摘要
基于小波包变换能够把平稳和非平稳信号根据它们的时频特性分解到不同层次上不同频道内，与模糊数学能够处理工程中的不确定性问题，以及ＭＡＸＮＥＴ聚类结构的网络具有自组织聚类分析的优点，提出了小波包模糊聚类网络．该网络能够处理平稳和非平稳信号的不确定性问题，并且具有自适应、自组织聚类分析功能．最后举例说明了该网络在机械诊断实践中是一种行之有效的智能分类器．
This paper advances a new approach based on wavelet packets in tandem with the fuzzy cluster neural network. Wavelet packets decompose stationary or nonstationary signals into different bands at different levels. Fuzzy cluster processes the uncertainty problem, and MAXNET realizes selforganizing classification. The approach integrates the advantages of wavelet packets and fuzzy cluster with MAXNET, and therefore it can process uncertainty problems of stationary or nonstationary signals and carry out adaptive pattern recognition and selforganization classification. The network was use to analyse for an example, and the results indicate that it is a useful and effective intelligent classification in the field of fault diagnosis.
出处
《西安交通大学学报》
EI
CAS
CSCD
北大核心
1998年第2期15-19,共5页
Journal of Xi'an Jiaotong University
基金
国家自然科学基金
关键词
小波包
模糊聚类
神经网络
故障诊断
机械
wavelet packets fuzzy cluster neural network signal processing fault diagnosis
