Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
The role of artificial intelligence in preventing water leakages from water supply networks
Introduction. One of foundations for the sustainable development and improvement of centralized water supply networks (CWN) and sanitation is the use of artificial intelligence (AI) based on machine learning (ML) algorithms and models: supervised, unsupervised, reinforcement learning. Leaks and unauthorized connections to CWN pose risks, leading to losses of drinking water and reduced pricing in the field of water resource metering. The relevance is associated with solving practical AI problems based on the latest innovations — forecasting and preventing accidents at CWN with optimal planning of repair work and timely maintenance. The purpose of study is to substantiate the role of AI using ML tools in the tasks of predicting pipeline failures and emergency situations in CWN.Materials and methods. The study of information on the role of AI in preventing water leaks from water supply networks was carried out using the method of literature review of the used AI algorithms for predicting pipe failures in CWN.Results. The ML models used for diagnostic analysis to predict water leaks from CWN are identified and presented. The review of technologies shows the use of 18 ML algorithms to solve problems related to leaks in CWN. Start of use of Kohonen neural network algorithms (KNN) in Russia indicates the availability of the only neural network software translated into Russian, STATISTICA Automated Neural Networks. Acoustic and ultrasonic methods for monitoring the condition of underground pipeline networks, based on the propagation of volumetric and directional waves (noise), are beginning to develop rapidly.Conclusions. Among the conclusions — for the Sustainable Development of CWN, water utilities need to ensure reliable and continuous data collection, this is a key practice that will help make reliable decisions based on AI predictions after the ML phase. Databases may include: pipe diameter, length of the section and age of the pipe, pressure, type of soil. The pressure itself (or difference) in the network is not a sign of an accident. This parameter should be considered together with the number of network failures (accidents) in the sections.
The role of artificial intelligence in preventing water leakages from water supply networks
Introduction. One of foundations for the sustainable development and improvement of centralized water supply networks (CWN) and sanitation is the use of artificial intelligence (AI) based on machine learning (ML) algorithms and models: supervised, unsupervised, reinforcement learning. Leaks and unauthorized connections to CWN pose risks, leading to losses of drinking water and reduced pricing in the field of water resource metering. The relevance is associated with solving practical AI problems based on the latest innovations — forecasting and preventing accidents at CWN with optimal planning of repair work and timely maintenance. The purpose of study is to substantiate the role of AI using ML tools in the tasks of predicting pipeline failures and emergency situations in CWN.Materials and methods. The study of information on the role of AI in preventing water leaks from water supply networks was carried out using the method of literature review of the used AI algorithms for predicting pipe failures in CWN.Results. The ML models used for diagnostic analysis to predict water leaks from CWN are identified and presented. The review of technologies shows the use of 18 ML algorithms to solve problems related to leaks in CWN. Start of use of Kohonen neural network algorithms (KNN) in Russia indicates the availability of the only neural network software translated into Russian, STATISTICA Automated Neural Networks. Acoustic and ultrasonic methods for monitoring the condition of underground pipeline networks, based on the propagation of volumetric and directional waves (noise), are beginning to develop rapidly.Conclusions. Among the conclusions — for the Sustainable Development of CWN, water utilities need to ensure reliable and continuous data collection, this is a key practice that will help make reliable decisions based on AI predictions after the ML phase. Databases may include: pipe diameter, length of the section and age of the pipe, pressure, type of soil. The pressure itself (or difference) in the network is not a sign of an accident. This parameter should be considered together with the number of network failures (accidents) in the sections.
The role of artificial intelligence in preventing water leakages from water supply networks
V. I. Bazhenov (Autor:in) / O. G. Primin (Autor:in) / V. V. Bazhenov (Autor:in)
2024
Aufsatz (Zeitschrift)
Elektronische Ressource
Unbekannt
Metadata by DOAJ is licensed under CC BY-SA 1.0
Identification of leakages in water networks-virtual distortion method approach
| British Library Conference Proceedings | 2003
Benchmarks to minimize water leakages in basements
| British Library Online Contents | 2003
Benchmarks to minimize water leakages in basements
| Online Contents | 2003