Water leak detection using self-supervised time series classification

Abstract Leaks in water distribution networks cause a loss of water that needs to be compensated to ensure a continuous supply for all customers. This compensation is achieved by increasing the flow of the network, which entails an undesirable economical expense as well as negative consequences for the environment. For these reasons, detecting and fixing leaks is a relevant task for water distribution companies. This paper proposes a water leak detection method based on a self-supervised classification of flow time series. The aim is to detect the leaks in the network, providing a low false positive rate. The proposed method is applied to two water distribution networks and compared to two other methods in the literature, obtaining the best balance between the number of false positives and detected leaks.

[1]  Nikos Komodakis,et al.  Unsupervised Representation Learning by Predicting Image Rotations , 2018, ICLR.

[2]  Ran El-Yaniv,et al.  Deep Anomaly Detection Using Geometric Transformations , 2018, NeurIPS.

[3]  Andrew J. Day,et al.  Sensor-fusion of hydraulic data for burst detection and location in a treated water distribution system , 2003, Inf. Fusion.

[4]  Zoran Kapelan,et al.  Automated Detection of Pipe Bursts and Other Events in Water Distribution Systems , 2014 .

[5]  Joby Boxall,et al.  Development and Verification of an Online Artificial Intelligence System for Detection of Bursts and Other Abnormal Flows , 2010 .

[6]  Xue Wu,et al.  Burst detection in district metering areas using a data driven clustering algorithm. , 2016, Water research.

[7]  Shuming Liu,et al.  Burst Detection by Analyzing Shape Similarity of Time Series Subsequences in District Metering Areas , 2020 .

[8]  F. J. Arregui,et al.  Burst Detection in Water Networks Using Principal Component Analysis , 2012 .

[9]  Richard Mounce,et al.  Novelty detection for time series data analysis in water distribution systems using support vector machines , 2011 .

[10]  Ioan Silea,et al.  A survey on gas leak detection and localization techniques , 2012 .

[11]  Karim Salahshoor,et al.  Pipeline leakage detection and isolation: An integrated approach of statistical and wavelet feature extraction with multi-layer perceptron neural network (MLPNN) , 2016 .

[12]  Wei Liu,et al.  Detection and interpretation of anomalous water use for non-residential customers , 2018, Environ. Model. Softw..

[13]  James Large,et al.  A tale of two toolkits, report the third: on the usage and performance of HIVE-COTE v1.0 , 2020, ArXiv.

[14]  Isam Shahrour,et al.  Leakage Detection Using Smart Water System: Combination of Water Balance and Automated Minimum Night Flow , 2017, Water Resources Management.

[15]  Jorge E. Pesantez,et al.  Review of Modeling Methodologies for Managing Water Distribution Security. , 2020, Journal of water resources planning and management.

[16]  Riku Vahala,et al.  Leakage detection in a real distribution network using a SOM , 2009 .

[17]  Jianping Yin,et al.  Effective End-to-end Unsupervised Outlier Detection via Inlier Priority of Discriminative Network , 2019, NeurIPS.

[18]  Tao Tao,et al.  A review of methods for burst/leakage detection and location in water distribution systems , 2015 .

[19]  Zoran Kapelan,et al.  Burst Detection and Location in Water Distribution Systems , 2011 .

[20]  Jose A. Lozano,et al.  Analyzing rare event, anomaly, novelty and outlier detection terms under the supervised classification framework , 2019, Artificial Intelligence Review.

[21]  G. Zhang,et al.  Real-Time Burst Detection in District Metering Areas in Water Distribution System Based on Patterns of Water Demand with Supervised Learning , 2018, Water.

[22]  Zoran Kapelan,et al.  REAL-TIME LEAK DETECTION IN WATER DISTRIBUTION SYSTEMS , 2011 .

[23]  Kate Smith,et al.  Burst Detection in District Metering Areas Using Deep Learning Method , 2020 .

[24]  P D Widdop,et al.  A neural network approach to burst detection. , 2002, Water science and technology : a journal of the International Association on Water Pollution Research.

[25]  Shuming Liu,et al.  A review of data-driven approaches for burst detection in water distribution systems , 2017 .

[26]  Jiheon Kang,et al.  Novel Leakage Detection by Ensemble CNN-SVM and Graph-Based Localization in Water Distribution Systems , 2018, IEEE Transactions on Industrial Electronics.

[27]  D. Vries,et al.  Application of machine learning techniques to predict anomalies in water supply networks , 2016 .

[28]  Francesco Piazza,et al.  A Statistical Framework for Automatic Leakage Detection in Smart Water and Gas Grids , 2016 .

[29]  Miss A.O. Penney.  (b) , 1974, The New Yale Book of Quotations.

[30]  R. Fenner,et al.  Kalman Filtering of Hydraulic Measurements for Burst Detection in Water Distribution Systems , 2011 .

[31]  R. Fenner,et al.  Weighted Least Squares with Expectation-Maximization Algorithm for Burst Detection in U.K. Water Distribution Systems , 2014 .

[32]  Stephen R. Mounce,et al.  Burst detection using hydraulic data from water distribution systems with artificial neural networks , 2006 .