Research Papers

Multisource Data Fusion for Classification of Surface Cracks in Steel Pipes

[+] Author and Article Information
Samir Mustapha

Department of Mechanical Engineering,
Maroun Semaan Faculty of
Engineering and Architecture,
American University of Beirut,
Beirut 1107 2020, Lebanon;
Laboratory of Smart Materials and
Structures (LSMS),
School of Aerospace, Mechanical and
Mechatronic Engineering,
The University of Sydney,
Sydney 2006, New South Wales, Australia
e-mail: sm154@aub.edu.lb

Ali Braytee

Quantum Computation and Intelligent Systems,
University of Technology Sydney,
Sydney 2007, Australia
e-mail: ali.braytee@uts.edu.au

Lin Ye

Laboratory of Smart Materials and
Structures (LSMS),
School of Aerospace, Mechanical and
Mechatronic Engineering,
The University of Sydney,
Sydney 2006, New South Wales, Australia
e-mail: lin.ye@sydney.edu.au

1Corresponding author.

Manuscript received September 9, 2017; final manuscript received December 20, 2017; published online January 24, 2018. Assoc. Editor: Hoon Sohn.

ASME J Nondestructive Evaluation 1(2), 021007 (Jan 24, 2018) (11 pages) Paper No: NDE-17-1093; doi: 10.1115/1.4038862 History: Received September 21, 2017; Revised December 20, 2017

This paper focuses on the development and validation of a robust framework for surface crack detection and assessment in steel pipes based on measured vibration responses collected using a network of piezoelectric (PZT) wafers. The pipe structure considered in this study contained multiple progressive cracks occurring at different locations and with various orientations (along the circumference or length). The fusion of data collected from multiple PZT wafers was investigated based on two approaches: (a) combining the raw data from all sensors before establishing a statistical model for damage classification and (b) combining the features from each sensor after applying a multiclass support vector machine recursive feature elimination (MCSVM-RFE), for dimensionality reduction, and taking the union of discriminative features among the different sources of data. A MCSVM learning algorithm was employed to train the data and generate a statistical classifier. The dataset consisted of ten classes, consisting of nine damage cases and the healthy state. The accuracy of the prediction based on the two fusion approaches resulted in a high accuracy, exceeding 95%, but the number of features needed to enrich the accuracy (95%) differed between the two approaches. Furthermore, the performance and the precision in the prediction of the classifier were evaluated when the data from only a single sensor was used compared with the combined data from all the sensors within the network. Very promising results in the classification of damage were obtained, based on the case study that included multiple damage scenarios with different lengths and orientations.

Copyright © 2018 by ASME
Your Session has timed out. Please sign back in to continue.


Konar, P. , and Chattopadhyay, P. , 2011, “ Bearing Fault Detection of Induction Motor Using Wavelet and Support Vector Machines (SVMs),” Appl. Soft Comput., 11(6), pp. 4203–4211. [CrossRef]
Fakih, M. A. , Mustapha, S. , Tarraf, J. , Ayoub, G. , and Hamade, R. , 2018, “ Detection and Assessment of Flaws in Friction Stir Welded Joints Using Ultrasonic Guided Waves: Experimental and Finite Element Analysis,” Mech. Syst. Signal Process., 101(Suppl. C), pp. 516–534. [CrossRef]
Kishawy, H. A. , and Gabbar, H. A. , 2010, “ Review of Pipeline Integrity Management Practices,” Int. J. Pressure Vessels Piping, 87(7), pp. 373–380. [CrossRef]
Lowe, M. J. S. , and Cawley, P. , 2006, “Long Range Guided Wave Inspection Usage–Current Commercial Capabilities and Research Directions,” Imperial College London, London.
Jarvis, R. , Cawley, P. , and Nagy, P. B. , 2016, “ Current Deflection NDE for Pipeline Inspection and Monitoring,” AIP Conf. Proc., 1706(1), p. 160002.
Chang, P. C. , Flatau, A. , and Liu, S. C. , 2003, “ Review Paper: Health Monitoring of Civil Infrastructure,” Struct. Health Monit., 2(3), pp. 257–267. [CrossRef]
Lie, S. T. , Zhang, Y. , and Wang, L. Q. , 2015, “ Damage Detection in Compressed Natural Gas (CNG) Cylinders Based on Auxiliary Mass Induced Frequency Shift,” Exp. Mech., 55(3), pp. 487–498. [CrossRef]
Fassois, S. D. , and Sakellariou, J. S. , 2009, “ Statistical Time Series Methods for SHM,” Encyclopedia of Structural Health Monitoring, Wiley, Hoboken, NJ. [CrossRef]
Makki Alamdari, M. , Li, J. , and Samali, B. , 2015, “ Damage Identification Using 2-D Discrete Wavelet Transform on Extended Operational Mode Shapes,” Arch. Civ. Mech. Eng., 15(3), pp. 698–710. [CrossRef]
Barthorpe, R. J. , and Worden, K. , 2011, “ Classification of Multi-Site Damage Using Support Vector Machines,” J. Phys.: Conf. Ser., 305(1), p. 012059. [CrossRef]
Byvatov, E. , Fechner, U. , Sadowski, J. , and Schneider, G. , 2003, “ Comparison of Support Vector Machine and Artificial Neural Network Systems for Drug/Nondrug Classification,” J. Chem. Inf. Comput. Sci., 43(6), pp. 1882–1889. [CrossRef] [PubMed]
Ghiasi, R. , Torkzadeh, P. , and Noori, M. , 2016, “ A Machine-Learning Approach for Structural Damage Detection Using Least Square Support Vector Machine Based on a New Combinational Kernel Function,” Struct. Health Monit., 15(3), pp. 302–316. [CrossRef]
Worden, K. , and Lane, A. , 2001, “ Damage Identification Using Support Vector Machines,” Smart Mater. Struct., 10(3), p. 540. [CrossRef]
Yuan, S.-F. , and Chu, F.-L. , 2006, “ Support Vector Machines-Based Fault Diagnosis for Turbo-Pump Rotor,” Mech. Syst. Signal Process., 20(4), pp. 939–952. [CrossRef]
Sbarufatti, C. , Manson, G. , and Worden, K. , 2014, “ A Numerically-Enhanced Machine Learning Approach to Damage Diagnosis Using a Lamb Wave Sensing Network,” J. Sound Vib., 333(19), pp. 4499–4525. [CrossRef]
Farrar, C. R. , and Worden, K. , 2012, “ Unsupervised Learning—Novelty Detection,” Structural Health Monitoring, Wiley, Chichester, UK, pp. 321–360. [CrossRef]
Farrar, C. R. , and Worden, K. , 2012, “ Supervised Learning—Classification and Regression,” Structural Health Monitoring, Wiley, Chichester, UK, pp. 361–401. [CrossRef]
Cortes, C. , and Vapnik, V. , 1995, “ Support-Vector Networks,” Mach. Learn., 20(3), pp. 273–297.
Hsu, C.-W. , and Lin, C.-J. , 2002, “ A Comparison of Methods for Multiclass Support Vector Machines,” IEEE Trans. Neural Networks, 13(2), pp. 415–425. [CrossRef]
Auria, L. , and Moro, R. A. , 2008, “Support Vector Machines (SVM) as a Technique for Solvency Analysis,” Discussion Paper, DIW, Berlin, pp. 1–16.
Cyganek, B. , 2008, “ Color Image Segmentation With Support Vector Machines: Applications to Road Signs Detection,” Int. J. Neural Syst., 18(4), pp. 339–345. [CrossRef] [PubMed]
Huynh, C. P. , Mustapha, S. , Runcie, P. , and Porikli, F. , 2015, “ Multi-Class Support Vector Machines for Paint Condition Assessment on the Sydney Harbour Bridge Using Hyperspectral Imaging,” Struct. Monit. Maint., 2(3), pp. 181–197.
Alamdari, M. M. , Samali, B. , Li, J. , Kalhori, H. , and Mustapha, S. , 2016, “ Spectral-Based Damage Identification in Structures Under Ambient Vibration,” J. Comput. Civ. Eng., 30(4), p. 04015062. [CrossRef]
Khoa, N. L. D. , Zhang, B. , Wang, Y. , Chen, F. , and Mustapha, S. , 2014, “ Robust Dimensionality Reduction and Damage Detection Approaches in Structural Health Monitoring,” Struct. Health Monit., 13(4), pp. 406–417. [CrossRef]
HosseinAbadi, H. Z. , Amirfattahi, R. , Nazari, B. , Mirdamadi, H. R. , and Atashipour, S. A. , 2014, “ GUW-Based Structural Damage Detection Using WPT Statistical Features and Multiclass SVM,” Appl. Acoust., 86, pp. 59–70. [CrossRef]
Widodo, A. , Kim, E. Y. , Son, J.-D. , Yang, B.-S. , Tan, A. C. C. , Gu, D.-S, Choi, B.-K. , and Mathew, J. , 2009, “ Fault Diagnosis of Low Speed Bearing Based on Relevance Vector Machine and Support Vector Machine,” Expert Syst. Appl., 36(3), pp. 7252–7261.
Yang, B.-S. , Han, T. , and Hwang, W.-W. , 2005, “ Fault Diagnosis of Rotating Machinery Based on Multi-Class Support Vector Machines,” J. Mech. Sci. Technol., 19(3), pp. 846–859. [CrossRef]
Yeesock, K. , Jo Woon, C. , Ki, H. C. , and JungMi, K. , 2013, “ Wavelet-Based AR–SVM for Health Monitoring of Smart Structures,” Smart Mater. Struct., 22(1), p. 015003. [CrossRef]
Saeys, Y. , Inza, I. , and Larrañaga, P. , 2007, “ A Review of Feature Selection Techniques in Bioinformatics,” Bioinformatics, 23(19), pp. 2507–2517. [CrossRef] [PubMed]
Khatibinia, M. , Javad Fadaee, M. , Salajegheh, J. , and Salajegheh, E. , 2013, “ Seismic Reliability Assessment of RC Structures Including Soil–Structure Interaction Using Wavelet Weighted Least Squares Support Vector Machine,” Reliab. Eng. Syst. Saf., 110, pp. 22–33. [CrossRef]
Sohn, H. , Czarnecki, J. A. , and Farrar, C. R. , 2000, “ Structural Health Monitoring Using Statistical Process Control,” J. Struct. Eng., 126(11), pp. 1356–1363. [CrossRef]
Worden, K. , and Manson, G. , 1999, “ Visualisation and Dimension Reduction of High-Dimensional Data for Damage Detection,” 17th International Modal Analysis Conference, Kissimmee, FL, Feb. 8–11, pp. 1576–1585. https://pdfs.semanticscholar.org/5eb4/3e944b27287591646e05317d99a99910ffff.pdf
Zang, C. , and Imregun, M. , 2001, “ Structural Damage Detection Using Artificial Neural Networks and Measured FRF Data Reduced Via Principal Component Projection,” J. Sound Vib., 242(5), pp. 813–827. [CrossRef]
Zang, C. , Friswell, M. I. , and Imregun, M. , 2004, “ Structural Damage Detection Using Independent Component Analysis,” Struct. Health Monit., 3(1), pp. 69–83. [CrossRef]
Keogh, E. , Chakrabarti, K. , Pazzani, M. , and Mehrotra, S. , 2001, “ Dimensionality Reduction for Fast Similarity Search in Large Time Series Databases,” Knowl. Inf. Syst., 3(3), pp. 263–286. [CrossRef]
Zhou, Q. , Zhou, H. , Zhou, Q. , Yang, F. , and Luo, L. , 2014, “ Structure Damage Detection Based on Random Forest Recursive Feature Elimination,” Mech. Syst. Signal Process., 46(1), pp. 82–90. [CrossRef]
Statnikov, A. , Wang, L. , and Aliferis, C. F. , 2008, “ A Comprehensive Comparison of Random Forests and Support Vector Machines for Microarray-Based Cancer Classification,” BMC Bioinf., 9(1), p. 319. [CrossRef]
Guyon, I. , Weston, J. , Barnhill, S. , and Vapnik, V. , 2002, “ Gene Selection for Cancer Classification Using Support Vector Machines,” Mach. Learn., 46(1–3), pp. 389–422. [CrossRef]
Zhou, X. , and Tuck, D. P. , 2007, “ MSVM-RFE: Extensions of SVM-RFE for Multiclass Gene Selection on DNA Microarray Data,” Bioinformatics, 23(9), pp. 1106–1114. [CrossRef] [PubMed]
Alamdari, M. M. , Rakotoarivelo, T. , and Khoa, N. L. D. , 2017, “ A Spectral-Based Clustering for Structural Health Monitoring of the Sydney Harbour Bridge,” Mech. Syst. Signal Process., 87(Pt. A), pp. 384–400. [CrossRef]
Diez, A. , Khoa, N. L. D. , Makki Alamdari, M. , Wang, Y. , Chen, F. , and Runcie, P. , 2016, “ A Clustering Approach for Structural Health Monitoring on Bridges,” J. Civ. Struct. Health Monit., 6(3), pp. 429–445. [CrossRef]
Vapnik, V. N. , and Vapnik, V. , 1998, Statistical Learning Theory, Vol. 1, Wiley, New York.
Knerr, S. , Personnaz, L. , and Dreyfus, G. , 1990, “ Single-Layer Learning Revisited: A Stepwise Procedure for Building and Training a Neural Network,” Neurocomputing, Springer, Berlin, pp. 41–50. [CrossRef]
Bottou, L. , Cortes, C. , Denker, J. S. , Drucker, H. , Guyon, I. , Jackel, L. D. , LeCun, Y. , Muller, U. A. , Sackinger, E. , Simard, P. , and Vapnik, V. , 1994, “ Comparison of Classifier Methods: A Case Study in Handwritten Digit Recognition,” 12th IAPR International Conference on Pattern Recognition (Conference B: Computer Vision and Image Processing, Jerusalem, Israel, Oct. 9–13, pp. 77–82.
Banks, H. T. , Inman, D. J. , Leo, D. J. , and Wang, Y. , 1996, “ An Experimentally Validated Damage Detection Theory in Smart Structures,” J. Sound Vib., 191(5), pp. 859–880. [CrossRef]
Makki Alamdari, M. , Li, J. , and Samali, B. , 2014, “ FRF-Based Damage Localization Method With Noise Suppression Approach,” J. Sound Vib., 333(14), pp. 3305–3320. [CrossRef]
Ko, M. H. , West, G. , Venkatesh, S. , and Kumar, M. , 2008, “ Using Dynamic Time Warping for Online Temporal Fusion in Multisensor Systems,” Inf. Fusion, 9(3), pp. 370–388. [CrossRef]
Pires, I. , Garcia, N. , Pombo, N. , and Flórez-Revuelta, F. , 2016, “ From Data Acquisition to Data Fusion: A Comprehensive Review and a Roadmap for the Identification of Activities of Daily Living Using Mobile Devices,” Sensors, 16(2), p. 184. [CrossRef] [PubMed]
Dasarathy, B. V. , 1994, Decision Fusion, Vol. 1994, IEEE Computer Society Press, Los Alamitos, CA. [PubMed] [PubMed]
Hanley, J. A. , and McNeil, B. J. , 1982, “ The Meaning and Use of the Area Under a Receiver Operating Characteristic (ROC) Curve,” Radiology, 143(1), pp. 29–36. [CrossRef] [PubMed]


Grahic Jump Location
Fig. 1

Multiclass SVM-RFE algorithm [39]

Grahic Jump Location
Fig. 2

Typical measurements after FRF for the benchmark and the nine damage cases: (a) full FRF data and (b) zoom in into the first one thousand features

Grahic Jump Location
Fig. 4

Feature fusion based on feature aggregation

Grahic Jump Location
Fig. 5

Schematic of the pipe dimensions and the location of the mounted sensors: (a) side view and (b) top view

Grahic Jump Location
Fig. 6

Typical collected raw signals: (a) impact and (b) response from PZT1

Grahic Jump Location
Fig. 7

Surface cutting of the pipe to simulate different damage severity cases: (a) benchmark, (b) damage case 1, (c) damage case 2, (d) damage case 3, (e) damage case 4, (f) damage case 5, (g) damage case 6, (h) damage case 7, (i) damage case 8, and (j) damage case 9

Grahic Jump Location
Fig. 8

Classification after training using the data from PZT1 ceramics and testing with the rest of the data from PZT1: (a) first ten features, (b) first 100 features, (c) using ten features after applying MCSVM-RFE, and (d) using 100 features after applying MCSVM-RFE

Grahic Jump Location
Fig. 9

Distribution of the normalized mean values of the signals collected from the three PZT ceramics

Grahic Jump Location
Fig. 10

Classification after training using the data combined from the three PZT ceramics: (a) first ten features, (b) first 100 features, (c) using ten features after applying MCSVM-RFE, and (d) using 100 features after applying MCSVM-RFE

Grahic Jump Location
Fig. 11

Classification after training using the features combined from the three PZT ceramics: (a) first ten features and (b) first 100 features



Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In