A fault sensitivity analysis for anomaly detection in water distribution systems using Machine Learning algorithms

The introduction of Machine Learning in large scale utility networks extends the room for improvement in the quality of service and maintenance costs. The ever expanding network of smart meters allows for a more accurate estimation of the state of the water distribution systems, at the same time requiring modern data processing solutions. By fusion with the more traditional approach in this field of research it is possible to enhance the existing capabilities for network analysis and to extend the algorithms to the level of cognitive abilities that form a basis for more efficient decision support system. In this paper we extend the fault sensitivity analysis for water distribution systems with the insights provided by state-of-the-art Machine Learning algorithms for data clustering and anomaly detection.

[1]  Ana L. N. Fred,et al.  Data clustering using evidence accumulation , 2002, Object recognition supported by user interaction for service robots.

[2]  Peter Friess,et al.  Internet of Things: Converging Technologies for Smart Environments and Integrated Ecosystems , 2013 .

[3]  Ciprian Lupu,et al.  Consideration on Leak/Fault Detection System in Mass Transfer Networks☆ , 2017 .

[4]  Sindre Oven Leak Detection in Pipelines by the use of State and Parameter Estimation , 2014 .

[5]  Ciprian Lupu,et al.  A Multiple-Layer Clustering Method for Real-Time Decision Support in a Water Distribution System , 2018, BIS.

[6]  Muhammad Umar,et al.  Integrative Review of Decentralized and Local Water Management Concepts as Part of Smart Cities (LoWaSmart) , 2016 .

[7]  W. R. Furnass,et al.  Clustering and classification of aggregated smart meter data to better understand how demand patterns relate to customer type , 2016 .

[8]  Rolf Isermann,et al.  Process fault detection based on modeling and estimation methods - A survey , 1984, Autom..

[9]  Paul Honeine,et al.  Detection of cyberattacks in a water distribution system using machine learning techniques , 2016, 2016 Sixth International Conference on Digital Information Processing and Communications (ICDIPC).

[10]  N. C. Turner,et al.  Hardware and Software Techniques for Pipeline Integrity and Leak Detection Monitoring , 1991 .

[11]  Ciprian Lupu,et al.  Modeling the Effects of Leaks on Measured Parameters in a Water Distribution System , 2017, 2017 21st International Conference on Control Systems and Computer Science (CSCS).

[12]  Magnus Moglia,et al.  Decision support system for water pipeline renewal prioritisation , 2006, J. Inf. Technol. Constr..