Machine Learning Approach for Blockage Detection and Localization using Pressure Transients

Pipe networks in industries and water distribution systems are prone to the formation of blockages resulting in higher pumping requirements. Thus, detection and localization of blockages are of prime importance to maintain the operational efficiency of the system. In this work, a method is proposed to detect the existence, location, and magnitude of discrete blockages in a single pipeline using pressure transients. The pressure transients interact with blockages and thus the data obtained from them contain necessary features to identify pipeline blockage conditions. Features are extracted from experimentally obtained pressure signals using the TSFresh algorithm and stationary wavelet transform. Recursive feature elimination and support vector machines are used for feature selection and building the classifiers respectively. Three classifiers were built for classifying between blocked-unblocked conditions, locations of blockages, and magnitude of the blockages which resulted in the accuracies of 93.44%, 89.96%, and 80.67% respectively. Another classifier built for the combination of all the above cases resulted in 86.58% accuracy.

[1]  Silvia Meniconi,et al.  Diagnosis of Pipe Systems by means of a Stochastic Successive Linear Estimator , 2013, Water Resources Management.

[2]  Huan-Feng Duan,et al.  Transient Wave-blockage Interaction in Pressurized Water Pipelines☆ , 2014 .

[3]  Shantanu Datta,et al.  A review on different pipeline fault detection methods , 2016 .

[4]  Alexander Gegov,et al.  Blockage Detection in Pipeline Based on the Extended Kalman Filter Observer , 2020 .

[5]  Ahmed M. A. Sattar,et al.  Partial Blockage Detection in Pipelines by Frequency Response Method , 2008 .

[6]  Zao Feng,et al.  Multiple Blockage Identification of Drainage Pipeline Based on VMD Feature Fusion and Support Vector Machine , 2019, 2019 IEEE 8th Data Driven Control and Learning Systems Conference (DDCLS).

[7]  Zao Feng,et al.  Pipeline Blockage Detection Based on Sparse Characterization Classification Enhanced by VMD , 2019, 2019 IEEE 8th Data Driven Control and Learning Systems Conference (DDCLS).

[8]  Howard Rosenbaum,et al.  Effects of reading proficiency on embedded stem priming in primary school children , 2021 .

[9]  Jong Min Lee,et al.  Diagnosis of partial blockage in water pipeline using support vector machine with fault-characteristic peaks in frequency domain , 2017 .

[10]  Nur Liyana Tajul Lile,et al.  Blockage Detection in Circular Pipe Using Vibration Analysis , 2012 .

[11]  Huan-Feng Duan,et al.  Experimental Investigation of Coupled Frequency and Time-Domain Transient Test–Based Techniques for Partial Blockage Detection in Pipelines , 2013 .

[12]  M. Chaudhry,et al.  Detection of Partial Blockage in Single Pipelines , 2006 .

[13]  B. Silverman,et al.  The Stationary Wavelet Transform and some Statistical Applications , 1995 .

[14]  Andreas W. Kempa-Liehr,et al.  Time Series FeatuRe Extraction on basis of Scalable Hypothesis tests (tsfresh - A Python package) , 2018, Neurocomputing.

[15]  Huan-Feng Duan,et al.  Multiple-fault detection in water pipelines using transient-based time-frequency analysis , 2016 .

[16]  Yeou-Koung Tung,et al.  Extended Blockage Detection in Pipes Using the System Frequency Response: Analytical Analysis and Experimental Verification , 2013 .