摘要
在分析经验模态分解端点效应出现原因的基础上,采用镜像延拓法和径向基函数神经网络预测法对端点效应进行了研究,并对一组数值仿真信号和12层钢筋混凝土框架模型振动台试验实测得到的加速度信号进行了边界处理和经验模态分解。算例结果表明,这两种方法基于边界两端预测数据,都可以有效抑制端点效应对分析信号的影响,提高经验模态分解的效果。另外,对于复杂信号仅采用径向基函数神经网络延拓原始信号,对抑制端点效应的效果不很明显,而对复杂信号经滤波后先利用径向基函数神经网络预测、再利用镜像延拓进行处理,则可以明显抑制端点效应的影响。
Empirical mode decomposition(EMD) is a new method to process nonlinear and nonstationary signals.However,there is some trouble with its end-effect due to using spline interpolation to get its upper and lower envelopes.Based on a brief discussion to the cause of the end-effect,the mirror extension and radial basis function(RBF) neural network prediction are adopted to suppress the end-effect in EMD.A simulated signal and a signal recorded from the shaking table test of a 12-stroey reinforced concrete frame model are processed by the two methods and further decomposed by EMD.The results indicate that the two methods predict and extend the data according to the boundary information of the signal and can suppress the end-effect effectively,thus improving the decomposition results to a certain extent.In addition,for a complex signal,such as a measured acceleration signal of a structure,only extending the signal by RBF neural network is not effective in suppression of the end-effect.But applying mirror extension after filtering the signal and predicting the filtered signal by RBF neural network can suppress the end-effect obviously.
出处
《振动．测试与诊断》
EI
CSCD
北大核心
2010年第4期414-417,共4页
Journal of Vibration,Measurement & Diagnosis
基金
甘肃省科技攻关资助项目(编号:2GS057-A52-008)
关键词
信号处理
经验模态分解
端点效应
镜像延拓
径向基函数神经网络
signal processing empirical mode decomposition end-effect mirror extension radial basis function neural network
作者简介
韩建平 男，1970年12月生，教授。主要从事工程结构抗震减振、结构健康监测及结构检测鉴定与加固等方面的教学与科研工作。曾发表《土木工程抗震设计》（北京：科学出版社，2005年）等论著。E-mail：jphan@lut．cn，jphan1970@gmail．com
