Neural network data analysis for ultrasonic non-destructive testing of main gas pipelines

Authors and copyright holders:

• Borovskoy I. G. , Tomsk State University of Control Systems and Radioelectronics (Tomsk, Russia)
• Matolygin A. A. , Tomsk State University of Control Systems and Radioelectronics (Tomsk, Russia)
• Ilin E. P. , Tomsk State University of Control Systems and Radioelectronics (Tomsk, Russia)

• 1. The decree of the President of the Russian Federation of 13.05.2019 г. № 216 about Russian Federation of energy supply security doctrine. Available at: http://www.kremlin.ru/acts/bank/44252/page/1, free (Accessed: October 28, 2024) (in Russ.).
• 2. Kunina P.S., Velichko E.I., Stepanov M.S., Muzykantova A.V. [The problems that arise when analyzing the technical state of modern drives of compressor installations of main gas]. Building Oil and Gas Wells on Land and Sea, 2019, no. 3, pp. 56–58 (in Russ.).
• 3. Kaputkin, D.E., Arabey A.B. [Two types of the crack arrest during full-scale pneumatic testing of main gas pipelines]. Letters on Materials. 2021. Vol. 11, no. 3 (43), pp. 239–243 (in Russ.).
• 4. Lyapichev D.M, Admakin M.M. [Technical state monitoring system as an element of the digital twin of the main gas pipeline]. Equipment and Technologies for an Oil Complex, 2024, no. 1 (139), pp. 60–65 (in Russ.).
• 5. Golofast S.L. [Assessment of the main gas pipeline strength reliability considering the actual regularities of the distribution of the pipe wall thickness]. Industrial Labor Safety, 2020, no. 6. pp. 21–28 (in Russ.).
• 6. Borovskoy I.G., Shelmina E.A., Matolygin A.A., Ilin E.P. [Neural network analysis of ultrasonic flaw detection data of main gas pipelines using a hardware and software DVU system]. Tomsk State University Journal of Control and Computer Science, 2023, no. 64. pp. 50–60 (in Russ.).
• 7. Marcos N., Orti S., Oihana O. [Boosting AI applications: Labeling format for complex datasets]. SoftwareX, 2021, vol. 13. Available at: https://www.sciencedirect.com/science/article/pii/S2352711020303666, free (Accessed: November 02, 2024).
• 8. Kroese D.P., Botev Z.I., Taimre T., Vaisman R. Data Science and Machine Learning: Mathematical and Statistical Methods. Chapman & Hall/CRC machine learning & pattern recognition. CRC Press, Boca Raton, 2019, 532 p.
• 9. Murphy K.P. Probabilistic Machine Learning: an Introduction. MIT press, 2022, 864 p.
• 10. Shai S.S., Shai S.B. Idei machinnogo obuchenia: ot teorii k algoritmam. Understanding machine learning. From Theory to Algorithms. Moscow: DMK Press, 2019, 436 p. (in Russ.).
• 11. An internal pipeline inspection gauge 40-DFR.00-00.000. The State Register number 84766-22. Federal information foundation of the uniformity of measurements ensuring, 2022. Available at: https://fgis.gost.ru/fundmetrology/registry/4/items/1397751, free (Accessed: November 02, 2024) (in Russ.).
• 12. Emelyanov S.O, Ivanova A.A, Shvets E.A., Nikolaev D.P. [Methods of training data augmentation in the task of image classification]. Sensor Systems, 2018, vol. 32, no. 3, pp. 236–245 (in Russ.).
• 13. Preprocessing layers. Available at: https://keras.io/api/layers/preprocessing_layers/image_augmentation, free (Accessed: November 02, 2024).
• 14. Binary Cross Entropy. Available at: https://www.tensorflow.org/api_docs/python/tf/keras/losses/BinaryCrossentropy, free (Accessed: November 02, 2024).
• 15. Area under the Curve. Available at: https://www.tensorflow.org/api_docs/python/tf/keras/metrics/AUC, free (Accessed: November 02, 2024).
• 16. Precision. Available at: https://www.tensorflow.org/api_docs/python/tf/keras/metrics/Precision (Accessed: November 02, 2024).
• 17. Recall. Available at: https://www.tensorflow.org/api_docs/python/tf/keras/metrics/Recall, free (Accessed: November 02, 2024).
• 18. Stochastic Gradient Descent. Available at: https://www.tensorflow.org/api_docs/python/tf/keras/optimizers/SGD, free (Accessed: November 02, 2024).