Article Article
A Neural Network System for Fault Prediction in Pipelines by Acoustic Emission Techniques

The problem of evaluating the risk of failure associated with the propagation of a crack in a pipe under pressure has great practical relevance, and it may be tackled with acoustic emission techniques. Artificial neural networks may be trained to classify the acoustic emissions generated by the crack according to the phase of propagation, and such a classification permits to evaluate the risk of mantaining a system in operation. In order to train the network, a human specialist has to estimate the transition times between any two consecutive phases by inspecting the results of a previous hydrostatic test, and such determination of the transition times has a high degree of subjectivity and uncertainty, affecting the classification performance of the network. In this paper, we propose a human independent method for the estimation of the transition times, and we show successful applications to the data from two hydrostatic tests. For a test on a 2 m-long pipe, the method exhibited 98% of correct-classification rate, an improvement of 8% over results obtained with human-determined transition times. For a 40 m-long pipe, under experimental conditions comparable to those found in industrial applications, the method exhibited 91% of correct-classification rate. The proposed method provides a fully automated framework for the evaluation of the state of a crack.

DOI: https://doi.org/10.1080/09349847.2021.1930305

References

A. Zolghadri et al., IFAC-PapersOnLine 48, 1096 (2015). DOI: 10.1016/j.ifacol.2015.09.673.

M. Schlechtingen and I. F. Santos, Mech. Syst. Signal Process. 25 (5), 1849 (2011). DOI: 10.1016/j.ymssp.2010.12.007.

R. Nybø, Neurocomputing 73, 1987 (1992). DOI: 10.1016/j.neucom.2009.10.020.

A. Khodabakhsh, I. Ari, and M. Bakir, ArXiv:1705.04583 (2017).

Pipeline Incident 20 Year Trends, PHMSA, https://www.phmsa.dot.gov/data-andstatistics/pipeline/pipeline-incident-20-year-trends (accessed 2018)

C. J. Hellier, Handbook of Nondestructive Evaluation, 3rd ed. (McGraw-Hill, 2020). New York.

DiSP with AEwin User’s Manual Rev 4 (Mistras Group Inc, 2011). New Jersey.

H. Lasi et al., Business Information Systems Eng. 6, 239 (2014). DOI: 10.1007/s12599-014-0334-4.

C. M. Bishop, Pattern Recognition and Machine Learning (Springer, 2006). New York.

S. Haykin, Neural Networks and Learning Machines, 3rd ed. (Pearson Prentice Hall, 2009). Hoboken.

A. K. Das, D. Suthar, and C. K. Y. Leung, Cement Concrete Res. 121, 42 (2019). DOI: 10.1016/j.cemconres.2019.03.001.

Z. Kral, W. Horn, and J. Steck, Scientific World J. 1, 2013 (2013).

H. Gaja and F. Liou, Int. J. Adv. Manuf. Technol. 94, 315 (2018). DOI: 10.1007/s00170-017-0878-9.

X. Zhang et al. Paper presented at the IEEE Instrumentation and Measurement Technology Conference, Torino, Italy, 2017.

L. Yang et al., Exp. Mech. 55 (2), 321 (2015). DOI: 10.1007/s11340-014-9956-1.

J.-T. Kim et al., J. Mech. Sci. Technol. 32 (1), 129 (2018). DOI: 10.1007/s12206-017-1214-x.

R. R. Da Silva et al., Insight 48, 45 (2006). DOI: 10.1784/insi.2006.48.1.45.

C. F. C. Pinto et al., Insight 56 (4), 204 (2014). DOI: 10.1784/insi.2014.56.4.204.

Boiler and Pressure Vessel Code Section V - Nondestructive Examination (ASME, 2019). Hoboken.

 

Metrics
Usage Shares
Total Views
3 Page Views
Total Shares
0 Tweets
3
0 PDF Downloads
0
0 Facebook Shares
Total Usage
3