Advertisement

Cluster Computing

, Volume 22, Supplement 5, pp 12949–12957 | Cite as

Oil pipeline leak signal image recognition based on improved data field theory

Article
  • 79 Downloads

Abstract

To maximize use of the valid features of time series signal images, and to detect oil pipeline leaks rapidly, accurately and reliability, the theory of data field is used for its advantages in clustering and singular value recognition. First, the feasibility of using acoustic wave signals for leak detection is demonstrated. Then, the semi-hard semi-soft thresholding function is used for de-noising. This method not only reduces the constant deviation in wavelet-based soft thresholding and hard thresholding, but also preserves the original features of signals and makes the de-noised signals smooth. Finally, the application of data field theory for leak detection and localization is analyzed and an improved algorithm based on data field theory is proposed. And the accuracy and universality of the proposed algorithm are verified through experiments. It is found that the adjusting parameters, influence factors and the width of the sliding window only affect the amplitude of the potential curve. That is, the localization of leak signals is not affected. Research shows that the proposed algorithm is a simple and effective new method for pipeline leak detection and localization besides correlation algorithm.

Keywords

Time series Image recognition Leak detection Data field 

Notes

Acknowledgements

Foundation item: the project supported by the Scientific Searching Plan Project of Shaanxi Province Education Department (No. 16JK1184) and the Project Foundation of Shaanxi Xueqian Normal University (No. 2016YBKJ074). Authors are grateful to the related departments for the financial supports to carry out this work.

References

  1. 1.
    Ellul, I.R.: Advance in pipeline leak detection. Pipeline Eng. ASME 34, 15–19 (2005)Google Scholar
  2. 2.
    Van Hieu, Bui, Choi, Seunghwan, Kim, Young Uk, et al.: Wireless transmission of acoustic emission signals for real-time monitoring of leakage in underground pipes. KSCE J. Civil Eng. 15(5), 800–822 (2011)Google Scholar
  3. 3.
    Mao, H.J., Li, W., Feng, X.L.: Investigation of method for pipeline leak detection and location based on EMD and cross-correlation. Sci. Technol. Eng. 10(19), 4532–4628 (2010)Google Scholar
  4. 4.
    Ge, C.H., Wang, G.Z., Ye, H., et al.: Leak location based on generalized correlation analysis. Inf. Control 38(2), 194–205 (2009)Google Scholar
  5. 5.
    Lian, L.J., Lin, W.G., Wu, H.Y.: Liquid-chlorine leak detection method based on power spectrum comparison. CIESC J. 64(12), 4461–4467 (2013)Google Scholar
  6. 6.
    Ma, B.X., Pan, H.X., Yang, S.M.: Gearbox fault diagnosis based on EEMD and two-dimensional marginal spectrum entropy. Veh. Power Technol. 4, 39–43 (2013)Google Scholar
  7. 7.
    Ekuakille, A.L., Vergallo, P.: Decimated signal diagonalization method for improved spectral leak detection in pipelines. IEEE Sensors 14(6), 1741–1748 (2014)CrossRefGoogle Scholar
  8. 8.
    Ren, X.P., Yao, A.Q., Ren, X.K.: Analysising the method of finding leaking point in pipelines based on wavelat transformation in Matlab. J. Hebei Normal Univ. 31(2), 200 (2007)Google Scholar
  9. 9.
    Sun, L.Y., Li, Y.B., Qu, Z.G., et al.: Study on acoustic emission pipeline leaking detection based on EMD signal analysis method. Piezoelect. AcousZGtooptics 30(2), 239–241 (2008)Google Scholar
  10. 10.
    Li, W., Kuang, P., Li, Y.: A pipeline leak detection method based on fuzzy neural network. Comput Simul. 29(2), 232–290 (2009)Google Scholar
  11. 11.
    Feng, J., Zhang, H.G.: Diagnosis and localization of pipeline leak based on fuzzy decision-making method. Acta Autom. Sin. 31(3), 484–490 (2005)Google Scholar
  12. 12.
    Silva, D.H.V., Morooka, C.K., Guilherme, I.R.: Leak detection in petroleum pipelines using a fuzzy System. J. Pet. Sci. Eng. 49(4), 223–238 (2005)CrossRefGoogle Scholar
  13. 13.
    Wang, M.D., Zhang, L.B., Liang, W., Chen, Z.G.: Pipeline leakage detection method based on independent component analysis and support vector machine. Acta Pet. Sin. 31(4), 559–663 (2010)Google Scholar
  14. 14.
    Ma, J.W., Liu, S.H., Ma, C.F.: The analysis of vector angles in remotely sensed data field and it’s application. J. Remote Sensing 5(1), 17–21 (2001)Google Scholar
  15. 15.
    Wang S L.: Data field and cloud model based spatial data mining and knowledge discovery. Ph.D. Thesis, Wuhan University, China, (2002)Google Scholar
  16. 16.
    Li, D.R., Wang, S.L., Li, D.Y.: The spatial data mining theoty and it’s application. Science Press, Beijing (2006)CrossRefGoogle Scholar
  17. 17.
    Wang, S.L., Wu, J.B., Cheng, F., et al.: Behavior mining of spatial objects with data field. Geo-spatial Inf. Sci. 12(3), 202–211 (2009)CrossRefGoogle Scholar
  18. 18.
    Sun, G.Y., Zhang, A.Z., Wang, Z.J.: Edge detection for multispectral image based on data firld model. J. Southeast Univ. 43(Sup(I)), 77–80 (2013)Google Scholar
  19. 19.
    Li, K., Tian, S.L., Geng, L.J., et al.: Facial feature extraction basedon data field. J. Northwest Univ. Natl. 30(12), 32–36 (2009)Google Scholar
  20. 20.
    Wu, J.B.: Study on image feature extration based on cloud model and data field. Ph.D. Thesis, Wuhan University, China, (2010)Google Scholar
  21. 21.
    Wu, T., Chen, Y.X., Yang, J.J.: Data field-based feature extraction method for sparse image. Comput. Sci. 41(10), 310–316 (2014)Google Scholar
  22. 22.
    Wang, S.L., Zou, S.S., Cao, B.H., et al.: Facial expression recognition based on data field. Geomat. Inf. Sci. Wuhan Univ. 35(6), 738–742 (2010)Google Scholar
  23. 23.
    Wang, Y.X., Zhao, J.M., Zheng, Z.L., et al.: A palmprint recognition method based on data fields and wavelet packet entropy. J. Nanjing Univ. 51(1), 174–180 (2015)zbMATHGoogle Scholar
  24. 24.
    Li, N., Li, Y.X.: Image segmentation with two-dimension threshold based on adaptive particla swarm optimization and data field. J. Comput. Aided Des. Comput. Gr. 24(5), 628–635 (2012)Google Scholar
  25. 25.
    Su, R., Wang, Y.: Application of data field in network topology modeling. J. Guilin Electr. Technol. 28(6), 516–518 (2008)Google Scholar
  26. 26.
    Gao, Z.K., Jin, N.D.: Detecting community structure in complex networks based on K-means clustering and data field theory. Control Decition 24(3), 377–382 (2009)Google Scholar
  27. 27.
    Gan, W.Y., He, N., Li, D.Y., et al.: Community discovery method in networks based on topological potential. J. Softw. 20(8), 2241–2254 (2009)CrossRefGoogle Scholar
  28. 28.
    Wang, L.J., Yang, B.R., Xie, Y.H.: Algotithm of community detection based on data fields. Appl. Res. Comput. 28(11), 4142–4145 (2011)Google Scholar
  29. 29.
    Li, X.S.: Study on classification and clustering mining based on cloud model and data field. Ph.D. Thesis, PLA University of Science and Technogy, China, (2003)Google Scholar
  30. 30.
    Fu, H.D., Li, X.: Dynamic recognition algotithm based on data field in immune intrusion detection. Comput. Appl. 27(9), 2160–2162 (2007)Google Scholar
  31. 31.
    Fu, J.M., Yu, Q.L., Yang, C.: Network security risk fusion model based on data field. Comput. Sci. 369(5), 72–75 (2009)Google Scholar
  32. 32.
    Liu, Y.L., Tang, X., He, J.H.: Spatial analysis based on data field and it’s application to land grade. Geomat. Inf. Sci. Wuhan Univ. 34(9), 1009–1013 (2009)Google Scholar
  33. 33.
    Tian, Y.G., Du, Y.H., Qin, D.H., et al.: Flood risk evaluation method based on data field and cloud modal. China Saf. Sci. J. 21(8), 158–163 (2011)Google Scholar
  34. 34.
    Hou, C.X., Zhang, E.H.: Pipeline leak detection based on double sensor negative pressure wave. Appl. Mech. Mater. 313–314, 1225–1228 (2013)CrossRefGoogle Scholar
  35. 35.
    How, Q.M., Ren, L., Jiao, W.L., et al.: An improved negative pressure wave method for natural gas pipeline leak location using FBG based strain sensor and wavelet transform. Hindawi Publishing Corporation. Math. Probl. Eng. 2013(278794), 8 (2013).  https://doi.org/10.1155/2013/278794 CrossRefGoogle Scholar
  36. 36.
    Osrapkowicz, P.: Leakage detection from liquid transmission pipelines using improved pressure wave techinque. Eksploatacjai Niezawodnosc-maintenance Reliab. 16(1), 9–16 (2014)Google Scholar
  37. 37.
    Fanisulaima, M., Abdullah, F., Jali, M.H., et al.: A feasibility study of internal and external based system for pipeline leak detection in upstream petroleum industry. Aust. J. Basic Appl. Sci. 8(3), 204–210 (2014)Google Scholar
  38. 38.
    Yang, R.G.: Research on leak detection and localization technology for long distance crede oil pipeline. Ph.D. Thesis, Nanjing University of Science & Technology, China, (2011)Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Computer and Electronic Information DepartmentShaanxi Xueqian Normal UniversityXi’anChina

Personalised recommendations