向量机

本文引用格式

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(4) : 225 -228 . DOI: 10.15892/j.cnki.djzdxb.2012.04.028

Abstract

Aiming at the problem of small samples in equipment fault prognosis and the defects of the existing data-driven methods, a method for fault prognosis based on relevance vector machine was proposed. Example calculation results demonstrate the rationality and the validity of the proposed method. The theoretical analysis and the results of example calculation show that, compared with support vector machine, the proposed method is better in terms of output form and parameter setting while retain high prediction accuracy, and is more suitable for on-line prognosis.

Key words： small sample; fault prognosis; relevance vector machine(RVM)

[an error occurred while processing this directive]

参考文献

[1]	Hess A. PHM a key enabler for the JSF autonomic logistics support concept[C]//2004 IEEE Aerospace Conference Proceedings,2004: 3543-3550.
[2]	张宝珍. 国外综合诊断、预测与健康管理技术的发展及应用[J]. 计算机测量与控制,2008,16(5): 591-594.
[3]	Brown E R,McCollom N N. Prognostics and health management a data-driven approach to supporting the F-35 lightning Ⅱ[C]//2007 IEEE Aerospace Conference Proceedings, 2007: 1-11.
[4]	Luo J H,Namburu M,Pattipati K,et al. Model-based prognostic techniques [C]//2003 IEEE Systems Readiness Technology Conference,2003.
[5]	Goh K M,Tjahjono B,Baines T,et al. A review of research in manufacturing prognostics [C]//2006 IEEE Con-ference on Industrial Informatics,Singapore,2006: 417-422.
[6]	彭宇,刘大同,彭喜元. 故障预测与健康管理技术综述 [J]. 电子测量与仪器学报,2010,24(1): 1-9.
[7]	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: 1-3.
[8]	Vapnik V N. 统计学习理论的本质[M]. 张学工,译. 北京: 清华大学出版社,2000: 96-118.
[9]	Tipping M E. The relevance vector machine [C]//Proceedings of Advances in Neural Information Processing Systems 12,Cambridge,2000: 652-658.
[10]	Tipping M E. Sparse bayesian learning and the relevance vector machine [J]. Journal of Machine Learning Research, 2001(1): 211-244.
[11]	Bishop C M,Tipping M E. Variational relevance vector machines [C]//Uncertainty in Artificial Intelligence Processing, California,USA,2000: 46-53.
[12]	Tipping M E,Faul A C. Fast marginal likelihood maximization for sparse bayesian models [C]//Proceedings of the Ninth International Workshop on Artificial Intelligence and Statistics,Key West,Florida,2003.
[13]	田干,张炜,杨正伟,等. SVM 方法在火箭发动机故障预测中的应用研究[J]. 机械科学与技术,2010,24(1): 1-9.
[14]	田路,张炜,杨正伟,等. Elman 型神经网络在液体火箭发动机故障预测中的应用研究[J]. 弹箭与制导学报,2009,29(1): 191-194.
[15]	刘芳. 基于小波分析和相关向量机的非线性径流预报模型研究[D]. 武汉: 华中科技大学,2007.

Options

文章导航