Article Article
NDE 4.0 compatible ultrasound inspection of butt-fused joints of medium-density polyethylene gas pipes, using chord-type transducers supported by customized deep learning models

Pipe joints mostly form the weakest points in pipeline networks. Infield joints are prone to various flaws. Thus, the infrastructure industry requires an effective inspection technique. Our work focused on evaluating the performance of chord-type transducers for flaw detection in polyethylene (PE) pipe joints. Various artificially introduced flaws were fabricated and tested for statistical estimation of system performance. A-scans data was gathered to develop and assess the viability of a deep learning approach for automated flaw detection. Such an automated “smart” quality control method aligns with requirements of a nondestructive evaluation (NDE) 4.0 platform which can be utilized to achieve reliable and real-time inspection. In this we will introduce results of our current development, starting with approaches to generic data formats, communication protocols, signal processing, artificial intelligence-based (AI) information generation, and decision making. For each of the aspects, results and prototypical implementations will be provided. This includes a pilot development for modern human-machine-interaction using assistive technologies for manual NDE 4.0 inspection. This gives an outlook on further challenges and possible approaches for requirements in the context of secure data exchange, trusted and reliable AI processing, new standardization procedures, and validation of new “smart” NDE 4.0 ultrasonic inspection systems.

DOI: https://doi.org/10.1080/09349847.2020.1841864

References

A. Frank, G. Pinter, and R. W. Lang, Polym Test 28(7), 737–745 (2009). DOI: 10.1016/j.polymertesting.2009.06.004.

M. S. Prowant et al., in Pressure Vessels and Piping Conference (2016), Vancouver, British Columbia, Canada. DOI: 10.1115/PVP2016-63688.

ASTM F2620-19, Standard Practice for Heat Fusion Joining of Polyethylene Pipe and Fittings

J. Zheng et al., Front. Mech. Eng. 13, 535–545(2018). DOI: 10.1007/s11465-018-0515-9.

M. H. Taghipour, J. Phys. Sci. Appl. 5(5), 349–355 (2015).

M. Pal, N. Dixon, and J. Flint, in Proceedings of the World Congress on Engineering, pp. 889–894 (2010), London, U.K.

C. Wunderlich, C. Tschöpe, and F. Duckhorn, In AIP Conference Proceedings (Vol. 1949, No. 1, p. 020022). (AIP Publishing LLC, 2018, April).

J. Vrana (2019). NDE 4.0: The Fourth Revolution in Non-Destructive Evaluation: Digital Twin, Semantics, Interfaces, Networking, Feedback, New Markets and Integration into the Industrial Internet of Things.

S. Kil et al., J. Energ. Eng. 25(4), 103–109 (2016). DOI: 10.5855/ENERGY.2016.25.4.103.

F. Hagglund, M. A. Spicer, and M. J. Troughton. Detection capabilities of a phased array ultrasonic inspection system for plastic pipe butt fusion joints. 51st Annual Conference of British Institute of Non-Destructive Testing. (2012).

V. Ushakov, V. Mikhalev, and D. Davydov, Russ. J. Of Nondestruct. Test. 44(11), 762–765 (2008). DOI: 10.1134/S106183090811003X.

SP 42-103-2003 Design and construction of gas pipelines from polyethylene pipes and renovation of worn out gas pipelines. Code for design and construction Russian Federation.

R. Gr., ASNT Mater. Eval. J. 71(7) July (2013).

S. Marsland, Machine Learning: An Algorithmic Perspective, 2nd ed., (CRC Press, 2014), pp. 4.

I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning (MIT Press, 2016), pp. 13.

J. Schmidhuber, Neural Netw 61, 85–117 (2015). DOI: 10.1016/j.neunet.2014.09.003.

R. Sikora et al., The 18th World Conference on Nondestructive Testing, pp. 16–20 (2012).

G. D’Angelo and S. Rampone, in IEEE Metrology for Aerospace (2015), pp. 406–410.

J. Ye, et al., Sensors. 18(11), 3820 (2018). DOI:10.3390/s18113820

K. Virupakshappa and E. Oruklu, IEEE International Ultrasonics Symposium, pp. 1647–1650 (2019), Glasgow, United Kingdom.

A. Aravind and A. VA., ACTA Sci. Comp. Sci. 2(1), 23–27 (2020).

L. Posilović et al., in 2019 International Symposium on Image and Signal Processing and Analysis (2019), pp. 163–168.

W. Du et al., J. Of Intell. Manuf. (2020). DOI: 10.1007/s10845-020-01566-1.

G. Kang et al., IEEE Trans. Instrum. Meas. 68(8), 2679–2690 (2019). DOI: 10.1109/TIM.2018.2868490.

I. Virkkunen et al. arXiv. (2019).

Q. Jiang, et al., Appl. Sci. 10 (1)87 (2020). DOI: 10.3390/app10010087.

X. Yin et al., Constr. 109 (2020). DOI: 10.1016/j.autcon.2019.102967.

P. Vincent et al., Proceedings of the 25th International Conference on Machine Learning, pp. 1096–1103 (2008), Helsinki Finland.

T. Tagawa and Y. Tadokoro, Proceedings of the Sixth Asian Conference on Machine Learning. pp. 96–111 (2015), Hong Kong.

A. Vasilev et al., arXiv (2019).

Y. LeCun, et al., Proc. IEEE. 86(11), 2278–2324 (1998).

J. Masci et al., International Conference on Artificial Neural Networks. Springer Berlin Heidelberg (2011), Espoo, Finland.

L. Gondara, in 2016 IEEE 16th International Conference on Data Mining Workshops (ICDMW) (Barcelona 2016), pp.241–246. DOI: 10.1109/ICDMW.2016.0041.

S. Mei, Y. Wang, and G. Wen, Sensors. 18 (1064) (2018). Doi: 10.3390/s18041064.

G. Dlamini, R. Galieva, and M. Fahim, in IEEE Conference on Computer Systems and Applications (2019), pp. 1–5. DOI: 10.1109/AICCSA47632.2019.

K. Hyun Kim et al., in Proceedings of the International Conference on Learning Representations (awaiting publication - 2020).

S. Ioffe and C. Szegedy, in Proceedings of the 32nd International Conference on Machine Learning (2015), pp. 448–456.

X. Glorot, A. Bordes, and Y. Bengio, Proceedings of the 14th International Conference on Artificial Intelligence and Statistics, pp. 315–323 (2011), Ft. Lauderdale, FL, USA.

M. Zeiler arXiv. (2012).

F. Chollet. (2015). https://keras.io

M. Abadi et al., (2015). http://tensorflow.org

 

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