Abstract:In order to solve the difficult problem of the identify the early damage of structure correctly, a trend prediction model of support vector machine (SVM) based on ensemble empirical mode decomposition (EEMD) is proposed, where the EEMD method processing stochastic uncertainty signal and the SVM regression(SVR) solving the small-sample pattern recognition problem are integrated. First,the response signals of acceleration vibration signals of a single-degree of freedom structure model are processed by using EEMD, the intrinsic mode function (IMF) which contains structural damage information are selected; and then the selected IMF is transformed by using Hilbert transform (HT) and instantaneous frequency(IF) are calculated; finally, the trend prediction based on SVR of IF is realized. The prediction of structural engineering simulation data shows that the method can predict the trends of structure conditions accurately and precisely.
刘义艳;贺栓海;巨永锋;段晨东. 基于EEMD和SVR的单自由度结构状态趋势预测[J]. , 2012, 31(5): 60-64.
Liu Yi-yan;He quan-hai;Ju Yong-feng;Duan Chen-dong. Trend prediction of single-degree of freedom structure’s state based on EEMD and SVR. , 2012, 31(5): 60-64.