Novelty detection based on elastic wave signals measured by different techniques

Piotr Nazarko; Leonard Ziemiański

doi:10.24423/cames.82

Piotr Nazarko Rzeszow University of Technology, Rzeszów
Leonard Ziemiański Rzeszow University of Technology, Rzeszów

DOI: http://dx.doi.org/10.24423/cames.82

Abstract

The paper discusses the results of laboratory experiments in which three independent measurement techniques were compared: a digital oscilloscope, phased array acquisition system, a laser vibrometer 3D. These techniques take advantage of elastic wave signals actuated and sensed by a surface-mounted piezoelectric transducers as well as non-contact measurements. In these experiments two samples of aluminum strips were investigated while the damage was modeled by drilling a hole. The structure responses recorded were then subjected to a procedure of signal processing, and features' extraction was done by Principal Components Analysis. A pattern database defined was used to train artificial neural networks for the purpose of damage detection.

Keywords

Artificial neural networks, damage detection, structural health monitoring, elastic waves, non-destructive testing,

References

[1] Y-K. An, B. Park, H. Sohn. Complete noncontact laser ultrasonic imaging for automated crack visualization in a plate, Smart Materials and Structures 22, 2013.
[2] M.R. Hernandez-Garcia, M. Sanchez-Silva. Learning Machines for Structural Damage Detection. In: Lagaros N.D., Tsompanakis Y. [Eds.] Intelligent Computational Paradigms in Earthquake Engineering. Idea Group Publishing, 2007.
[3] M. Jurek, P. Nazarko, L. Ziemiański. Laboratory tests on elastic waves application to damage detection in metal, Plexiglas strips and composite plates. In: Uhl T., Ostachowicz W., Holnicki-Szulc J. [Eds.] Proceedings of the Fourth European Workshop on Structural Health Monitoring, 2008.
[4] K. Kuźniar, Z. Waszczyszyn. Neural Networks and Principal Component Analysis for Identification of Building Natural Periods. Journal of Computing in Civil Engineering, 20: 431–436, 2006.
[5] W.H. Leong, W.J. Staszewski, B.C. Lee, F. Scarpa. Structural health monitoring using scanning laser vibrometry: III. Lamb waves for fatigue crack detection. Smart Materials and Structures, 14: 1387–1395, 2005.
[6] L. Mallet, B.C. Lee, W.J. Staszewski, F. Scarpa. Structural health monitoring using scanning laser vibrometry: II. Lamb waves for damage detection. Smart Materials and Structures, 13: 261–169, 2004.
[7] MATLAB 7.2, Signal Processing Toolbox, Neural Network Toolbox.
[8] P. Nazarko and L. Ziemiański, Towards Application of Soft Computing in Structural Health Monitoring, in Artificial Intelligence and Soft Computing, LNAI 6114: 56-–63, Springer-Verlag Berlin Heidelberg, 2010.
[9] P. Nazarko and L. Ziemiański, Application of artificial neural networks in the damage identification of structural elements, Computer Assisted Mechanics and Engineering Sciences, 18(3): 175–189, 2011.
[10] P. Nazarko, Soft computing methods in the analysis of elastic wave signals and damage identification, Inverse Problems in Science and Engineering (Submitted for publication in January 2013).
[11] W. Ostachowicz, P. Kudela, P. Malinowski, T. Wandowski. Damage localization in plate-like structures based on PZT sensors. Mechanical Systems and Signal Processing, 23: 1805–1829, 2009.
[12] Y. Qian, A. Mita. Acceleration based damage indicators for building structures using neural network emulators. Structural Control and Health Monitoring, 15: 901–920, 2007.
[13] W.J. Staszewski, B.C. Lee, L. Mallet, F. Scarpa. Structural health monitoring using laser vibrometry: I. Lamb wave sensing. Smart Materials and Structures, 13: 251–260, 2004.
[14] W.J. Staszewski, C. Boller, G. Tomlinson. Health Monitoring of Aerospace Structures: Smart Sensor Technologies and Signal Processing. John Wiley & Sons, 2004.
[15] Z. Su, L. Ye. Lamb wave-based quantitative identification of delamination in CF/EP composite structures using artificial neural algorithm. Composite Structures, 66: 627–637, 2004.
[16] Z. Waszczyszyn, L. Ziemiański. Neural networks in the identification analysis of structural mechanics problems. In: Mroz Z., Stavroulakis G.E. [Eds.]. Parameter Identification of Materials and Structures. New York: Springer-Wien, 2005.