Master thesis presentation: Monitoring Water Distribution Network using Machine Learning

Abstract: Around one-third of water utilities across the globe report a loss of 40% of clean water due to leakage. The increase in pumping, treatment and operational costs are pushing water utilities to combat water loss by developing methods to detect, locate and fix leaks. However, traditional pipeline leakage detection methods require periodical inspection with large-scale human involvement, which makes it slow and inefficient for leakage detection in a timely manner. An alternative is on-line, continuous, real-time monitoring of the network facilitating early detection and localization of these leakages. This thesis aims to find such an alternative using various Machine Learning techniques.
In the thesis, for a water distribution network, out of the several available junction nodes, a method is proposed based on the concept of dominant nodes, which finds out the number of sensors required, their corresponding locations in the network and sub-divides the network into corresponding leakage zones. Thereafter, training data is acquired by virtually injecting leakages in the network using hydraulic simulation software. The time-series pressure data obtained through this process is pre-processed using one-dimensional wavelet series decomposition.

This pre-processed data serves as a basis for recognition of patterns and regularities in the data using supervised Machine learning techniques such as Logistic Regression, Support Vector Machine and Artificial Neural Network. Furthermore, ensemble of these trained model is used to build a better model for leakage detection and its localization. In addition to it, Random Forest algorithm is trained and its performance is compared to the obtained ensemble of earlier models. Also, leak size estimation is performed using Support Vector Regression algorithm.

It is observed that the sensor node placement using proposed algorithm provides a better leakage localization resolution than random deployment of sensor. Moreover, it is noticed that Random Forest algorithm performs better than the ensemble model except for the low leakage scenario. Thus, it is concluded to estimate the leak size first using Support Vector Regression. Based on this estimation, for small leakage case ensemble models can be applied while for large leakage case only Random Forest is sufficient to predict leakage detection and its localization in the network.