«Equipment and technologies for oil and gas complex»

Diagnostic approaches to polymer reinforced pipes. Segmentation of detected defects using computer vision

UDC: 658.562
DOI: -

Authors:

¹ All-Union Research Institute for Construction, Operation of Pipelines and Fuel and Energy Complex Facilities - Engineering Oil and Gas Company, Moscow, Russia
² I. Kant Baltic Federal University, Kaliningrad, Russia

Keywords: polymer reinforced pipes, diagnostics, pipe defects, segmentation, computer vision, machine learning

Annotation:

The development of modern pipeline transport in the energy, oil and gas, housing and communal services sectors involves a gradual departure from classical design solutions based on the use of metal (steel and cast iron) and non-metallic (plastic) pipes. The active development of chemical technologies and small-scale mechanization makes it possible to produce multilayer pipes that simultaneously combine the positive qualities of both polymers and metals. Thus, polymer reinforced pipes are gradually starting to play an increasingly important role in industry. However, there are a number of difficulties in their usage. First, there are problems with non-destructive testing and assessment of equipment technical state. The presented study analyzes methods applied for diagnosing polymer reinforced pipes and selecting optimal techniques for segmenting defects with the subsequent development of proposals for creating software that will evaluates the technical condition of pipes of this type.

Bibliography:

1. Potapov B.V., Marchenko S.V., Potapov A.B. Podkhod k perspektivnym issledovaniyam v oblasti tekhnicheskogo diagnostirovaniya neftegazopromyslovykh truboprovodov iz armirovannykh polimernykh trub // Truboprovodnyy transport: teoriya i praktika. – 2023. – № 1(83). – S. 19–26.
2. Mohamed I., Hutchins D., Davis L. Ultrasonic NDE of thick polyurethane flexible riser stiffener material // Nondestructive Testing and Evaluation. – 2017. – Vol. 32, Issue 4. – P. 343–362. – DOI: 10.1080/10589759.2016.1241253
3. Kažys R., Tumšys O., Pagodinas D. Ultrasonic method for detection and location of defects in three-layer plastic pipe based on the wavelet transform // Ultragarsas. – 2005. – No. 1(54). – P. 33–38.
4. Vyyavlyaemost' defektov truboprovoda putem diagnostiki magnitnym defektoskopom / A.N. Kovalenko, V.V. Ulanov, V.I. Chebotova, R.A. Shestakov // Truboprovodnyy transport: teoriya i praktika. – 2020. – № 4(76). – S. 49–54.
5. An Eddy Current Testing Platform System for Pipe Defect Inspection Based on an Optimized Eddy Current Technique Probe Design / D. Rifai, A.N. Abdalla, R. Razali [et al.] // Sensors. – 2017. – Vol. 17, Issue 3. – P. 579. – DOI: 10.3390/s17030579
6. Antonelli L., De Simone V., Di Serafino D. A view of computational models for image segmentation // Annali dell'Universita' di Ferrara. – 2022. – Vol. 68, Issue 2. – P. 277–294. – DOI: 10.1007/s11565-022-00417-6
7. Vliyanie konstruktivnykh defektov na nadezhnost' polimernykh trub, armirovannykh metallicheskimi lentami / V.R. Gallyamov, A.S. Romanchuk, A.A. Chervov [i dr.] // Neftegazovoe delo. – 2023. – T. 21, № 1. – S. 117–124. – DOI: 10.17122/ngdelo-2023-1-117-126
8. Milletari F., Navab N., Ahmadi S.A. V-net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation // 2016 Fourth Int. Conf. on 3D Vision (3DV), Stanford, CA, USA, Oct. 25–28, 2016. – IEEE, 2016. – P. 565–571. – DOI: 10.1109/3DV.2016.79
9. Shmatin A.K., Panteleev A.S. Budushchee upravleniya kachestvom: iskusstvennyy intellekt kak klyuchevoy instrument optimizatsii protsessov // Oborudovanie i tekhnologii dlya neftegazovogo kompleksa. – 2024. – № 1(139). – S. 18–22.
10. Klochkov Yu.S., Tveryakov A.M. Approaches to the improvement of quality management methods // Int. J. of System Assurance Engineering and Management. – 2020. – Vol. 11, No. Suppl. 2. – P. 163–172. – DOI: 10.1007/s13198-019-00939-x
11. Kershenbaum V.Ya. Standartizatsiya i konkurentosposobnost' neftegazovogo oborudovaniya // Oborudovanie i tekhnologii dlya neftegazovogo kompleksa. – 2014. – № 1. – S. 4–6.
12. D'yakonov A.G. Metody resheniya zadach klassifikatsii s kategorial'nymi priznakami // Prikladnaya matematika i informatika: tr. fak. VMK MGU im. M.V. Lomonosova. – 2014. – T. 46. – S. 103–127.
13. Daolei Wang, Yiteng Liu. An Improved Neural Network Based on UNet for Surface Defect Segmentation // 3D Imaging Technologies – Multidimensional Signal Processing and Deep Learning. Vol. 2. Methods, Algorithms and Applications / L.C. Jain, R. Kountchev, Yonghang Tai (editors). – Singapore: Springer, 2021. – P. 27–33. – (Smart Innovation, Systems and Technologies. Vol. 236). – DOI: 10.1007/978-981-16-3180-1_4
14. Al-Shayea Q., Al-Ani M. Efficient 3D Object Visualization via 2D Images // Int. J. of Computer Science and Network Security. – 2009. – Vol. 9, No. 11. – P. 234–239.
15. Klochkov Yu.S., Fokin G.A., Syrovatsskiy O.V. Uchet neopredelennosti pri provedenii protsedury FMEA-analiza // Izv. Samarskogo nauch. tsentra RAN. – 2021. – T. 23, № 6(104). – S. 26–32. – DOI: 10.37313/1990-5378-2021-23-6-26-32