基于总体平均经验模态分解算法的自适应改进  

Adaptive Improvement of EEMD algorithm

作　　者：徐健[1] 周志祥[1] 唐亮[1] 冉杰 何杰[3] YIN Song KONG Ling-wei YANG Ai-Wu MU Kun WANG Tao(State Key Laboratory of Geomechanics and Geotechnical Engineering, Institute of Rock and Soil Mechanics, Chinese Academy of Sciences, Wuhan 430071, China Key Laboratory of Soft Soil Characteristics and Engineering Environment of Tianjin, Tianjin 300381)

机构地区：[1]重庆交通大学土木工程学院,重庆404100 [2]南充市住房和城乡建设局,637000 [3]西南交通大学土木工程学院,成都610031

出　　处：《振动与冲击》2017年第11期215-223,共9页Journal of Vibration and Shock

基　　金：国家自然科学基金(11627802;51478071)

摘　　要：目前较为广泛使用的总体平均经验模态分解算法(EEMD)不能实现桥梁结构响应信号的自适应分解和重构,基于此,针对EEMD算法的不足,提出了能够实现桥梁结构响应信号自适应分解与重构的改进算法:首先引入自适应极值点匹配延拓算法以抑制端点效应;再对分解信号进行聚类分析以避免模态混叠现象;最后利用各本征模态函数(IMF)对应的信息熵、能量密度和平均周期构建筛选有效IMF分量的指标(有效程度系数),以实现有效IMF分量的自动筛选,再利用筛选出的有效分量对桥梁结构响应信号进行重构。模拟信号和简支梁桥仿真算例表明,所提改进算法能够更有效、更准确的实现桥梁结构响应信号的自适应分解与重构。At pre sent ,the ensemble empirical mode decomposition （ EEMD） algorithm is widely used, but it cannot realize adaptive decomposition and reconstruction of bridge structures ’ response signals. Here, aiming at shortcomings of EEMD algorithm, an improved algorithm realizing adaptive decomposition and reconstruction of bridge structures’ response signals was proposed. Firstly, the adaptive extremums matching and extension algorithm was introduced to suppress end effects. Secondly, the decomposed signals were processed with the clustering analysis technique to avoid modal aliasing phenomena. Finally, the corresponding information entropy, energy density and average period of each intrinsic mode function （IMF） were used to construct an index named the effective level coefficient and realize the automatic selection of effective IMF components with this index. The selected effective IMF components were adopted to reconstruct bridge structures ^ response signals. The results of simulated signals and a simply supported girder bridge simulation example showed that this proposed algorithm can realize adaptive decomposition and reconstruction of bridge structures ^ response signals effectively.

关 键 词：桥梁结构 模态分解算法 端点效应 聚类分析 信号重构 

分 类 号：U446.3[建筑科学—桥梁与隧道工程]