Cover
Vol. 19 No. 1 (2023)

Published: June 30, 2023

Pages: 100-110

Original Article

Machine Learning Approach Based on Smart Ball COMSOL Multiphysics Simulation for Pipe Leak Detection

Marwa H. Abed 1 Wasan A. Wali Musaab Alaziz
1Department of Computer Engineering, University of Basrah, Basrah, Iraq
History
  • Received: November 16, 2022
  • Revised: January 14, 2023
  • Accepted: January 15, 2023
  • Available Online: February 24, 2023
DOI

https://doi.org/10.37917/ijeee.19.1.13

Abstract

Due to the changing flow conditions during the pipeline's operation, several locations of erosion, damage, and failure occur. Leak prevention and early leak detection techniques are the best pipeline risk mitigation measures. To reduce detection time, pipeline models that can simulate these breaches are essential. In this study, numerical modeling using COMSOL Multiphysics is suggested for different fluid types, velocities, pressure distributions, and temperature distributions. The system consists of 12 meters of 8-inch pipe. A movable ball with a diameter of 5 inches is placed within. The findings show that dead zones happen more often in oil than in gas. Pipe insulation is facilitated by the gas phase's thermal inefficiency (thermal conductivity). The fluid mixing is improved by 2.5 m/s when the temperature is the lowest. More than water and gas, oil viscosity and dead zones lower maximum pressure. Pressure decreases with maximum velocity and vice versa. The acquired oil data set is utilized to calibrate the Support Vector Machine and Decision Tree techniques using MATLAB R2021a, ensuring the precision of the measurement. The classification result reveals that the Support Vector Machine (SVM) and Decision Tree (DT) models have the best average accuracy, which is 98.8%, and 99.87 %, respectively.

Keywords

References

  1. R. Kroes, L. Amundsen, and R. Hoffmann, “Crude oil-water flow in horizontal pipes,” 2013. http://essay.utwente.nl/69533/
  2. W. A. Wali, “Carbon Dioxide Conversion Control Based on Microwave Plasma Technology,” Int. Conf. Electr. Commun. Comput. Eng., pp. 1–4, 2020. doi: 10.1109/ICECCE49384.2020.9179393.
  3. W. R. Chalgham, A. C. Seibi, and M. Mokhtari, “Simulation of Sound Wave Propagation Inside a Spherical Ball Submerged in a Pipeline,” Proc. 2016 COMSOL Conf. Bost., p. 2016, 2016.
  4. M. M. Hathal, “Oil fouling in double ‐ pipe heat exchanger under liquid ‐ liquid dispersion and the influence of copper oxide nanofluid,” Heat Transfer, vol. 48, Issue 5, pp. 1963-1981, July 2019. doi: 10.1002/htj.21473.
  5. J. V. N. de Sousa, C. H. Sodré, A. G. B. de Lima, and S. R. de F. Neto, “Numerical Analysis of Heavy Oil-Water Flow and Leak Detection in Vertical Pipeline,” Adv. Chem. Eng. Sci., vol. 03, no. 01, pp. 9–15, 2013. doi: 10.4236/aces.2013.31002.
  6. C. W. Liu, Y. X. Li, Y. K. Yan, J. T. Fu, and Y. Q. Zhang, “A new leak location method based on leakage acoustic waves for oil and gas pipelines,” J. Loss Prev. Process Ind., vol. 35, pp. 236–246, May 2015. doi: 10.1016/j.jlp.2015.05.006.
  7. S. I. Kam, “Mechanistic modeling of pipeline leak detection at fixed inlet rate,” J. Pet. Sci. Eng., vol. 70, no. 3–4, pp. 145–156, Feb. 2010. doi: 10.1016/J.PETROL.2009.09.008.
  8. S. Valizadeh, B. Moshiri, and K. Salahshoor, “Multiphase pipeline leak detection based on fuzzy classification,” AIP Conf. Proc., vol. 1159, no. 2009, pp. 72–80, 2009. doi: 10.1063/1.3223958.
  9. L. Dong, S. Chai, and B. Zhang, “Leak detection and localization of gas pipeline system based on wavelet analysis,” Proc. 2nd Int. Conf. Intell. Control Inf. Process. ICICIP 2011, no. PART 1, pp. 478–483, 2011. doi: 10.1109/ICICIP.2011.6008290.
  10. R. Hu, H. Ye, G. Wang, and C. Lu, “Leak detection in pipelines based on PCA,” 2004 8th Int. Conf. Control. Autom. Robot. Vis., vol. 3, pp. 1985–1989, 2004. doi: 10.1109/ICARCV.2004.1469466.
  11. C. Verde, “Multi-leak detection and isolation in fluid pipelines,” Control Eng. Pract., vol. 9, no. 6, pp. 673–682, Jun. 2001. doi: 10.1016/S0967-0661(01)00026-0.
  12. M. Francis, A. Ross, and A. James, “Experimental Observation And Analysis Of Inverse Transient For Pipeline Leak Detection,” ASCE, vol. 133, no. March, pp. 519–530, 2014.
  13. Y. Liu, X. Ma, Y. Li, Y. Tie, Y. Zhang, and J. Gao, “Water pipeline leakage detection based on machine learning and wireless sensor networks,” Sensors (Switzerland), vol. 19, no. 23, pp. 1–21, 2019. doi: 10.3390/s19235086.
  14. U. Baroudi, A. A. Al-Roubaiey, and A. Devendiran, “Pipeline Leak Detection Systems and Data Fusion: A Survey,” IEEE Access, vol. 7, pp. 97426–97439, 2019. doi: 10.1109/ACCESS.2019.2928487.
  15. Y. Song and S. Li, “Gas leak detection in galvanised steel pipe with internal flow noise using convolutional neural network,” Process Saf. Environ. Prot., vol. 146, pp. 736–744, 2021. doi: 10.1016/j.psep.2020.11.053.
  16. A. Terfous, A. Hazzab, and A. Ghenaim, “Predicting the drag coefficient and settling velocity of spherical Abed, Wali, & Alaziz particles,” Powder Technol., vol. 239, pp. 12–20, May 2013. doi: 10.1016/J.POWTEC.2013.01.052.
  17. M. D. Mikhailov and A. P. S. Freire, “The drag coefficient of a sphere: An approximation using Shanks transform,” Powder Technol., vol. 237, pp. 432–435, Mar. 2013. doi: 10.1016/J.POWTEC.2012.12.033.
  18. N. S. Cheng, “Comparison of formulas for drag coefficient and settling velocity of spherical particles,” Powder Technol., vol. 189, no. 3, pp. 395–398, Feb. 2009. doi: 10.1016/J.POWTEC.2008.07.006.
  19. R. Barati, S. A. A. S. Neyshabouri, and G. Ahmadi, “Development of empirical models with high accuracy for estimation of drag coefficient of flow around a smooth sphere: An evolutionary approach,” Powder Technol., vol. 257, pp. 11–19, May 2014. doi: 10.1016/J.POWTEC.2014.02.045.
  20. A. B. Figueiredo, R. M. Baptista, F. B. de F. Rachid, and G. C. R. Bodstein, “A straightforward strategy for leak localization in two-phase gas pipelines,” J. Nat. Gas Sci. Eng., vol. 94, Oct. 2021. doi: 10.1016/j.jngse.2021.104061.
  21. J. V. N. de Sousa, C. H. Sodré, A. G. B. de Lima, and S. R. de F. Neto, “Numerical Analysis of Heavy Oil-Water Flow and Leak Detection in Vertical Pipeline,” Adv. Chem. Eng. Sci., vol. 03, no. 01, pp. 9–15, 2013. doi: 10.4236/aces.2013.31002.
  22. M. De Vasconcellos Araújo, S. R. De Farias Neto, A. G. B. De Lima, and F. Daylane Tavares De Luna, “Hydrodynamic study of oil leakage in pipeline via CFD,” Adv. Mech. Eng., vol. 2014, 2014. doi: 10.1155/2014/170178.
  23. O. Akinsete and A. Oshingbesan, “Leak detection in natural gas pipelines using intelligent models,” Soc. Pet. Eng. - SPE Niger. Annu. Int. Conf. Exhib. 2019. NAIC 2019, no. April, 2019, doi: 10.2118/198738-MS.
  24. R. R. Sharma, “Gas Leakage Detection in Pipeline by SVM classifier with Automatic Eddy Current based Defect Recognition Method,” J. Ubiquitous Comput. Commun. Technol., vol. 3, no. 3, pp. 196–212, 2021. doi: 10.36548/jucct.2021.3.004.
  25. Y. Shen and W. Cheng, “A Tree-Based Machine Learning Method for Pipeline Leakage Detection,” Water (Switzerland), vol. 14, no. 18, 2022. doi: 10.3390/w14182833.
  26. H. Salim, M. Alaziz, and T. Abdalla, “Human Activity Recognition Using The Human Skeleton Provided by Kinect,” Iraqi J. Electr. Electron. Eng., vol. 17, no. 2, pp. 183–189, 2021. doi: 10.37917/ijeee.17.2.20.
  27. N. Mashhadi, I. Shahrour, N. Attoue, J. El Khattabi, and A. Aljer, “Use of machine learning for leak detection and localization in water distribution systems,” Smart Cities, vol. 4, no. 4, pp. 1293–1315, 2021. doi: 10.3390/smartcities4040069.
  28. J. Kemba, K. Gideon, and C. N. Nyirenda, “Leakage detection in Tsumeb east water distribution network using EPANET and support vector regression,” 2017 IST-Africa Week Conf. IST-Africa 2017, Nov. 2017. doi: 10.23919/ISTAFRICA.2017.8102401.
  29. A. Krishnakumari, A. Elayaperumal, M. Saravanan, and C. Arvindan, “Fault diagnostics of spur gear using decision tree and fuzzy classifier,” Int. J. Adv. Manuf. Technol. 2016 899, vol. 89, no. 9, pp. 3487–3494, Aug. 2016. doi: 10.1007/S00170-016-9307-8.
  30. V. N. Vapnik, “The Nature of Statistical Learning Theory,” Nat. Stat. Learn. Theory, 2000. doi: 10.1007/978-1-4757-3264-1.
  31. V. Franc and V. Hlaváč, “Vector machine multi-class support,” Proc. - Int. Conf. Pattern Recognit., vol. 2, pp. 236–239, 2002. doi: 10.1109/ICPR.2002.1048282.
  32. Karim Egab et al., “ Study the Effect of Heat Transfer Coefficient and Thermal Conductivity on Cracked Pipes Carrying Pressurized Fluid,” Int. J. Eng. Technol. , vol. 8, no. 2019, pp. 275–282, 2019.
  33. M. Ghasemi, M. Zarei, A. Foroutannia, and S. Jafari, “Study of functional connectivity of central motor system in Parkinson’s disease using copula theory,” Biomed. Signal Process. Control, vol. 65, no. November 2020, pp. 102320, 2021. doi: 10.1016/j.bspc.2020.102320.