A probabilistic multi-class classifier for structural health monitoring

Abstract In this paper, a probabilistic multi-class pattern recognition algorithm is developed for damage monitoring of smart structures. As these structures can face damages of different severities located in various positions, multi-class classifiers are needed. We propose an original support vector machine (SVM) multi-class clustering algorithm that is based on a probabilistic decision tree (PDT) that produces a posteriori probabilities associated with damage existence, location and severity. The PDT is built by iteratively subdividing the surface and thus takes into account the structure geometry. The proposed algorithm is very appealing as it combines both the computational efficiency of tree architectures and the SVMs classification accuracy. Damage sensitive features are computed using an active approach based on the permanent emission of non-resonant Lamb waves into the structure and on the recognition of amplitude disturbed diffraction patterns. The effectiveness of this algorithm is illustrated experimentally on a composite plate instrumented with piezoelectric elements.

[1]  Luis Roseiro,et al.  Neural networks in damage detection of composite laminated plates , 2005 .

[2]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[3]  E. Peter Carden,et al.  Vibration Based Condition Monitoring: A Review , 2004 .

[4]  Michel Verge,et al.  Structural Damage Diagnosis Using Subspace Based Residual and Artificial Neural Networks , 2009 .

[5]  Tanuja Ganu,et al.  Sparse Max-Margin Multiclass and Multi-label Classifier Design for Fast Inference , 2013, SDM.

[6]  Nazih Mechbal,et al.  Tactile objects based on an amplitude disturbed diffraction pattern method , 2009 .

[7]  Jeong-Beom Ihn,et al.  Pitch-catch Active Sensing Methods in Structural Health Monitoring for Aircraft Structures , 2008 .

[8]  Jiebo Luo,et al.  Learning multi-label scene classification , 2004, Pattern Recognit..

[9]  C. Fritzen,et al.  DAMAGE DETECTION BASED ON MODEL UPDATING METHODS , 1998 .

[10]  Grigorios Tsoumakas,et al.  Multi-Label Classification: An Overview , 2007, Int. J. Data Warehous. Min..

[11]  Shehroz S. Khan,et al.  A Survey of Recent Trends in One Class Classification , 2009, AICS.

[12]  Alex A. Freitas,et al.  A survey of hierarchical classification across different application domains , 2010, Data Mining and Knowledge Discovery.

[13]  Simon Chesne,et al.  Damage localization using transmissibility functions: A critical review , 2013 .

[14]  Nazih Mechbal,et al.  Principal component analysis and perturbation theory–based robust damage detection of multifunctional aircraft structure , 2013 .

[15]  Hao Helen Zhang,et al.  Hard or Soft Classification? Large-Margin Unified Machines , 2011, Journal of the American Statistical Association.

[16]  Ryan M. Rifkin,et al.  In Defense of One-Vs-All Classification , 2004, J. Mach. Learn. Res..

[17]  Rémi Gilleron,et al.  Learning Multi-label Alternating Decision Trees from Texts and Data , 2003, MLDM.

[18]  José Antonio Lozano,et al.  Sensitivity Analysis of k-Fold Cross Validation in Prediction Error Estimation , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  M. Aly.  Survey on Multiclass Classification Methods , 2005 .

[20]  S. Abe,et al.  Why pairwise is better than one-against-all or all-at-once , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[21]  Nicolas Gayton,et al.  A combined Importance Sampling and Kriging reliability method for small failure probabilities with time-demanding numerical models , 2013, Reliab. Eng. Syst. Saf..

[22]  Nazih Mechbal,et al.  Damage monitoring based on wave illumination of structures , 2011 .

[23]  Nicolás García-Pedrajas,et al.  An empirical study of binary classifier fusion methods for multiclass classification , 2011, Inf. Fusion.

[24]  Nazih Mechbal,et al.  Perturbation analysis for robust damage detection with application to multifunctional aircraft structures , 2015 .

[25]  Grant P. Steven,et al.  VIBRATION-BASED MODEL-DEPENDENT DAMAGE (DELAMINATION) IDENTIFICATION AND HEALTH MONITORING FOR COMPOSITE STRUCTURES — A REVIEW , 2000 .

[26]  Thomas G. Dietterich,et al.  Solving Multiclass Learning Problems via Error-Correcting Output Codes , 1994, J. Artif. Intell. Res..

[27]  Chih-Jen Lin,et al.  Asymptotic Behaviors of Support Vector Machines with , 2003 .

[28]  Jason Weston,et al.  Multi-Class Support Vector Machines , 1998 .

[29]  Ayech Benjeddou,et al.  New insights in piezoelectric free-vibrations using simplified modeling and analyses , 2009 .

[30]  Z. Su,et al.  Identification of Damage Using Lamb Waves , 2009 .

[31]  Dejan Gjorgjevikj,et al.  A Multi-class SVM Classifier Utilizing Binary Decision Tree , 2009, Informatica.

[32]  Charles R. Farrar,et al.  Nonlinear System Identification for Damage Detection , 2007 .

[33]  Ehsanollah Kabir,et al.  A subspace approach to error correcting output codes , 2013, Pattern Recognit. Lett..

[34]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[35]  L. Mevel,et al.  Statistical model-based damage detection and localization: subspace-based residuals and damage-to-noise sensitivity ratios , 2004 .

[36]  Domonkos Tikk,et al.  A hierarchical text categorization approach and its application to FRT expansion 1 , 2003 .

[37]  Victor S. Sheng,et al.  Does One-Against-All or One-Against-One Improve the Performance of Multiclass Classifications? , 2013, AAAI.

[38]  Hsuan-Tien Lin,et al.  A note on Platt’s probabilistic outputs for support vector machines , 2007, Machine Learning.

[39]  John Platt,et al.  Probabilistic Outputs for Support vector Machines and Comparisons to Regularized Likelihood Methods , 1999 .

[40]  Nazih Mechbal,et al.  An acoustic multi-touch sensing method using amplitude disturbed ultrasonic wave diffraction patterns , 2010 .

[41]  Charles R. Farrar,et al.  The fundamental axioms of structural health monitoring , 2007, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[42]  Chih-Jen Lin,et al.  Asymptotic Behaviors of Support Vector Machines with Gaussian Kernel , 2003, Neural Computation.

[43]  Marc Rébillat,et al.  Nonlinear structural damage detection based on cascade of Hammerstein models , 2014 .

[44]  Charles R. Farrar,et al.  Structural Health Monitoring: A Machine Learning Perspective , 2012 .

[45]  Zhi-Hua Zhou,et al.  On the Consistency of Multi-Label Learning , 2011, COLT.

[46]  Spilios D. Fassois,et al.  Statistical Time Series Methods for SHM , 2009 .

[47]  Laurent Mevel,et al.  Lptv Subspace Analysis of Wind Turbines Data , 2014 .

[48]  Nello Cristianini,et al.  Large Margin DAGs for Multiclass Classification , 1999, NIPS.

[49]  Nazih Mechbal,et al.  Probabilistic decision trees using SVM for multi-class classification , 2013, 2013 Conference on Control and Fault-Tolerant Systems (SysTol).

[50]  Lin Ye,et al.  Guided Lamb waves for identification of damage in composite structures: A review , 2006 .

[51]  Chih-Jen Lin,et al.  A comparison of methods for multiclass support vector machines , 2002, IEEE Trans. Neural Networks.