北京航空航天大学学报 ›› 2012, Vol. 38 ›› Issue (10): 1300-1305.

• 论文 • 上一篇    下一篇

基于SMO-SVR的飞机舵面损伤故障趋势预测

董磊, 任章, 李清东   

  1. 北京航空航天大学 飞行器控制一体化技术重点实验室, 北京 100191
  • 收稿日期:2012-06-07 出版日期:2012-10-30 发布日期:2012-10-30
  • 基金资助:
    国家自然科学基金资助项目(60874117, 61101004)

Fault prediction for aircraft control surface damage based on SMO-SVR

Dong Lei, Ren Zhang, Li Qingdong   

  1. Science and Technology on Aircraft Control Laboratory, Beijing University of Aeronautics and Astronautics, Beijing 100191, China
  • Received:2012-06-07 Online:2012-10-30 Published:2012-10-30

摘要: 飞机舵面出现损伤时,为了更准确的预测状态参量变化情况,提出了一种改进的序贯最小优化支持向量回归(SMO-SVR, Sequential Minimal Optimization Support Vector Regression)预测方法.采用改进C-C平均方法对多元时间序列进行相空间重构,以确定最优嵌入维数m和延迟时间τd.根据所求mτd建立加权SVR预测模型,并调整了SMO算法的停机准则.利用区间自适应粒子群算法(IAPSO, Interval Adaptive Particle Swarm Optimization)优化SVR参数,以提高参数优化速度.为了验证改进算法的有效性,针对飞机方向舵损伤故障趋势进行了预测和分析,并与径向基函数神经网络(RBFNN, Radial Basis Function Neural Network)方法进行了对比,仿真结果表明SMO-SVR预测模型具有很好的预测能力.

Abstract: In order to predict changes more accurately when the surface of aircraft damaged, an algorithm based on improved sequential minimal optimization support vector regression (SMO-SVR) was presented. This algorithm reconstructed the phase space of multivariate and nonlinear time series using improved C-C average method to determine the embedding dimension m and the delay time τd. Then, a weighted SVR model was built according to m and τd, and in which the halt criterion of SMO was modified. The parameters of SVR were optimized by interval adaptive particle swarm optimization (IAPSO) to improve the efficiency of parameter optimization. In order to verify the validity of the algorithm, the prediction and analysis of surface damage trend were performed. Comparing with the radial basis function neural network (RBFNN) method, the simulation result demonstrates that the improved SMO-SVR prediction model has good predictive ability.

中图分类号: 


版权所有 © 《北京航空航天大学学报》编辑部
通讯地址:北京市海淀区学院路37号 北京航空航天大学学报编辑部 邮编:100191 E-mail:jbuaa@buaa.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发