Acoustic emission source localization by artificial neural networks

The objective of this work is to present an alternative localization method based on the use of neural networks, using experimental training data as a modeling basis. For this purpose, test sources are applied on the test object to yield input data for a neural network. Subsequently, the trained neural network can be applied to recorded data from material failure of the test object. The presented method is validated using a type III carbon-fiber-reinforced polymer pressure vessel with metallic liner and is compared with an established localization method using the time difference of arrivals. It was shown that the neural-network-based method is not only superior by a factor of 6 in accuracy but also results in a lower scattering of the localized source positions by a factor of 11. For the neural-network-based approach, the localization accuracy is only limited by the theoretical localization accuracy, which is based on measurement errors of the acquisition chain and the subsequent determination of the time of arrival of the detected signal. Source localization using neural networks on the basis of experimental training data thus is very promising to approach the limits of theoretical measurement accuracy.

[1]  John A. Nelder,et al.  A Simplex Method for Function Minimization , 1965, Comput. J..

[2]  Markus G. R. SAUSE,et al.  Localization of Acoustic Emission Sources in Fiber Composites Using Artificial Neural Networks , 2014 .

[3]  Zenon Waszczyszyn,et al.  Identification problems of Recurrent Cascade Neural Network application in predicting an additional mass location , 2017 .

[4]  Alain Thionnet,et al.  Life prediction for carbon fibre filament wound composite structures , 2010 .

[5]  T. Kundu,et al.  Acoustic source localization in anisotropic plates. , 2012, Ultrasonics.

[6]  Fred L. Bookstein,et al.  Principal Warps: Thin-Plate Splines and the Decomposition of Deformations , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Masayasu Ohtsu,et al.  Acoustic Emission Testing , 2006, Advanced Materials Research.

[8]  Tribikram Kundu,et al.  Acoustic source localization. , 2014, Ultrasonics.

[9]  Markus G. R. Sause,et al.  Quantification of the Uncertainty of Pattern Recognition Approaches Applied to Acoustic Emission Signals , 2013 .

[10]  S. Horn,et al.  Quantification of failure mechanisms in mode-I loading of fiber reinforced plastics utilizing acoustic emission analysis , 2012 .

[11]  Michal Blahacek,et al.  Acoustic Emission Source Location Based on Signal Features , 2006 .

[13]  F. L. Matthews,et al.  Composite Materials : Engineering and Science , 1993 .

[14]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[15]  H. Lamb.  On waves in an elastic plate , 1917 .

[16]  Antolino Gallego,et al.  Research and applications of AE on advanced composites , 2012 .

[17]  Markus G. R. Sause,et al.  INVESTIGATION OF PENCIL-LEAD BREAKS AS ACOUSTIC EMISSION SOURCES , 2011 .

[18]  Michael R Wisnom,et al.  A GENERIC TECHNIQUE FOR ACOUSTIC EMISSION SOURCE LOCATION , 2009 .

[19]  Jochen H Kurz,et al.  Strategies for reliable automatic onset time picking of acoustic emissions and of ultrasound signals in concrete. , 2005, Ultrasonics.

[20]  Markus G. R. Sause,et al.  Finite element modeling of lamb wave propagation in anisotropic hybrid materials , 2013 .

[21]  Georg W. Mair,et al.  Acoustic Emission Testing of High-Pressure Composite Cylinders , 2006 .

[22]  K. Toda,et al.  Propagation characteristics of leaky Lamb waves in a liquid-loaded double-layered substrate consisting of a thin piezoelectric ceramic plate and a thin glass plate , 1999 .

[23]  B. Hosten.  Heterogeneous structure of modes and Kramers–Kronig relationship in anisotropic viscoelastic materials , 1998 .

[24]  Dirk Aljets,et al.  Acoustic emission source location in composite aircraft structures using modal analysis , 2011 .