›› 2011, Vol. 31 ›› Issue (1): 119-122.

• 信号处理与故障诊断 • Previous Articles     Next Articles

Fault diagnosis method of rotating machinery based on Volterra series and KPCA

<FONT face=Verdana><a href="https://nvc.sjtu.edu.cn/EN/article/advancedSearchResult.do?searchSQL=(((JIANG Jing[Author]) AND 1[Journal]) AND year[Order])" target="_blank">JIANG Jing</a> 1, 2,Li Zhi-nong 1, 2,yi Xiao-bing 3</FONT>   

  1. ( 1. Key Laboratory of Nondestructive Testing, Ministry of Education, Nanchang Hangkong University, Nanchang 360063 , China ; 2. School of Mechanical Engineering, ZhengZhou University, Zhengzhou 450001, China ; 3. Henan Vocational & Technical College of Communications, Zhengzhou 450005, China )
  • Received:2010-01-08 Revised:2010-05-16 Online:2011-02-18 Published:2011-02-18
  • Contact: JIANG Jing

基于Volterra级数和KPCA的旋转机械故障诊断方法研究

蒋静,李志农,易小兵   

  1. ( 1. 南昌航空大学 无损检测技术教育部重点实验室, 南昌 330063;2. 郑州大学 机械工程学院, 郑州 450001; 3. 河南省机电学校, 郑州 450001 )
  • 通讯作者: 蒋静

Abstract: A new fault diagnosis method based on Volterra series and KPCA is proposed. In the proposed method, the Volterra series of four states, i.e. normal, rotor crack, rotor rub and pedestal looseness, are identified by the particle swarm optimization (QPSO) algorithm, then the Volterra kernel function are used as feature vectors to input into kernel principal component analysis (KPCA) for training and recognition. The experiment result shows the proposed method is very effective. The higher order Volterra kernels such as second-order, third-order kernel are used to recognize each fault when the fault is hardly distinguished by first-order Volterra kernel (linear kernel function).

Key words: Volterra series, particle swarm optimization, kernel principal component analysis, fault diagnosis

摘要: 提出了一种基于Volterra级数和核函数主元分析(KPCA)的故障诊断方法。在提出的方法中,首先利用量子粒子群优化(QPSO)算法辨识出正常、转子裂纹、转子碰摩、基座松动四种状态下的Volterra级数,然后将Volterra核函数作为特征向量输入到KPCA进行训练识别。实验结果表明,提出的方法是有效的,在只考虑一阶Volterra核不能进行很好地识别时,可以从二阶、三阶Volterra核上来区分。

关键词: Volterra级数, 量子粒子群优化, 核函数主元分析, 故障诊断