Noise removal by cluster analysis after long time AE corrosion monitoring of steel reinforcement in concrete

Abstract Acoustic Emission technique is gaining more and more appreciation in the field of structural health monitoring for reinforced concrete structures. Noise removal and suppression still however remain a concern in AE data analysis. Clustering technique have been proposed in the present work as a tool to overcome this problem. Clustering can, in fact, support the identification of existing underlying relationships among sets of variables related for example to crack growth mechanism or noisy perturbations. It may represent a basic tool not only for classification of known categories, but also for discovery of new relevant classes. In this work different algorithms for automatic clustering and separation of AE events based on multiple features have been adopted. Noise was separated from events of interest and subsequently removed using a combination of different methods like PCA and k-means method. Several validation techniques have also been introduced for AE expression data analysis. Normalization and validity aggregation strategies have been proposed to improve the prediction about the number of relevant clusters. The remaining data have been processed using a self-organizing map (SOM) algorithm.

[1]  Gang Zhang,et al.  Application of Noise Cancelling and Damage Detection Algorithms in NDE of Concrete Bridge Decks Using Impact Signals , 2011 .

[2]  Michalis Vazirgiannis,et al.  On Clustering Validation Techniques , 2001, Journal of Intelligent Information Systems.

[3]  Tomoki Shiotani,et al.  Stress Wave Scattering: Friend or Enemy of Non Destructive Testing of Concrete? , 2008 .

[4]  Teuvo Kohonen,et al.  The self-organizing map , 1990, Neurocomputing.

[5]  Kanji Ono,et al.  DIAGNOSTICS OF REINFORCED CONCRETE BRIDGES BY ACOUSTIC EMISSION , 2002 .

[6]  E. Proverbio.  Evaluation of deterioration in reinforced concrete structures by AE technique , 2011 .

[7]  Thomas Vogel,et al.  Acoustic emission for monitoring a reinforced concrete beam subject to four-point-bending , 2007 .

[8]  Tomoki Shiotani,et al.  The influence of propagation path on elastic waves as measured by acoustic emission parameters , 2012 .

[9]  A. J. Batchelor,et al.  Acoustic emission to assess and monitor the integrity of bridges , 2001 .

[10]  Matteo Falasconi,et al.  Cluster validation for electronic nose data , 2007 .

[11]  J. Hair.  Multivariate data analysis , 1972 .

[12]  Nathalie Godin,et al.  Clustering of acoustic emission signals collected during tensile tests on unidirectional glass/polyester composite using supervised and unsupervised classifiers , 2004 .

[13]  Christian U. Grosse,et al.  Improvements of AE technique using wavelet algorithms, coherence functions and automatic data analysis , 2003 .

[14]  C. S. Cai,et al.  Acoustic emission monitoring of bridges: Review and case studies , 2010 .

[15]  K. Homma,et al.  Analysis of artificial acoustic emission waveforms using a neural network , 1991 .

[16]  Maurizio Vichi,et al.  Studies in Classification Data Analysis and knowledge Organization , 2011 .

[17]  Victor Baranov,et al.  Acoustic Emission in Friction , 2012 .

[18]  Michael Forde,et al.  Assessing Damage of Reinforced Concrete Beam using b -value Analysis of Acoustic Emission Signals , 2003 .

[19]  Thomas Vogel,et al.  Classification of the damage condition of preloaded reinforced , 2010 .

[20]  M. Ohtsu,et al.  Detection and evaluation of AE waves due to rock deformation , 2001 .

[21]  Erkki Oja,et al.  Kohonen Maps , 1999, Encyclopedia of Machine Learning.

[22]  Vladimir Batagelj,et al.  Data Science and Classification , 2006, Studies in Classification, Data Analysis, and Knowledge Organization.

[23]  André Carlos Ponce de Leon Ferreira de Carvalho,et al.  Quality indices for (practical) clustering evaluation , 2009, Intell. Data Anal..

[24]  M. G. R. Sause,et al.  Pattern recognition approach to identify natural clusters of acoustic emission signals , 2012, Pattern Recognit. Lett..

[25]  N. Barkoula,et al.  Acoustic emission characterization of the fracture process in fibre reinforced concrete , 2011 .

[26]  Tomoki Shiotani,et al.  Global Monitoring of Large Concrete Structures Using Acoustic Emission and Ultrasonic Techniques: Case Study , 2009 .

[27]  T. Kohonen.  Self-organized formation of topographically correct feature maps , 1982 .

[28]  D. W. Scott.  On optimal and data based histograms , 1979 .

[29]  Wei-Chien Chang.  On using Principal Components before Separating a Mixture of Two Multivariate Normal Distributions , 1983 .

[30]  M. Forde,et al.  Predicting the ultimate bending capacity of concrete beams from the “relaxation ratio” analysis of AE signals , 2005 .

[31]  Andrew L. Gyekenyesi,et al.  The velocity and attenuation of acoustic emission waves in SiC/SiC composites loaded in tension , 2002 .

[32]  J. A. Brandon,et al.  Classification of acoustic emission signatures using a self-organization neural network , 1999 .

[33]  Tomoki Shiotani,et al.  Damage evaluation of railway structures by using train-induced AE , 2003 .

[34]  R. Gaertner,et al.  Use of acoustic emission to identify damage modes in glass fibre reinforced polyester , 2002 .

[35]  Nathalie Godin,et al.  Integration of the Kohonen's self-organising map and k-means algorithm for the segmentation of the AE data collected during tensile tests on cross-ply composites , 2005 .

[36]  Jian Yang,et al.  Classification of mixed acoustic emission signals via neural networks , 1992, Defense, Security, and Sensing.

[37]  Teuvo Kohonen,et al.  Self-organized formation of topologically correct feature maps , 2004, Biological Cybernetics.

[38]  James Hensman,et al.  A Principal Component Analysis of Acoustic Emission Signals from a Landing Gear Component , 2008 .