作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2012, Vol. 38 ›› Issue (08): 283-286. doi: 10.3969/j.issn.1000-3428.2012.08.091

• 开发研究与设计技术 • 上一篇    下一篇

基于杂合支持向量回归机的电子装备故障预测

薛辉辉 1,肖明清 1,段军峰 2   

  1. (1. 空军工程大学工程学院自动测试系统实验室,西安 710038;2. 中国人民解放军93811部队,兰州 730020)
  • 收稿日期:2011-08-22 出版日期:2012-04-20 发布日期:2012-04-20
  • 作者简介:薛辉辉(1986-),男,硕士研究生,主研方向:智能化故障诊断,测试信息共享;肖明清,教授、博士生导师;段军峰,工程师

Fault Prediction for Electronic Equipment Based on Hybrid Support Vector Regression

XUE Hui-hui 1, XIAO Ming-qing  1, DUAN Jun-feng  2   

  1. (1. Automatic Test System Lab, Engineering College, Air Force Engineering University, Xi’an 710038, China; 2. People’s Liberation Army No.93811, Lanzhou 730020, China)
  • Received:2011-08-22 Online:2012-04-20 Published:2012-04-20

摘要:

针对电子装备性能特征参数间的耦合关联问题,提出一种基于杂合支持向量回归机的电子装备故障预测方法。运用D-S证据理 论,结合参数的纵向历史状态数据和横向的相关参数数据,设计杂合支持向量回归机预测算法,利用特征参数的时间相关性和空间相关性提高预测精度。实验结果表明,相对于单独使用纵向或者横向的支持向量回归机,该方法具有更高的精度,可有效地对复杂电子装备实施故障预测。

关键词: 电子装备, 故障预测, 杂合支持向量回归机, D-S证据理论, 特征参数, 诊断精度

Abstract:

Aiming at the coupling relationship among electronic equipment’s feature parameters, a hybrid Support Vector Regression(SVR) based fault prediction model is proposed in the paper, both the time relativity and space relativity of the feature parameter are taken into account, and it designes the algorithm process of hybrid SVR which improves the prediction accuracy by fusing the vertical historical state data and the horizontal correlation parameter together, applying D-S evidence theory. Experimental results show that, compared with vertical SVR or horizontal SVR, the proposed method is more accurate, and is capable of performing fault prognosis on the complicated electronic equipment effectively.

Key words: electronic equipment, fault prediction, hybrid Support Vector Regression(SVR), D-S evidence theory, feature parameter, diagnosis accuracy

中图分类号: