Optimization of acoustic emission parameters to discriminate failure modes in glass–epoxy composite laminates using pattern recognition

Abstract

In this article, to overcome the challenges encountered during the discrimination of various failure modes in post impacted/indented glass-fiber-reinforced plastic, techniques like pattern recognition method and advanced signal processing were employed. The significant acoustic emission parameters such as amplitude, rise time, counts, energy, duration, and peak frequency that are acquired during compression after impact test are considered as inputs to cluster validity index and for various clustering techniques such as k-means, fuzzy C-means, and Kohonen’s self-organizing map. The acoustic emission count–frequency and amplitude–frequency have no overlapping, whereas other combinations of acoustic emission parameters result in overlapping with four clusters. The clustering techniques are validated by discrete wavelet transform of acoustic emission signals. The discrete wavelet transform was performed on the clustered acoustic emission signals to identify the percentage of energy and frequency content of each level which correlates the different failure modes. The results infer that k-means, fuzzy C-means clustering, and Kohonen’s self-organizing map are 94.5%, 97.1%, and 98.6% reliability, respectively, clearly suggesting Kohonen’s self-organizing map as the most appropriate technique for the classification of acoustic emission signature.

Keywords

Glass-fiber-reinforced plastics compression after impact acoustic emission failure mechanism pattern recognition wavelet analysis

Get full access to this article

View all access options for this article.

References

Johnson

Classification of AE transients based on numerical simulations of composite laminates. NDT & E Int 2003; 36(1): 319–329.

Godin

Huguet

Gaertner

Integration of the Kohonen’s self organizing map and K-means algorithms for the segmentation of the AE data collected during tensile tests on cross ply composites. NDT&E Int 2005; 38: 299–309.

Philippidis

Nikolaidis

Anastassopoulos

AA.

Damage characterization of carbon/carbon laminates using neural network techniques on AE signals. NDT&E Int 1998; 31: 329–340.

De Oliveira

Marques

. Health monitoring of FRP using acoustic emission and artificial neural network. Comput Struct 2008; 86: 367–373.

Wevers

Listening to the sound of materials: acoustic emission for the analysis of material behavior. NDT&E Int 1997; 30(2): 99–106.

Barre

Benzeggagh

ML.

On the use of acoustic emission to investigate damage mechanism in glass-fiber-reinforced polypropylene. Compos Sci Technol 1994; 52: 369–376.

Bar

Bhat

Murthy

CRL

et al . Parametric analysis of acoustic emission signals for evaluating damage in composites using PVDF film sensors. NDT&E Int 2005; 24: 121–134.

Prosser

WH.

Applications of advanced waveform-based AE techniques for testing composite materials. In: Proceedings of the SPIE conference on nondestructive evaluation techniques for aging infrastructure and manufacturing materials and composites, Scottsdale, AZ, 2–5 December 1996, pp. 146–153. Washington, DC: SPIE.

Dzenis

Qian

Analysis of micro damage evolution histories in composites. Int J Solid Struct 2001; 38: 1831–1854.

10.

Yuki

Homma

Analysis of artificial acoustic emission waveforms using a neural network. J Acoust Emiss 1992; 10(3–4): 35–41.

11.

Anastassopoulos

Philippidis

TP.

Clustering methodology for the evaluation of acoustic emission from composites. J Acoust Emiss 1995; 13(1–2): 11–22.

12.

Belchamber

Betteridge

Chow

et al . Evaluation of pattern recognition analysis of acoustic emission from stressed polymers and composites. J Acoust Emiss 1985; 4: 71–83.

13.

Marec

Thomas

Guerjouma

et al . Damage characterization of polymer-based composites materials: multivariable analysis and wavelet transform for clustering acoustic emission data. Mech Syst Signal Process 2008; 22: 1441–1464.

14.

Johnson

Waveform based clustering and classification of AE transients in composite laminates using principal component analysis. NDT&E Int 2002; 35: 367–376.

15.

Suresh Kumar

Arumugam

Sajith

et al . Acoustic emission characterisation of failure modes in hemp/epoxy and glass/epoxy composite laminates. J Nondestruct Eval 2015; 34(4): 1–11.

16.

Pashmforoush

Fotouhi

Ahmadi

Acoustic emission-based damage classification of glass/polyester composites using harmony search k-means algorithm. J Reinf Plast Comp 2012; 31(10): 671–680.

17.

Fotouhi

Heidary

Ahmadi

et al . Characterization of composite materials damage under quasi-static three-point bending test using wavelet and fuzzy C-means clustering. J Compos Mater 2012; 46(15): 1795–1808.

18.

Kenji

Ono

Pattern recognition of acoustic emission signals from carbon fiber/epoxy composites. In: Proceedings of the 7th international acoustic emission symposium (IAES), London, 10–12 June 1987.

19.

Godin

Huguet

Gaertner

et al . Clustering of acoustic emission signals collected during tensile tests on unidirectional glass/polyester composite using supervised and unsupervised classifiers. NDT&E Int 2004; 37: 253–264.

20.

Huguet

Godin

Gaertner

et al . Use of acoustic emission to identify damage modes in glass fiber reinforced polyester. Compos Sci Technol 2002; 62: 1433–1444.

21.

Suresh Kumar

Arumugam

Sengottuvelusamy

et al . Failure strength prediction of glass/epoxy composite laminates from acoustic emission parameters using artificial neural network. Appl Acoust 2017; 115: 32–41.

22.

Yan

Holford

Carter

et al . Classification of acoustic emission signatures using a self-organization neural network. J Acoust Emiss 1999; 17(1–2): 49–59.

23.

Gutkin

Green

Vangrattanachai

et al . On acoustic emission for failure investigation in CFRP: pattern recognition and peak frequency analyses. Mech Syst Signal Pr 2011; 25: 1393–1407.

24.

Arumugam

Suresh Kumar

Santulli

et al . Identification of failure modes in composites from clustered acoustic emission data using pattern recognition and wavelet transformation. Arab J Sci Eng 2013; 38: 1087–1102.

25.

Arumugam

Suresh Kumar

Santulli

et al . A global method for the identification of failure modes in fiber glass using acoustic emission. J Test Eval 2011; 39(5): 103730.

26.

Ono

Huang

Pattern recognition analysis of acoustic emission signals, progress in acoustic emission VII. In: Proceedings of the 12th international acoustic emission symposium, Sapporo, Japan, 17–20 October 1994, pp. 69–78. Tokyo, Japan: Japanese Society of NDI.

27.

Davies

Bouldin

DW.

A cluster separation measure. IEEE T Pattern Anal 1979; PAMI-1: 224–227.

28.

Rousseeuw

. Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. J Comput Appl Math 1987; 20: 53–65.

29.

Likas

Vlassis

Verbeek

The global k-means clustering algorithm. Pattern Recogn 2003; 366(2): 451–461.

30.

Kohonen

Self-organized network. Proc IEEE 1990; 43: 59–69.

31.

Vesanto

Himberg

Alhoniemi

et al . Self-organizing map in MATLAB: the SOM toolbox. In: Proceedings of the MATLAB DSP, Espoo, 16–17 November 1999.