Leak detection in water distribution systems using Bayesian theory and Fisher’s law

Abstract

A leak detection method based on Bayesian theory and Fisher’s law was developed for water distribution systems. A hydraulic model was associated with the parameters of leaks (location, extent). The randomness of parameter values was quantified by probability density function and updated by Bayesian theory. Values of the parameters were estimated based on Fisher’s law. The amount of leaks was estimated by back propagation neural network. Based on flow characteristics in water distribution systems, the location of leaks can be estimated. The effectiveness of the proposed method was illustrated by simulated leak data of node pressure head and flow rate of pipelines in a test pipe network, and the leaks were spotted accurately and renovated on time.

Keywords

water distribution systems / leak / detection / EPANET / Fisher’s law / Bayesian theory / back propagation neural network

References

[1] Gao Y., Brennan M. J., Joseph P. F., et al. On the selection of acoustic/vibration sensors for leak detection in plastic water pipes[J]. Journal of Sound and Vibration, 2005, 283(3/4/5): 927-941.

[2] Yang J., Wen Y., Li Ping. Leak location using blind system identification in water distribution pipelines[J]. Journal of Sound and Vibration, 2008, 310(1/2): 134-148.

[3] Gao Y., Brennan M. J., Joseph P. F. On the effects of reflections on time delay estimation for leak detection in buried plastic water pipes[J]. Journal of Sound and Vibration, 2009, 325(3): 649-663.

[4] Majid A., Mehrdad S. B. Leak detection in water-filled plastic pipes through the application of tuned wavelet transforms to acoustic emission signals[J]. Applied Acoustics, 2010, 71(7): 634-639.

[5] Mounce Stephen R., Asar K., Wood A. S., et al. Sensor-fusion of hydraulic data for burst detection and location in a treated water distribution system[J]. Information Fusion, 2003, 4(3): 217-229.

[6] Shih-Chu H., Wuu-Wen L., Meng-Tsan T., et al. Fiber optic in-line distributed sensor for detection and localization of the pipeline leaks[J]. Sensors and Actuators A: Physical, 2007, 135(2): 570-579.

[7] Matthaios B., Angelos A., Nikolaos U. Detection of water leaks in supply pipes using continuous wave sensor operating at 2. 45 GHz[J]. Journal of Applied Geophysics, 2010, 70(3): 226-236.

[8] Ellul I. R. Advances in pipeline leak detection techniques [J]. Pipes and Pipeline International, 1989, 34(3): 7-12.

[9] Mukherjee J., Narasimhan S. Leak detection in networks of pipelines by the generalized likelihood ratio method[J]. Industrial and Engineering Chemistry Research, 1996, 35(6): 1886-1893.

[10] Rougier J. Probabilistic leak detection in pipelines using the mass imbalance approach[J]. Journal of Hydraulic Research, 2005, 43(5): 556-566.

[11] Misiunas D., Vítkovský J., Olsson G., et al. Pipeline break detection using pressure transient monitoring[J]. Journal of Water Resources Planning and Management, 2005, 131(4): 316-325.

[12] Jung B S, Karney B W. A systematic exploration of uncertainty and convergence of inverse transient calibration for WDSs[C]. In: Proceedings of World Water and Environmental Resources Congress 2005. Anchorage, AK, United States, 2005.

[13] Poulakis Z., Valougeorgis D., Papadimitriou C. Leakage detection in water pipe network using a Bayesian probabilistic framework[J]. Probabilistic Engineering Mechanics, 2003, 18(4): 315-327.

[14] Vítkovský J. P., Simpson A. R., Lambert M. F. Leak detection and calibration using transients and genetic algorithms [J]. Journal of Water Resources Planning and Management, 2000, 126(4): 262-265.

[15] Wu Zheng, Boulos Paul, de Schaetzen W et al. Using genetic algorithms for water distribution system optimization[C]. In: Proceedings of World Water and Environmental Resources Congress 2001. Orlando, FL, United States, 2001.