A leakage detection system on the Water Pipe Network through Support Vector Machine method

Salam, A. Ejah Umraeni; Tola, Muhammad; Selintung, Mary; Maricar, Farouk

doi:10.1109/miceei.2014.7067331

Cited by 9 publications

(5 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used five classifiers, k-nearest neighbors (KNN) [27], radial basis function (RBF)-SVM [22], linear (LIN)-SVM [30], back-propagation neural network (BPNN) [25] and random forest (RF) [23], to achieve the partition-level recognition results for the processed data obtained by the proposed and referenced methods. Considering the overall classification performance, the Monte Carlo method was used to determine the optimal parameters of these classifiers in Table 3.…”

Section: Model Settingsmentioning

confidence: 99%

“…The flaws of this method are its lack of interpretability and the time cost of model training. The machine learning approach includes clustering [7], Bayesian classifier [21], support vector machine (SVM) [22], and random forest [23]. It learns uncertain, strictly interpretable and nonlinear relationships between monitoring parameters and burst events [24].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Pipeline-Burst Detection on Imbalanced Data for Water Supply Networks

Wang

Liu

Zhang

2023

Water

View full text Add to dashboard Cite

Data-driven methods based on samples from a supervisory control and data acquisition system have been widely applied in water-supply-network burst detection to save unexpected economic and labor costs. However, the class imbalance problem in actual on-site monitoring needs to be revised to improve the performance of data-driven methods. In this study, we proposed a domain adaptation method to generate minor-category samples (pipeline-burst samples in general) of arbitrary pipe networks utilizing theoretical hydraulic models. The proposed method transferred pipeline-burst data generated from a random water supply network with theoretical hydraulic models to an actual imbalanced dataset. Accordingly, we established a machine learning model exploring a mapping matrix between two domains for minority-category data transfer. The experimental validation first verified the effectiveness and reliability of the proposed method between two customized water supply networks in terms of their bust recognition accuracy, model parameter sensitivity and time efficiency. Then, an actual monitoring dataset from a working water supply network was used to prove the suitability and compatibility of the proposed method. A bust-point location method was also provided based on the detection results of pipeline-bursting events. The validations show the superiority of our proposed approach for the imbalance data problem in pipe burst detection.

show abstract

Section: Model Settingsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Pipeline-Burst Detection on Imbalanced Data for Water Supply Networks

Wang

Liu

Zhang

2023

Water

View full text Add to dashboard Cite

show abstract

“…Compression data is obtained from simulation results using EPANET 2.0. To train the system detects the size and location of the leakage data with the pressure analysis obtained from EPANET using the neural network method [16]. A simpler energy efficiency solution provided for monitoring water quality inside pipes based on Internet of Things technology and analyzing the data uploaded online and gives an alert to the remote user, when water quality standards deviate from the predefined set of standard values [17].…”

Section: Literature Reviewmentioning

confidence: 99%

IoT- Based Design and Development Remote Drinking Water Quality Monitoring and Analysis System

Elhabian

2022

Journal of the ACS Advances in Computer Science

View full text Add to dashboard Cite

Today, smart solutions are gaining more importance with the communication technology in all areas of life by governments. Especially if the issue is concerned with the health of citizens, and since drinking water is the most important requirement of life, so the great care of governments is to confirm the validity of drinking water, usually by using specific equipment where the water quality is tested on all characteristics such as minerals, temperature, etc. This process takes more time to complete for the selected sample. In this paper, the design implementation and development of a system for monitoring the quality of drinking water using Internet of Things (IoT) technology is presented and explained. The proposed system consists of several sensors to measure different variables such as pH value, turbidity in water, dissolved oxygen and, temperature and humidity. Also, a microcontroller unit (MCU) is connected with these sensors and further processing is done on the personal computer (PC). The data obtained is sent to the cloud using to the point of interest by Wi-Fi Module, can be viewed online using the Internet of Thing (IoT) technology and ThinkSpeak IoT-based application for water quality monitoring. The uniqueness of our proposed paper are obtain high frequency water control system, high mobility, was implemented, manufactured and tested in one of the localities and low power.

show abstract

“…They found that they could locate the bursts with an accuracy of 98.33%. Salam et al [14] investigated an on-line monitoring system to detect leakages in pipe networks. They used a network from Makassar in Indonesia.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Pipe network leak detection: comparison between statistical and machine learning techniques

Walt

Heyns

Wilke

2018

Urban Water Journal

View full text Add to dashboard Cite

This paper investigates an inverse analysis technique to find leaks in water networks and compares different solution strategies. Although a number of strategies have been proposed by different authors to identify leaks on a vast selection of pipe networks, limited research has been done to compare strategies and point out their weakness. Three strategies, a Bayesian Probabilistic Analysis, a Support Vector machine and, an Artificial Neural Network were combined with the inverse analysis technique on different numerical and experimental networks to point out each strategies weakness. Two numerical networks are investigated and one experimental network. It is shown that the Bayesian Probabilistic Analysis struggles to find unique solutions when a few observations are available, while the Support Vector Machine and the Artificial Neural Network struggle when only flow measurements are available. Additionally it is shown that the Artificial Neural Network struggles to estimate unique solutions for leak size and location.

show abstract

A leakage detection system on the Water Pipe Network through Support Vector Machine method

Cited by 9 publications

References 1 publication

Pipeline-Burst Detection on Imbalanced Data for Water Supply Networks

Pipeline-Burst Detection on Imbalanced Data for Water Supply Networks

IoT- Based Design and Development Remote Drinking Water Quality Monitoring and Analysis System

Pipe network leak detection: comparison between statistical and machine learning techniques

Contact Info

Product

Resources

About