Classifying Induced Damage in Composite Plates Using One-Class Support Vector Machines

For many engineering and aerospace applications, detection and quantification of multiscale damage in fiber-reinforced composite structures is increasing in importance. Consequently, the development of an efficient and cost-effective diagnosis scheme that can accurately sense, characterize, and evaluate the existence of any form of damage will offer significant potential for improving the performance, reliability, and extending the operational life of these complex systems. We present an approach to characterize and classify different damage states in composite laminates by measuring the change in the signature of the resultant wave that propagates through the anisotropic media under forced excitation. The wave propagation is measured using surface-mounted piezoelectric transducers. Sensor signals collected from test specimens with various forms of induced damage are analyzed using a pattern-recognition algorithm known as the one-class support vector machines. The one-class support-vector-machine algorithm performs automatic anomaly detection and classification of damage signatures using various features from the sensor readings. The results obtained suggest that the one-class support-vector-machine algorithm, along with appropriate preprocessing techniques, can often achieve better accuracy than the popular k-nearest-neighbor method in detecting and classifying anomalies caused by structural defects, even when the perturbations caused in the sensor signals due to different damage states are minimal.

[1]  Keith Worden,et al.  TIME–FREQUENCY ANALYSIS IN GEARBOX FAULT DETECTION USING THE WIGNER–VILLE DISTRIBUTION AND PATTERN RECOGNITION , 1997 .

[2]  Mark Schwabacher.  Machine Learning for Rocket Propulsion Health Monitoring , 2005 .

[3]  P. Cawley,et al.  The interaction of Lamb waves with delaminations in composite laminates , 1993 .

[4]  Fu-Kuo Chang,et al.  Impact damage diagnostics for composite structures using built-in sensors and actuators , 1996, Other Conferences.

[5]  Bernhard Schölkopf,et al.  Estimating the Support of a High-Dimensional Distribution , 2001, Neural Computation.

[6]  Rolf Isermann.  Model-based fault-detection and diagnosis - status and applications § , 2004 .

[7]  Antonia Papandreou-Suppappola,et al.  Analysis and classification of time-varying signals with multiple time-frequency structures , 2002, IEEE Signal Processing Letters.

[8]  Jun Zhang,et al.  Time series prediction using Lyapunov exponents in embedding phase space , 1998, SMC'98 Conference Proceedings. 1998 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.98CH36218).

[9]  R. Akella,et al.  Discovering Atypical Flights in Sequences of Discrete Flight Parameters , 2006, 2006 IEEE Aerospace Conference.

[10]  V. Giurgiutiu.  Tuned Lamb Wave Excitation and Detection with Piezoelectric Wafer Active Sensors for Structural Health Monitoring , 2005 .

[11]  Irem Y. Tumer,et al.  Analysis of Triaxial Vibration Data for Health Monitoring of Helicopter Gearboxes , 2003 .

[12]  Irene Yu-Hua Gu,et al.  Support Vector Machine for Classification of Voltage Disturbances , 2007, IEEE Transactions on Power Delivery.

[13]  O. Bousquet,et al.  Kernel methods and their potential use in signal processing , 2004, IEEE Signal Processing Magazine.

[14]  Jennifer E. Michaels,et al.  A comparison of feature-based classifiers for ultrasonic structural health monitoring , 2004, SPIE Smart Structures and Materials + Nondestructive Evaluation and Health Monitoring.

[15]  Fu-Kuo Chang,et al.  Structural Health Monitoring: Current Status and Perspectives , 1998 .

[16]  Jeong-Beom Ihn,et al.  A Potential Link from Damage Diagnostics to Health Prognostics of Composites through Built-in Sensors , 2007 .

[17]  Ron J. Patton,et al.  Fault diagnosis using quantitative and qualitative knowledge integration , 1996 .

[18]  Stephen D. Bay,et al.  Mining distance-based outliers in near linear time with randomization and a simple pruning rule , 2003, KDD '03.

[19]  J.J. Gertler,et al.  Survey of model-based failure detection and isolation in complex plants , 1988, IEEE Control Systems Magazine.

[20]  Nello Cristianini,et al.  Kernel Methods for Pattern Analysis , 2003, ICTAI.

[21]  Antonia Papandreou-Suppappola,et al.  Detecting faults in structures using time-frequency techniques , 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

[22]  Yong Zhang,et al.  Application of support vector machines to sensor fault diagnosis in ESP system , 2004, Proceedings of 2004 International Conference on Machine Learning and Cybernetics (IEEE Cat. No.04EX826).

[23]  Jun Zhang,et al.  Time Series Prediction Using Lyapunov Exponents In Embedding Phase Space , 1998, SMC'98 Conference Proceedings. 1998 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.98CH36218).

[24]  Mark Schwabacher,et al.  A Survey of Data -Driven Prognostics , 2005 .

[25]  Fulei Chu,et al.  Support vector machines-based fault diagnosis for turbo-pump rotor , 2006 .

[26]  Constantinos Soutis,et al.  Lamb waves for the non-destructive inspection of monolithic and sandwich composite beams , 2005 .

[27]  Hyun Joon Shin,et al.  One-class support vector machines - an application in machine fault detection and classification , 2005, Comput. Ind. Eng..

[28]  Antonia Papandreou-Suppappola,et al.  Classification of Acoustic Emissions Using Modified Matching Pursuit , 2004, EURASIP J. Adv. Signal Process..

[29]  Fujun He,et al.  WPT-SVMs based approach for fault detection of valves in reciprocating pumps , 2002, Proceedings of the 2002 American Control Conference (IEEE Cat. No.CH37301).

[30]  Constantinos Soutis,et al.  Detection of Low-velocity Impact Damage in Composite Plates using Lamb Waves , 2004 .

[31]  Alexander J. Smola,et al.  Advances in Large Margin Classifiers , 2000 .

[32]  A. Papandreou-Suppappola,et al.  Monte Carlo Matching Pursuit Decomposition Method for Damage Quantification in Composite Structures , 2009 .

[33]  Biswanath Samanta,et al.  Bearing Fault Detection Using Artificial Neural Networks and Genetic Algorithm , 2004, EURASIP J. Adv. Signal Process..

[34]  Qin Ding,et al.  k-nearest Neighbor Classification on Spatial Data Streams Using P-trees , 2002, PAKDD.

[35]  David L. Iverson.  Inductive System Health Monitoring , 2004, IC-AI.

[36]  R. J. Shuford,et al.  Acoustic emission signal detection by ceramic/polymer composite piezoelectrets embedded in glass‐epoxy laminates , 1996 .

[37]  George Vachtsevanos,et al.  Fault prognosis using dynamic wavelet neural networks , 2001, 2001 IEEE Autotestcon Proceedings. IEEE Systems Readiness Technology Conference. (Cat. No.01CH37237).

[38]  Pfister,et al.  Optimal delay time and embedding dimension for delay-time coordinates by analysis of the global static and local dynamical behavior of strange attractors. , 1992, Physical review. A, Atomic, molecular, and optical physics.

[39]  Li Ling-jun,et al.  Support Vector Machine for mechanical faults classification , 2005 .

[40]  Charles R. Farrar,et al.  Damage identification and health monitoring of structural and mechanical systems from changes in their vibration characteristics: A literature review , 1996 .

[41]  Satish S. Udpa,et al.  Feature extraction techniques for ultrasonic signal classification , 2002 .

[42]  Keith Worden,et al.  Damage identification using support vector machines , 2001 .