Leakage Classification Based on Improved Kullback-Leibler Separation in Water Pipelines
One of the least difficult, quickest, and most useful strategies for the characteristic selection of real applications such as leak detection systems is the selection method based on Kullback-Leibler divergence. Nevertheless, this technique has issues when the preparation dataset is not sufficiently expansive. This paper proposes an improvement on this method to overcome its limitations. The assessment results show that the proposed strategy is steadier, more dependable, and has higher precision than the original technique.
KeywordsAcoustic emissions Leakage classification Kullback-Leibler divergence
This work was supported by the Korea Institute of Energy Technology Evaluation and Planning (KETEP) and the Ministry of Trade, Industry & Energy (MOTIE) of the Republic of Korea (No. 20172510102130, No. 20192510102510).
- 1.Frauendorfer, R., Liemberger, R.: The Issues and Challenges of Reducing Non-Revenue Water. Asian Development Bank (2010)Google Scholar
- 3.Sinha, D.N.: Acoustic sensor for pipeline monitoring. Gas Technology Management Division Strategic Center for Natural Gas and Oil National Energy Technology Laboratory, p. 2 (2005)Google Scholar
- 6.Brunner, A.J., Barbezat, M.: Acoustic emission monitoring of leaks in pipes for transport of liquid and gaseous media: a model experiment. In: Advanced Materials Research, pp. 351–356. Trans Tech Publications (2006)Google Scholar
- 8.Tang, X., Liu, Y., Zheng, L., Ma, C., Wang, H.: Leak detection of water pipeline using wavelet transform method. In: 2009 International Conference on Environmental Science and Information Application Technology, pp. 217–220. IEEE, (2009)Google Scholar
- 14.Anastasopoulos, A., Kourousis, D., Bollas, K.: Acoustic emission leak detection of liquid filled buried pipeline. J. Acoust. Emission 27, 27–39 (2009)Google Scholar
- 24.Moore, S.: A review of noise and vibration in fluid-filled pipe systems. Acoustics, Brisbane, Australia (2016)Google Scholar
- 25.Ribeiro, M.I.: Gaussian probability density functions: properties and error characterization. Institute for Systems and Robotics, Lisboa, Portugal (2004)Google Scholar