Leak detection of oil transport pipelines based on prediction and modeling

For solving the problem of discriminating leaks and valve adjusting operations in leak detection of oil pipeline based on dynamic pressure transducer (DPT). In this paper, the fuzzy neural system (FNS) based chaos time series prediction method is used to detect and locate the leakage based on DPT pressure signals. Offline tests based on the real historical data demonstrate that the proposed method can not only discriminate the leak from valve adjusting operations effectively, but also achieve satisfying detection and location precision.

[1]  F. Takens.  Detecting strange attractors in turbulence , 1981 .

[2]  P. Grassberger,et al.  Measuring the Strangeness of Strange Attractors , 1983 .

[3]  C. Mira,et al.  Chaotic Dynamics: From the One-Dimensional Endomorphism to the Two-Dimensional Diffeomorphism , 1987 .

[4]  Chet Sandberg,et al.  The application of a continuous leak detection system to pipelines and associated equipment , 1988 .

[5]  M. Rosenstein,et al.  A practical method for calculating largest Lyapunov exponents from small data sets , 1993 .

[6]  Shoji Suzuki,et al.  Short-Term Prediction of Chaotic Time Series by Local Fuzzy Reconstruction Method , 1997, J. Intell. Fuzzy Syst..

[7]  M. Taniguchi,et al.  Industrial applications of short-term prediction on chaotic time series by local fuzzy reconstruction method , 1997, Proceedings of 1st International Conference on Conventional and Knowledge Based Intelligent Electronic Systems. KES '97.

[8]  W. Wang,et al.  The application of a correlation dimension in large rotating machinery fault diagnosis , 2000 .

[9]  Spyros G. Tzafestas,et al.  Computational Intelligence Techniques for Short-Term Electric Load Forecasting , 2001, J. Intell. Robotic Syst..

[10]  Francesco Camastra,et al.  Neural Short-Term Prediction Based on Dynamics Reconstruction , 1999, Neural Processing Letters.

[11]  Hao Ye,et al.  Leak Detection in Transport Pipelines Using Enhanced Independent Component Analysis and Support Vector Machines , 2005, ICNC.

[12]  Junaid Khan,et al.  Fuzzy neural very-short-term load forecasting based on chaotic dynamics reconstruction , 2006 .