Leakage detection and localization on water transportation pipelines: a multi-label classification approach

Abstract

One of the main problems of water transportation pipelines is leak which can cause water resources loss, possible human injuries, and damages to the environment. There are many studies in the literature focusing on detection and localization of leaks in the water pipeline systems. In this study, we have designed a wireless sensor network-based real-time monitoring system to detect and locate the leaks on multiple positions on water pipelines by using pressure data. At first, the pressure data are collected from wireless pressure sensor nodes. After that, unlike from the previous works in the literature, both the detection and localization of leakages are carried out by using multi-label learning methods. We have used three multi-label classification methods which are RAkELd, BRkNN, and BR with SVM. After the evaluation and comparison of the methods with each other, we observe that the RAkELd method performs best on almost all measures with the accuracy ratio of 98%. As a result, multi-label classification methods can be used on the detection and localization of the leaks in the pipeline systems successfully.