PLOS Water · 2024 · 10 citations · 23 references
ComputingComputer ScienceWater Resources ManagementMachine LearningPredictive AnalyticsWater Resources EngineeringFault DetectionLeak DetectionLeak RepairFault Detection Using Machine LearningMachine Learning-based Fault DiagnosisPipe Burst PredictionPipesWater Leak DetectionWater Leakage Detection
Water is one of the essential matters that keeps living species alive; yet, the lifespan of pipes has two direct impacts on wasting water in very great amounts: pipe leakages and pipe bursts. Consequently, the proper detection of aged pipes in the water distribution networks has always been an issue in overcoming the problem. This makes water pipe monitoring an important duty of municipalities. Traditionally, leakages and bursts were only detected visually or through reports in local areas, leading municipalities to change the old pipes. Although this helps to fix the issue, a more desired way is to perhaps let officials know about the possibilities of such problems in advance by predicting which pipes are aged, so they can prevent the wastage. Therefore, to automate the detection process, in this study, we take the initial steps to predict the pipes needing repair in a particular area using machine learning methods. We first obtain a private dataset provided by the municipality of Saveh, Iran which outlines pipes that were damaged previously. We then train three machine learning algorithms to predict whether a set of pipes in an area is prone to damage. To achieve this, One-Class (OC) Classification methods such as OC-SVM, Isolation Forest, and Elliptic Envelope are used and they achieved the highest accuracy of 0.909. This study is of value since it requires zero additional devices (i.e., sensors).
23
SMOTE: Synthetic Minority Over-sampling Technique
Nitesh V. Chawla, Kevin W. Bowyer, Lawrence Hall et al. · Journal of Artificial Intelligence Research · 2002 · 31.2K citations · Full text
Pattern recognition and machine learning
Choice Reviews Online · 2007 · 2.7K citations
A critical overview of outlier detection methods
Abir Smiti · Computer Science Review · 2020 · 417 citations
Computing, Data Science, Data Mining +13
Deep learning identifies accurate burst locations in water distribution networks
Xiao Zhou, Zhenheng Tang, Weirong Xu et al. · Water Research · 2019 · 244 citations · Full text