基于小波/包与ICA结合的结构损伤识别
|
摘要
目的为了有效地剔除测量数据中的噪声、提高结构损伤检测的诊断率.方法提出了一种新的消噪与结构损伤识别方法.采用小波/包变换对结构响应进行消噪处理,利用独立组分分析ICA中的固定点算法分离得到ICA滤波基并进行信号分离,接着对消噪、分离后的信号提取IC自相关特征,最后利用概率神经网络进行损伤识别.结果用Benchmark模型进行的损伤识别,并与进行二次小波/包消噪及未消噪的数据识别结果进行了比较结果验证了所提方法的可行性和有效性.结论笔者所提方法对信号消噪是可行、有效的,对提高损伤识别精度也有着重要的贡献.
In order to effectively remove the noise of measured data and improve the diagnosis rate of a structure,a new approach of both de-noising and structural damage identification was proposed in this paper.Wavelet transform and wavelet packet transform were addressed according to the structural responses for denoising firstly,and then the fixed-point algorithm of the Independent Component Analysis(ICA) was used to process the denoised signal for acquiring the filtering base-function of ICA;afterwards,the signal was separated.The IC autocorrelation characteristics were extracted as soon as the signal was denoised and separated,and a prob-abilistic neural network(PNN) model was used for damage pattern recognition finally.To verify the method proposed,damage detection was conducted through the ASCE's Benchmark model,and a comparison was made between the two proposed approaches,the one using twice denoising by wavelet and wavelet packet,and the one without any processing as well.The experimental study shows that the method proposed is effective for signal-noise separation,and provides crucial contribution to increase damage accuracy as well.
In order to effectively remove the noise of measured data and improve the diagnosis rate of a structure,a new approach of both de-noising and structural damage identification was proposed in this paper.Wavelet transform and wavelet packet transform were addressed according to the structural responses for denoising firstly,and then the fixed-point algorithm of the Independent Component Analysis(ICA) was used to process the denoised signal for acquiring the filtering base-function of ICA;afterwards,the signal was separated.The IC autocorrelation characteristics were extracted as soon as the signal was denoised and separated,and a prob-abilistic neural network(PNN) model was used for damage pattern recognition finally.To verify the method proposed,damage detection was conducted through the ASCE's Benchmark model,and a comparison was made between the two proposed approaches,the one using twice denoising by wavelet and wavelet packet,and the one without any processing as well.The experimental study shows that the method proposed is effective for signal-noise separation,and provides crucial contribution to increase damage accuracy as well.
引文
[1]Worden K,Delieu-Barton J M.An overview of intel-ligent fault detection in systems and structures[J].Structural Health Monitoring,2004,3:85-98.
[2]姜绍飞.结构健康监测-智能信息处理及应用[J].工程力学,2009,26(SII):184-212.(Jiang Shaofei.Structural health monitoring-intelli-gent information processing and application[J].Engi-neering Mechanics,2009,26(SII):184-212.)
[3]高隽.智能信息处理方法导论[M].北京:机械工业出版社,2004.(Gao Juan.Introduction to intelligent information pro-cessing methods[M].Beijing:Machinery IndustryPress,2004.)
[4]何清波,孔凡让,王建平,等.基于独立分量分析特征提取带噪信号端点检测[J].数据采集与处理,2007,22(1):25-30.(He Qingbo,Kong Fanrang,Wang Jianping,et al.Endpoint detection of noisy signal based on feature ex-traction using independent component analysis[J].Journal of Data Acquisition&Processing,2007,22(1):25-30.)
[5]冯健,张化光.基于小波消噪和盲源分离的信号奇异点检测方法[J].控制与决策,2007,22(9):1035-1038.(Feng Jian,Zhang Huaguang.Method of signal singu-larity detection based on wavelet canceling noise andblind source separation[J].Control and Decision,2007,22(9):1035-1038.)
[6]Banakar A,Azeem M F.Artificial wavelet neural net-work and its application in neuro-fuzzy models[J].Applied Soft Computing,2008,8:1463-1485.
[7]林志波.基于盲源分离的结构响应噪声剔除与损伤识别方法研究[D].福州:福州大学图书馆,2010.(Ling Zhibo.Study on structural response denoisingand damage identification methods based on blindsource separation[D].Fuzhou:Fuzhou University Li-brary,2010.)
[8]刘涛,李爱群,丁幼亮.小波分析在结构损伤识别中的应用[J].地震工程与工程振动,2008,28(2):29-35.(Liu Tao,Li Aiqun,Ding Youliang.Application ofwavelet analysis to structural damage identification[J].Journal of Earthquake Engineering and Engineer-ing Vibrarion,2008,28(2):29-35.)
[9]He Qingbo,Feng Zhihua,Kong Fanrang.Detection ofsignal transients using independent component analy-sis and its application in gearbox condition monitoring[J].Mechanical Systems and Signal Processing,2007,21:2056-2071.
[10]Jiang Shaofei,Zhang Chunming,Zhang Shuai.Two-stage structural damage detection using fuzzy neuralnetworks and data fusion techniques[J].Expert Sys-tems with Applications,2011,38(1):511-519.
[11]Zhou Wenliang,Chelidze D.Blind source separationbased vibration mode identification[J].MechanicalSystems and Signal Processing,2007,21:3072-3087.
[12]Specht D F.Probabilistic neural networks[J].NeuralNetworks,1990,3:109-118.
[13]Jiang Shaofei,Zhang Chunming,Koh C G.Structuraldamage detection by integrating data fusion and prob-abilistic neural network[J].Advances in StructuralEngineering,2006,9(4):445-458.
[14]Cheng Jaohong,Chen Hueiping,Lin Yimin.A hybridforecast marketing timing model based on probabilisticneural network,rough set and C4.5[J].Expert Sys-tems with Applications,2010,37:1814-1820.
[15]Hojjat A,Ashif P.A probabilistic neural network forearthquake magnitude prediction[J].Neural Net-works,2009,22:1018-1024.
[2]姜绍飞.结构健康监测-智能信息处理及应用[J].工程力学,2009,26(SII):184-212.(Jiang Shaofei.Structural health monitoring-intelli-gent information processing and application[J].Engi-neering Mechanics,2009,26(SII):184-212.)
[3]高隽.智能信息处理方法导论[M].北京:机械工业出版社,2004.(Gao Juan.Introduction to intelligent information pro-cessing methods[M].Beijing:Machinery IndustryPress,2004.)
[4]何清波,孔凡让,王建平,等.基于独立分量分析特征提取带噪信号端点检测[J].数据采集与处理,2007,22(1):25-30.(He Qingbo,Kong Fanrang,Wang Jianping,et al.Endpoint detection of noisy signal based on feature ex-traction using independent component analysis[J].Journal of Data Acquisition&Processing,2007,22(1):25-30.)
[5]冯健,张化光.基于小波消噪和盲源分离的信号奇异点检测方法[J].控制与决策,2007,22(9):1035-1038.(Feng Jian,Zhang Huaguang.Method of signal singu-larity detection based on wavelet canceling noise andblind source separation[J].Control and Decision,2007,22(9):1035-1038.)
[6]Banakar A,Azeem M F.Artificial wavelet neural net-work and its application in neuro-fuzzy models[J].Applied Soft Computing,2008,8:1463-1485.
[7]林志波.基于盲源分离的结构响应噪声剔除与损伤识别方法研究[D].福州:福州大学图书馆,2010.(Ling Zhibo.Study on structural response denoisingand damage identification methods based on blindsource separation[D].Fuzhou:Fuzhou University Li-brary,2010.)
[8]刘涛,李爱群,丁幼亮.小波分析在结构损伤识别中的应用[J].地震工程与工程振动,2008,28(2):29-35.(Liu Tao,Li Aiqun,Ding Youliang.Application ofwavelet analysis to structural damage identification[J].Journal of Earthquake Engineering and Engineer-ing Vibrarion,2008,28(2):29-35.)
[9]He Qingbo,Feng Zhihua,Kong Fanrang.Detection ofsignal transients using independent component analy-sis and its application in gearbox condition monitoring[J].Mechanical Systems and Signal Processing,2007,21:2056-2071.
[10]Jiang Shaofei,Zhang Chunming,Zhang Shuai.Two-stage structural damage detection using fuzzy neuralnetworks and data fusion techniques[J].Expert Sys-tems with Applications,2011,38(1):511-519.
[11]Zhou Wenliang,Chelidze D.Blind source separationbased vibration mode identification[J].MechanicalSystems and Signal Processing,2007,21:3072-3087.
[12]Specht D F.Probabilistic neural networks[J].NeuralNetworks,1990,3:109-118.
[13]Jiang Shaofei,Zhang Chunming,Koh C G.Structuraldamage detection by integrating data fusion and prob-abilistic neural network[J].Advances in StructuralEngineering,2006,9(4):445-458.
[14]Cheng Jaohong,Chen Hueiping,Lin Yimin.A hybridforecast marketing timing model based on probabilisticneural network,rough set and C4.5[J].Expert Sys-tems with Applications,2010,37:1814-1820.
[15]Hojjat A,Ashif P.A probabilistic neural network forearthquake magnitude prediction[J].Neural Net-works,2009,22:1018-1024.
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心