Eigen-Level Data Fusion Model by Integrating Rough Set and Probabilistic Neural Network for Structural Damage Detection

In this paper, a new eigen-level data fusion model, whereby rough set data and a probabilistic neural network (PNN) are integrated using a data fusion technique, is proposed for structural damage detection. This model is used for structural damage detection and identification, particularly for cases where the measurement data has many uncertainties. More specifically, structural modal parameters derived from vibration responses are first discretized by the K-means clustering technique and the rough set technique is then employed to deal with the great volume of data and to extract optimal feature parameters. After that, the processed data and information are input to the fusion centre of the data fusion technique and fused with the PNN to give a fusion-based damage detection result. To verify the proposed method, two numerical examples are presented to identify both single and multi-damage case patterns. The effects of measurement noise and of non pre-processed rough set data on the damage detection results are also discussed. The results show that the proposed model not only has good damage detection capability and noise tolerance, but also significantly reduces data storage memory requirements and saves runtime as a consequence of the data fusion processing.

[1]  K. Thangavel,et al.  Dimensionality reduction based on rough set theory: A review , 2009, Appl. Soft Comput..

[2]  Hong Hao,et al.  Vibration based damage detection using artificial neural network with consideration of uncertainties , 2007 .

[3]  Lin Ma,et al.  Machinery Fault Diagnosis Based on Feature Level Fuzzy Integral Data Fusion Techniques , 2006, 2006 4th IEEE International Conference on Industrial Informatics.

[4]  Hui Li,et al.  Structural damage identification based on integration of information fusion and shannon entropy , 2008 .

[5]  James H. Garrett,et al.  Use of neural networks in detection of structural damage , 1992 .

[6]  M. Imregun,et al.  Combined neural network and reduced FRF techniques for slight damage detection using measured response data , 2001 .

[7]  D. A. Bell,et al.  Rough Computational Methods for Information , 1998, Artif. Intell..

[8]  Xiaoling Zhang,et al.  Multiway kernel independent component analysis based on feature samples for batch process monitoring , 2009, Neurocomputing.

[9]  Shao-Fei Jiang,et al.  Structural Damage Detection by Integrating Data Fusion and Probabilistic Neural Network , 2006 .

[10]  Jan Ming Ko,et al.  Application of adaptive probabilistic neural network to damage detection of Tsing Ma suspension bridge , 2001, SPIE Smart Structures and Materials + Nondestructive Evaluation and Health Monitoring.

[11]  Andrzej Skowron,et al.  Rough set methods in feature selection and recognition , 2003, Pattern Recognit. Lett..

[12]  Keith Worden,et al.  Damage identification using multivariate statistics: Kernel discriminant analysis , 2000 .

[13]  Ming Yang,et al.  A novel condensing tree structure for rough set feature selection , 2008, Neurocomputing.

[14]  Hoon Sohn,et al.  Damage diagnosis under environmental and operational variations using unsupervised support vector machine , 2009 .

[15]  Qiang Shen,et al.  Semantics-preserving dimensionality reduction: rough and fuzzy-rough-based approaches , 2004, IEEE Transactions on Knowledge and Data Engineering.

[16]  Hong Hao,et al.  Damage identification of structures with uncertain frequency and mode shape data , 2002 .

[17]  D. L. Hall,et al.  Mathematical Techniques in Multisensor Data Fusion , 1992 .

[18]  Zhang Qing-ling.  Design of MATLAB Simulation Tool Box for Rough Set Data Analysis System , 2007 .

[19]  Xavier E. Gros.  Applications of NDT Data Fusion , 2001 .

[20]  Yi-Qing Ni,et al.  Constructing input vectors to neural networks for structural damage identification , 2002 .

[21]  Qunxiong Zhu,et al.  Rough set-based heuristic hybrid recognizer and its application in fault diagnosis , 2009, Expert Syst. Appl..

[22]  T. L. Paez,et al.  Damage identification with probabilistic neural networks , 1995 .

[23]  Sami F. Masri,et al.  Neural Network Approach to Detection of Changes in Structural Parameters , 1996 .

[24]  Young-Min Choi,et al.  Damage assessment of cable stayed bridge using probabilistic neural network , 2004 .

[25]  Bin Xu,et al.  Direct identification of structural parameters from dynamic responses with neural networks , 2004, Eng. Appl. Artif. Intell..

[26]  Dezhao Chen,et al.  Integrated method of compromise-based ant colony algorithm and rough set theory and its application in toxicity mechanism classification , 2008 .

[27]  Zhiwei Lian,et al.  Cooling-load prediction by the combination of rough set theory and an artificial neural-network based on data-fusion technique , 2006 .

[28]  Hoon Sohn,et al.  A review of structural health monitoring literature 1996-2001 , 2002 .

[29]  S. Masri,et al.  Application of Neural Networks for Detection of Changes in Nonlinear Systems , 2000 .

[30]  Nesrin Sarigul-Klijn,et al.  Distance similarity matrix using ensemble of dimensional data reduction techniques: Vibration and aerocoustic case studies , 2009 .

[31]  Hiroshi Motoda,et al.  Feature Selection for Knowledge Discovery and Data Mining , 1998, The Springer International Series in Engineering and Computer Science.

[32]  Donald F. Specht,et al.  Probabilistic neural networks , 1990, Neural Networks.