Bearing Fault Diagnostic Based on EMD and Neural Network

摘要：

Aiming at the signals of fault bearing in the movement process, however due to uncertainty principle limit,previous time-frequency analysis method (short-time Fourier transform, Vigner-Ville distribution, wavelet transform) cant very accurately extracting the local instantaneous characteristics of signal. This paper uses the relatively new time-frequency analysis method EMD (Empirical Mode Decomposition) to processes the fault signal. First the signal components of the basic mode is decomposed and collected, then the signal were doing time-frequency analysis after Hilbert transformation, and getting the local instantaneous characteristics of signal. RBF network is used to fitting the nonlinear relationship of bearing vibration signal changes. Finally construct the prediction model based on RBF network.

关键词： Rollinghearing IMFs EMD RBF

作者: Zhiping Guo Jiming Yan Xianfeng Zhou Qiangjun Wang Haifeng Lin Bei Zheng Erqing Zhang

作者单位: Chengdu Aircraft Industrial (Group) Co., Ltd Chengdu, China School Of Mechanical Engineering Southwest Jiaotong University Chengdu, China

会议类型: 国际会议

会议名称: 2011 3rd International Conference on Computer and Network Technology(ICCNT 2011)(2011第三届IEEE计算机与网络技术国际会议)

会议地点: 太原

会议语种:英文

页码: 561-564

在线出版日期: 2011-02-26（万方平台首次上网日期，不代表论文的发表时间）