Ensemble-based machine learning approach for improved leak detection in water mains

Ravichandran, T.; Gavahi, Keyhan; Ponnambalam, K.; Burtea, V.; Mousavi, S. Jamshid

doi:10.2166/hydro.2021.093

Cited by 48 publications

(19 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This implies the loss of relevant information about the event along with noise separation and rejection. However, when combined with computational intelligence methods, acoustic signal analysis allows for the accurate diagnosis of the operating conditions of a water supply network [48]. All acoustic methods are affected by noise from the external (urban) environment [38].…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Development of Methods for Diagnosing the Operating Conditions of Water Supply Networks over the Last Two Decades

Stańczyk

Burszta‐Adamiak

2022

Water

View full text Add to dashboard Cite

The need for water supply companies to exercise control over the operating conditions of water supply networks has contributed to the development of a number of methods for their diagnosis. The diagnostics of technical infrastructure is a constantly developing field, and therefore, over the years, we have observed the development of various methods of diagnosing network operating conditions and their classification. The article presents, in a synthetic way, the division and review of the previously used methods of diagnosing the operating conditions of water supply networks. The authors also classified and assessed the usefulness of the methods of diagnosis in specific operating conditions. The review carried out by the authors shows that there is a need for research on the detection of operating conditions of water supply networks under the operating conditions of real systems. The results of our deep analysis allow for the understanding of the most important areas of research, as well as the existing worldwide trends in the development of methods for leak diagnosis and detection in water distribution networks. This review is a compendium of knowledge on the detection and diagnosis of water supply networks.

show abstract

Section: Discussionmentioning

confidence: 99%

“…In addition, the sensors can be placed at quite considerable distances from each other outside or inside of the pipeline. Acoustic sensors combined with machine learning are currently state-of-the-art in detecting water supply network operating conditions [48].…”

Section: Acoustic Signal Processingmentioning

confidence: 99%

Development of Methods for Diagnosing the Operating Conditions of Water Supply Networks over the Last Two Decades

Stańczyk

Burszta‐Adamiak

2022

Water

View full text Add to dashboard Cite

show abstract

“…This specific toolbox uses any ANN in a relatively simple and user-friendly way. The Levenberg-Marquardt (LMA) has been demonstrated to have very good and fast convergence results [31,32], this being the one proposed herein. This algorithm is widely used in optimization problems requiring non-linear least squares curve fitting, with a fast convergence.…”

Section: Problem Formulation and Ann Architecture Definitionmentioning

confidence: 99%

Near–Real Time Burst Location and Sizing in Water Distribution Systems Using Artificial Neural Networks

Capelo

Brentan

Monteiro

et al. 2021

Water

View full text Add to dashboard Cite

The current paper proposes a novel methodology for near–real time burst location and sizing in water distribution systems (WDS) by means of Multi–Layer Perceptron (MLP), a class of artificial neural network (ANN). The proposed methodology can be systematized in four steps: (1) construction of the pipe–burst database, (2) problem formulation and ANN architecture definition, (3) ANN training, testing and sensitivity analyses, (4) application based on collected data. A large database needs to be constructed using 24 h pressure–head data collected or numerically generated at different sensor locations during the pipe burst occurrence. The ANN is trained and tested in a real–life network, in Portugal, using artificial data generated by hydraulic extended period simulations. The trained ANN has demonstrated to successfully locate 60–70% of the burst with an accuracy of 100 m and 98% of the burst with an accuracy of 500 m and to determine burst sizes with uncertainties lower than 2 L/s in 90% of tested cases and lower than 0.2 L/s in 70% of the cases. This approach can be used as a daily management tool of water distribution networks (WDN), as long as the ANN is trained with artificial data generated by an accurate and calibrated WDS hydraulic models and/or with reliable pressure–head data collected at different locations of the WDS during the pipe burst occurrence.

show abstract

“…Researchers of this study represent an investigation of the capacity of six machine learning methods presented by the data generated using EPANET software, indicate that the supervised logistic regression and random forest method performed well to localize the leakage (4) . A multi-strategy ensemble learning(MEL) was presented in this research as an effective solution for an improvement in leak detection using acoustic techniques (5) . In this study, real-time transient model has been used to avoid the large numbers of false alarms with some data mining methods having its own merits and demerits (6) .…”

Section: Introductionmentioning

confidence: 99%

An Experimental Study to Locate Leakage in the Water Distribution Network using Real-time Wireless Sensor and Machine Learning Algorithm

Dalal¹,

Vasani²

2022

IJST

View full text Add to dashboard Cite

Objective: To pinpoint the leakage location using a machine learning algorithm on a real-time basis. Method: A laboratory experimental model was developed using wireless sensors for real-time data collection and monitoring the changes in the pressure and flow in presence of leakage under a different scenario. Modification in laboratory model was made considering Loop network of distribution pipes as compared to the simple experimental model. The model has been validated in EPANET software. The machine learning algorithm, along with the K-fold approach has been used to locate leakage and it was compared with other algorithms like Support Vector Machine (SVM), logistic regression, multilayer perceptron, Recurrent Neural Network-Long Short-Term Memory (RNN-LSTM), Principal Component Analysis (PCA), Artificial Neural Network (ANN), Random Forest, Gradient Boosting Tree (GBT) Classification, and Convolutional Neural Network (CNN). Findings: In this research, a system was developed based on real-time data received by Wireless Sensor Network (WSN) was demonstrated and it is able to find even a small leak by monitoring pressure and flow. The K-fold approach in machine learning algorithm has been used to locate the leakage in different variations made in the experimental model in terms of pressure, leak size, cross-section of pipe, and profile level of the pipe network. A comparison was also presented with other machine learning algorithms of recent research in terms of accuracy, size of the opening for the leak, type of experimental model used, and variables considered to locate the leakage. Novelty: It is the first research kind of work that shows the average accuracy of 78% to locate leakage based on the real-time experimental data in a loop network using the K-Fold approach.

show abstract

Ensemble-based machine learning approach for improved leak detection in water mains

Cited by 48 publications

References 45 publications

Development of Methods for Diagnosing the Operating Conditions of Water Supply Networks over the Last Two Decades

Development of Methods for Diagnosing the Operating Conditions of Water Supply Networks over the Last Two Decades

Near–Real Time Burst Location and Sizing in Water Distribution Systems Using Artificial Neural Networks

An Experimental Study to Locate Leakage in the Water Distribution Network using Real-time Wireless Sensor and Machine Learning Algorithm

Contact Info

Product

Resources

About