0
Research Papers: NDE

Development of an Optimized Neural Network for the Detection of Pipe Defects Using a Microwave Signal

[+] Author and Article Information
Wissam M. Alobaidi

Department of Systems Engineering,
Donaghey College of Engineering and
Information Technology,
University of Arkansas at Little Rock,
Little Rock, AR 72204
e-mail: wmalobaidi@ualr.edu

Entidhar A. Alkuam

Department of Physics and Astronomy,
College of Arts, Letters, and Sciences,
University of Arkansas at Little Rock,
Little Rock, AR 72204
e-mail: eaalkuam@ualr.edu

Eric Sandgren

Department of Systems Engineering,
Donaghey College of Engineering and
Information Technology,
University of Arkansas at Little Rock,
Little Rock, AR 72204
e-mail: exsandgren@ualr.edu

1Corresponding author.

Contributed by the Pressure Vessel and Piping Division of ASME for publication in the JOURNAL OF PRESSURE VESSEL TECHNOLOGY. Manuscript received May 26, 2017; final manuscript received May 19, 2018; published online June 18, 2018. Assoc. Editor: Steve J. Hensel.

J. Pressure Vessel Technol 140(4), 041501 (Jun 18, 2018) (10 pages) Paper No: PVT-17-1098; doi: 10.1115/1.4040360 History: Received May 26, 2017; Revised May 19, 2018

Neural network technology is applied to the detection of a pipe wall thinning (PWT) in a pipe using a microwave signal reflection as an input. The location, depth, length, and profile geometry of the PWT are predicted by the neural network from input parameters taken from the resonance frequency plots for training data generated through computer simulation. The network is optimized using an evolutionary optimization routine, using the 108 training data samples to minimize the errors produced by the neural network model. The optimizer specified not only the optimal weights for the network links but also the optimal topology for the network itself. The results demonstrate the potential of the approach in that when data files were input that were not part of the training data set, fairly accurate predictions were made by the network. The results from the initial network models can be utilized to improve the future performance of the network.

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

References

Ju, Y. , 2007, “ Remote Measurement of the Pipe Thickness Reduction by Microwaves,” ASME Paper No. PVP2007-26565.
Chen, Z. , Zhu, W. , Di, Q. , and Wang, W. , 2015, “ Prediction of Burst Pressure of Pipes With Geometric Eccentricity,” ASME J. Pressure Vessel Technol., 137(6), p. 61201. [CrossRef]
Alobaidi, W. M. , Alkuam, E. A. , Sandgren, E. , and Al-rizzo, H. M. , 2015, “ Enhancing Production Efficiency of Oil and Natural Gas Pipes Using Microwave Technology,” Energy Power Eng., 7(10), pp. 440–450. [CrossRef]
Alobaidi, W. M. , Alkuam, E. A. , Al-Rizzo, H. M. , and Sandgren, E. , 2015, “ Applications of Ultrasonic Techniques in Oil and Gas Pipeline Industries: A Review,” Am. J. Oper. Res., 5(4), pp. 274–287. [CrossRef]
Alobaidi, W. , and Sandgren, E. , 2016, “ Detection of Defects in Spiral/Helical Pipes Using RF Technology,” 11th Pipeline Technology Conference, Berlin, May 23–25, pp. 22–33.
Chen, Z. , Ye, H. , Yan, S. , Shen, X. , and Jin, Z. , 2017, “ The Failure Window Method and Its Application in Pipeline Burst,” ASME J. Pressure Vessel Technol., 139(5), p. 051702. [CrossRef]
Alobaidi, W. M. , Nima, Z. A. , and Sandgren, E. , 2018, “ Localised Surface Plasmon-like Resonance Generated by Microwave Electromagnetic Waves in Pipe Defects,” Nondestructive Test. Evaluation, 33(1), pp. 109–118. [CrossRef]
Alobaidi, W. M. , Al-Rizzo, H. M. , and Sandgren, E. , 2015, “ NDT Applied to the Detection of Defects in Oil and Gas Pipes: A Simulation-Based Study,” ASME Paper No. IMECE2015-50641.
Alobaidi, W. M. , and Sandgren, E. , 2016, “ Classification of the Extent of Wall Thinning in Pipes Based on Simulations in the Time and Frequency Domain,” ASME Paper No. PVP2016-63387.
Alobaidi, W. M. , Sandgren, E. , and Al-Rizzo, H. M. , 2016, “ Waveform Pattern Recognition Applied to Rapid Detection of Wall-Thinning in Pipes: A Simulation-Based Case Study,” ASME Paper No. IPC2016-64320.
Alobaidi, W. M. , Kintner, C. E. , Alkuam, E. A. , Sasaki, K. , Yusa, N. , Hashizume, H. , and Sandgren, E. , 2018, “ Experimental Evaluation of Novel Hybrid Microwave/Ultrasonic Technique to Locate and Characterize Pipe Wall Thinning,” ASME J. Pressure Vessel Technol., 140(1), p. 011501. [CrossRef]
McCulloch, W. , and Pitts, W. , 1956, “ Representation of Events in Nerve Nets and Finite Automata,” Automata Studies (Annals of Mathematical Studies, Vol. 34) C. E. Shannon and J. McCarthy , eds., Princeton University Press, Princeton, NJ.
Werbos, P. , 1974, “ Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences,” Ph.D. thesis, Harvard University, Cambridge, MA.
Simone, G. , Morabito, F. , Polikar, R. , Ramuhalli, P. , Udpa, L. , and Udpa, S. , 2001, “ Feature Extraction Techniques for Ultrasonic Signal Classification,” Int. J. Appl. Electromagnetics Mech., 15(1–4), pp. 291–294.
Carvalho, A. A. , Rebello, J. M. A. , Sagrilo, L. V. S. , Camerini, C. S. , and Miranda, I. V. J. , 2006, “ MFL Signals and Artificial Neural Networks Applied to Detection and Classification of Pipe Weld Defects,” NDT and E Int., 39(8), pp. 661–667. [CrossRef]
Yang, M.-D. , and Su, T. C. , 2008, “ Automated Diagnosis of Sewer Pipe Defects Based on Machine Learning Approaches,” Expert Syst. with Appl., 35(3), pp. 1327–1337. [CrossRef]
Chen, J. , Huang, S. , and Zhao, W. , 2015, “ Three-Dimensional Defect Inversion From Magnetic Flux Leakage Signals Using Iterative Neural Network,” IET Sci., Meas. Technol., 9, pp. 418–426.
Linsheng, L. , 2010, “ Remote Detection and Quantitative Evaluation of Wall Thinning Volumes in a Metal Pipe,” E-J. Adv. Maint., 2(3), pp. 101–109.
Sakai, Y. , Yusa, N. , and Hashizume, H. , 2012, “ Nondestructive Evaluation of Wall Thinning Inside a Pipe Using the Reflection of Microwaves With the Aid of Signal Processing,” Nondestructive Test. Eval., 27(2), pp. 171–184. [CrossRef]
Alobaidi, W. M. , Sandgren, E. , 2016, “ High-Efficiency Remote Measurement of Pipe Defect Using RF/UT Technologies: A Theoretical Analysis Part One—Straight Beam UT,” ASME Paper No. PVP2016-63624.

Figures

Grahic Jump Location
Fig. 1

Basic layout of a neural network

Grahic Jump Location
Fig. 2

(a) and (b) Scheme for model pipe with two ports are represented. LP is pipe length. DD is depth of full circumferential PWT. Di is inner diameter.

Grahic Jump Location
Fig. 3

Microwave signals for semicircular shape, distance 381 mm from port one, depth is 11.43 mm, full circumferential length, with all the resulting parameters

Grahic Jump Location
Fig. 4

Microwave signals for two-fillet shape, distance 381 mm from port one, depth is 11.43 mm, 66% circumferential length, with all the resulting parameters

Grahic Jump Location
Fig. 5

Assumed neural network topology

Grahic Jump Location
Fig. 6

Output distribution for defect location for the first output level

Grahic Jump Location
Fig. 7

Output distribution for defect location for the second output level

Grahic Jump Location
Fig. 8

Output distribution for defect location for the third output level

Grahic Jump Location
Fig. 9

Output distribution for defect location for all output levels

Grahic Jump Location
Fig. 10

Optimal neural network topology for defect depth detection

Grahic Jump Location
Fig. 11

Optimal neural network topology for defect length detection

Grahic Jump Location
Fig. 12

Optimal neural network topology for defect position detection

Grahic Jump Location
Fig. 13

Optimal neural network topology for defect type detection

Grahic Jump Location
Fig. 14

Output distribution for defect depth for all output levels

Grahic Jump Location
Fig. 15

Output distribution for defect length for all output levels

Grahic Jump Location
Fig. 16

Output distribution for defect type for all output levels

Tables

Errata

Discussions

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