A data mining approach to the diagnosis of failure modes for two serial fastened sandwich composite plates

Abstract

The aim of this study is to diagnose and classify the failure modes for two serial fastened sandwich composite plates using data mining techniques. The composite material used in the study was manufactured using glass fiber reinforced layer and aluminum sheets. Obtained results of previous experimental study for sandwich composite plates, which were mechanically fastened with two serial pins or bolts were used for classification of failure modes. Furthermore, experimental data from previous study consists of different geometrical parameters for various applied preload moments as 0 (pinned), 2, 3, 4, and 5 Nm (bolted). In this study, data mining methods were applied by using these geometrical parameters and pinned/bolted joint configurations. Therefore, three geometrical parameters and 100 test data were used for classification by utilizing support vector machine, Naive Bayes, K-Nearest Neighbors, Logistic Regression, and Random Forest methods. According to experiments, Random Forest method achieved better results than others and it was appropriate for diagnosing and classification of the failure modes. Performances of all data mining methods used were discussed in terms of accuracy and error ratios.

Keywords

Data mining classification random forest logistic regression sandwich composite

Get full access to this article

View all access options for this article.

References

Han

Kamber

. Data mining: Concepts and techniques, San Francisco: Morgan Kaufmann Publishers, 2006.

Choudhary

Harding

Tiwari

. Data mining in manufacturing: a review based on the kind of knowledge. J Intell Manuf 2009; 20: 501–521.

Sayman

Siyahkoc

Sen

et al.

Experimental determination of bearing strength in fiber reinforced laminated composite bolted-joints under preload. J Reinf Plast Compos 2007; 26: 1051–1063.

Pakdil

Sen

Sayman

et al.

The effect of preload on failure response of glass-epoxy laminated composite bolted-joints with clearance. J Reinf Plast Compos 2007; 26: 1239–1252.

Ataş

Sen

Arslan

. Failure analysis of laminated composite plates with two parallel pin-loaded holes. J Reinf Plast Compos 2009; 28: 1265–1276.

Caprino

Squillace

Giorleo

et al.

Pin and bolt bearing strength of fibreglass/aluminium laminates. Compos Part A: Appl Sci Manuf 2005; 36: 1307–1315.

Sen

Sayman

. Failure response of two serial bolted aluminum sandwich composite plates. J Sandwich Struct Mater 2010; 12: 551–568.

Komur

Sen

Sayman

. The prediction of maximum failure loads of two serial pinned/bolted composite joints with ANN. J Adv Mater 2011; 43: 902–103.

Balli

Sen

. Failure Prediction of cross-ply laminated double-serial mechanically fastened composites using fuzzy expert system. Strojniški vestnik-J Mech Eng 2015; 61: 123–130.

10.

Sen

Balli

. Application of a fuzzy expert system for failure load estimation of two serial pinned or bolted sandwich composite plates. Mater Test 2016; 58: 343–349.

11.

Das S, Srivastava AN and Chattopadhyay A. Classification of damage signatures in composite plates using one-class SVMs. In: IEEE Aerospace Conference Proceedings, 2007, pp.1–19.

12.

Watkins

Akhavan

Dua

et al.

Impact-induced damage characterization of composite plates using neural networks. Smart Mater Struct 2007; 16: 515–515.

13.

Arumugam

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.

14.

McCrory

Al-Jumaili

Crivelli

et al.

Damage classification in carbon fibre composites using acoustic emission: A comparison of three techniques. Compos Part B: Eng 2015; 68: 424–430.

15.

İçten

Sayman

. Failure analysis of pin-loaded aluminum-glass-epoxy sandwich composite plates. Compos Sci Technol 2003; 63: 727–737.

16.

Chang

Scott

Springer

. Strength of mechanically fastened composite joints. J Compos Mater 1982; 16: 470–494.

17.

Okutan

. The effects of geometric parameters on the failure strength for pin-loaded multi-directional fiber-glass reinforced epoxy laminate. Compos Part B: Eng 2002; 33: 567–578.

18.

Mallick

. Fiber-reinforced composites materials, manufacturing, and design, 2nd ed. New York: Marcel Decker, 1993.

19.

Kradinov

Madenci

Ambur

. Combined in-plane and through-the-thickness analysis for failure prediction of bolted composite joints. Compos Struct 2007; 77: 127–147.

20.

Whitworth

Othieno

Barton

. Failure analysis of composite pin loaded joints. Compos Struct 2003; 59: 261–266.

21.

Hand

Mannila

Smyth

. Principles of data mining, Massachusetts: MIT Press, 2001.

22.

Cortes

Vapnik

. Support-vector networks. Mach Learn 1995; 20: 273–297.

23.

Cristianini

Shawe-Taylor

. An introduction to support vector machines and other kernel-based learning methods, Cambridge, UK: Cambridge University Press, 2000.

24.

Mitchell

. Machine learning, New York: McGraw-Hill Education, 1997.

25.

Witten

Frank

. Data mining: Practical machine learning tools and techniques, San Francisco, CA: Morgan Kaufmann Publishers, 2005.

26.

Feng

Mannor

et al.

Robust logistic regression and classification. In: Ghahramani

Welling

Cortes

et al. (eds). Advances in neural information processing systems 27, New York: Curran Associates, 2014, pp. 253–261.

27.

Breiman

. Random forests. Mach Learn 2001; 45: 5–32.

28.

Díaz-Uriarte

De Andres

. Gene selection and classification of microarray data using random forest. BMC Bioinform 2006; 7: 3–3.

29.

Breiman

Friedman

Stone

et al.

Classification and regression trees, New York: Chapman & Hall, 1984.

30.

Hall

Frank

Holmes

et al.

The WEKA data mining software: an update. ACM SIGKDD Explor Newslett 2009; 11: 10–18.