Probabilistic multiple model neural network based leak detection system: experimental study

This paper presents an effective decision making system for leak detection based on multiple generalized linear models and clustering techniques. The training data for the proposed decision system is obtained by setting up an experimental pipeline fully operational distribution system. The system is also equipped with data logging for three variables; namely, inlet pressure, outlet pressure, and outlet flow. The experimental setup is designed such that multi-operational conditions of the distribution system, including multi pressure and multi flow can be obtained. We then statistically tested and showed that pressure and flow variables can be used as signature of leak under the designed multi-operational conditions. It is then shown that the detection of leakages based on the training and testing of the proposed multi model decision system with pre data clustering, under multi operational conditions produces better recognition rates in comparison to the training based on the single model approach. This decision system is then equipped with the estimation of confidence limits and a method is proposed for using these confidence limits for obtaining more robust leakage recognition results.

[1]  Mohammad Burhan Abdulla,et al.  Pipeline leak detection using artificial neural network: Experimental study , 2013, 2013 5th International Conference on Modelling, Identification and Control (ICMIC).

[2]  Feng Jian,et al.  Oil pipeline leak detection and location using double sensors pressure gradient method , 2004, Fifth World Congress on Intelligent Control and Automation (IEEE Cat. No.04EX788).

[3]  D.M. Mount,et al.  An Efficient k-Means Clustering Algorithm: Analysis and Implementation , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Wei Liang,et al.  A wave change analysis (WCA) method for pipeline leak detection using Gaussian mixture model , 2012 .

[5]  Xu Tian,et al.  Validation of k-Nearest Neighbor Classifiers Using Inclusion and Exclusion , 2014, ArXiv.

[6]  Wang Li.  Study on Detection Technique for Pipeline Leakage , 2003 .

[7]  Rubén Morales-Menéndez,et al.  Leaks Detection in a Pipeline Using Artificial Neural Networks , 2009, CIARP.

[8]  Venu Govindaraju,et al.  Improved k-nearest neighbor classification , 2002, Pattern Recognit..

[9]  Feng Jian,et al.  A New Fault Detection and Diagnosis Method for Oil Pipeline Based on Rough Set and Neural Network , 2007, ISNN 2007.

[10]  Yang Song,et al.  IKNN: Informative K-Nearest Neighbor Pattern Classification , 2007, PKDD.

[11]  Seung Ihl Kam,et al.  Mechanistic modeling of pipeline leak detection at fixed inlet rate , 2010 .

[12]  Douglas C. Montgomery,et al.  Applied Statistics and Probability for Engineers, Third edition , 1994 .

[13]  Ana Cristina Bicharra Garcia,et al.  ARTIFICIAL NEURAL NETWORKS ENSEMBLE USED FOR PIPELINE LEAK DETECTION SYSTEMS , 2008 .

[14]  Steve,et al.  Artificial Neural Network Model for a Low Cost Failure Sensor: Performance Assessment in Pipeline Distribution , 2008 .

[15]  David Al-Dabass,et al.  Decision support system for water distribution systems based on neural networks and graphs theory for leakage detection , 2012, Expert Syst. Appl..

[16]  Miroslav Kárný,et al.  Fully probabilistic control design in an adaptive critic framework , 2011, Neural Networks.

[17]  Kuan-Cheng Lin,et al.  Supervised Learning Probabilistic Neural Networks , 2011, Neural Processing Letters.

[18]  Shankar Narasimhan,et al.  Leak detection in gas pipeline networks using an efficient state estimator. Part-I: Theory and simulations , 2011, Comput. Chem. Eng..

[19]  E C Hedberg,et al.  The power of a paired t-test with a covariate. , 2015, Social science research.

[20]  M. Meribout.  A Wireless Sensor Network-Based Infrastructure for Real-Time and Online Pipeline Inspection , 2011, IEEE Sensors Journal.

[21]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.

[22]  Eric Bax,et al.  Validation of $k$-Nearest Neighbor Classifiers , 2012, IEEE Transactions on Information Theory.

[23]  Wei Liang,et al.  Detection of small leakage from long transportation pipeline with complex noise , 2011 .

[24]  Margaret J. Robertson,et al.  Design and Analysis of Experiments , 2006, Handbook of statistics.

[25]  Heng Tao Shen,et al.  Optimized Cartesian K-Means , 2014, IEEE Transactions on Knowledge and Data Engineering.

[26]  Salvatore Belsito,et al.  Leak detection in liquefied gas pipelines by artificial neural networks , 1998 .

[27]  Randa Herzallah,et al.  Distribution Modeling of Nonlinear Inverse Controllers Under a Bayesian Framework , 2007, IEEE Transactions on Neural Networks.

[28]  Sakti Pramanik,et al.  k-Nearest neighbor searching in hybrid spaces , 2014, Inf. Syst..

[29]  E. Ceulemans,et al.  Subspace K-means clustering , 2013, Behavior Research Methods.

[30]  Donald F. Specht,et al.  Probabilistic neural networks , 1990, Neural Networks.

[31]  H. A. David,et al.  The Paired t Test Under Artificial Pairing , 1997 .