Prediction of Pipe Failure Rate in Heating Networks Using Machine Learning Methods DOI Creative Commons
Hristo Beloev, Stanislav Radikovich Saitov, А. А. Филимонова

et al.

Energies, Journal Year: 2024, Volume and Issue: 17(14), P. 3511 - 3511

Published: July 17, 2024

The correct prediction of heating network pipeline failure rates can increase the reliability heat supply to consumers in cold season. However, due large number factors affecting corrosion underground steel pipelines, it is difficult achieve high accuracy. purpose this study identify connections between rate pipelines and not taken into account traditional methods, such as residual wall thickness, soil activity, previous incidents on section, flooding (traces flooding) channel, intersections with communications. To goal, following machine learning algorithms were used: random forest, gradient boosting, support vector machines, artificial neural networks (multilayer perceptron). data collected related breakdown cities Kazan Ulyanovsk. Based these data, four intelligent models have been developed. accuracy was compared. best result obtained for boosting regression tree, follows: MSE = 0.00719, MAE 0.0682, MAPE 0.06069. feature «Previous section» excluded from training set least significant.

Language: Английский

Application of machine learning to leakage detection of fluid pipelines in recent years: A review and prospect DOI
Jianwu Chen, Xiao Wu, Zhibo Jiang

et al.

Measurement, Journal Year: 2025, Volume and Issue: unknown, P. 116857 - 116857

Published: Jan. 1, 2025

Language: Английский

Citations

1
Machine learning applications for anomaly detection in Smart Water Metering Networks: A systematic review DOI
Maria Nelago Kanyama, Fungai Bhunu Shava, Attlee M. Gamundani

et al.

Physics and Chemistry of the Earth Parts A/B/C, Journal Year: 2024, Volume and Issue: 134, P. 103558 - 103558

Published: Jan. 13, 2024

Language: Английский

Citations

7
Acoustic Identification of Water Supply Pipe Leakage Based on Bispectrum Analysis DOI
Zi‐Ming Feng,

Zhihong Long,

Liyun Peng

et al.

Journal of Pipeline Systems Engineering and Practice, Journal Year: 2025, Volume and Issue: 16(3)

Published: April 29, 2025

Language: Английский

Citations

0
Towards an Understanding of Hydraulic Sensitivity: Graph Theory Contributions to Water Distribution Analysis DOI Open Access
Meriem Adraoui, El Bachir Diop, Seyid Abdellahi Ebnou Abdem

et al.

Water, Journal Year: 2024, Volume and Issue: 16(5), P. 646 - 646

Published: Feb. 22, 2024

Water distribution systems (WDSs) are complex networks with numerous interconnected junctions and pipes. The robustness reliability of these critically dependent on their network structure, necessitating detailed analysis for proactive leak detection to maintain integrity functionality. This study addresses gaps in traditional WDS by integrating hydraulic measures graph theory improve sensitivity detection. Through case studies five distinct WDSs, we investigate the relationship between metrics. Our findings demonstrate collective impact factors system efficiency. research provides enhanced insights into operational dynamics highlights significant potential bolster resilience reliability.

Language: Английский

Citations

3
Foundations of Smart Water and Artificial Intelligence Technologies DOI
Jorge A. Ruíz-Vanoye, Ocotlán Díaz-Parra, Francisco Marroquín-Gutiérrez

et al.

IGI Global eBooks, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 30

Published: Feb. 18, 2025

The increasing global demand for water, compounded by the challenges posed climate change, urbanisation, and population growth, necessitates adoption of innovative solutions water management. Smart Water technologies, which encompass integration advanced sensors, data analysis, automated systems, offer a promising approach to optimising use enhancing sustainability. While remain, benefits adopting these technologies are substantial, warranting further investment research. As intensify, role systems will become increasingly critical in ensuring sustainable management this vital resource. This chapter explores components, benefits, providing comprehensive overview their modern

Language: Английский

Citations

0
Research on Leak Detection and Localization Algorithm for Oil and Gas Pipelines Using Wavelet Denoising Integrated with Long Short-Term Memory (LSTM)–Transformer Models DOI Creative Commons

Yunbin Ma,

Z. J. Shang, Jie Zheng

et al.

Sensors, Journal Year: 2025, Volume and Issue: 25(8), P. 2411 - 2411

Published: April 10, 2025

Traditional leakage prediction models for long-distance pipelines have limitations in effectively synchronizing spatial and temporal features of signals, leading to data processing that heavily relies on manual experience exhibits insufficient generalization capabilities. This paper introduces a novel detection localization algorithm oil gas pipelines, integrating wavelet denoising with Long Short-Term Memory (LSTM)-Transformer model. The proposed utilizes pressure sensors collect real-time pipeline applies eliminate noise from the signals. By combining LSTM’s feature extraction Transformer’s self-attention mechanism, we construct short-term average gradient-average instantaneous flow network model continuously predicts based gradient inputs, monitors deviations between actual predicted flow, employs curve distance accurately determine location. Experimental results Jilin-Changchun demonstrate possesses superior warning Specifically, accuracy reaches 99.995%, location error margin below 2.5%. Additionally, can detect leaks exceeding 0.6% main without generating false alarms during operation.

Language: Английский

Citations

0
Digital Twin Framework for Leakages Detection in Large-scale Water Distribution Systems: A Case Study of IIT-Jodhpur Campus DOI Open Access
Anushka Singh,

Abhilasha Maheshwari,

Shobhana Singh

et al.

IFAC-PapersOnLine, Journal Year: 2024, Volume and Issue: 57, P. 280 - 285

Published: Jan. 1, 2024

Sustainable development goals and industry 4.0 push for a holistic plan of action smart water infrastructure enabling advance digital technologies such as Digital Twins networks through an integrated use machine physical counterparts. This paper proposes Twin framework leakage detection applications in large scale distribution systems. The elucidates map generation the network, hydraulics modelling, calibration model manner using python interface. hydraulic accounting spatial temporal variations network optimization formulation graph neural identification has been developed. is applied, results have demonstrated on real-life case study IIT Jodhpur campus system.

Language: Английский

Citations

2
Optimizing energy storage plant discrete system dynamics analysis with graph convolutional networks DOI Creative Commons

Yangbing Lou,

Fengcheng Sun,

Jun Ni

et al.

Heliyon, Journal Year: 2024, Volume and Issue: 10(10), P. e31119 - e31119

Published: May 1, 2024

Addressing the challenges of suboptimal model performance and excessive parameters operations in optimization energy storage power plants utilizing Graph Convolutional Network (GCN), this paper introduces a novel approach - packet-switched graph convolutional network. Initially, GCN extreme learning machine is established. Drawing inspiration from solid foundation, we have innovatively crafted group exchange convolution module. This module leverages techniques to amalgamate unique node feature information, tailored diverse topology matrices based on various groupings. innovative ensures that information flows freely effectively among distinct Furthermore, designed cutting-edge timing depth separation module, comprising two components. The first component convolution, revolutionizing original second component, packet-switching network, revolutionizes time sequence process. It achieves by employing 1 × layers between different fusion packets, enabling seamless packets. Experimental results demonstrate efficacy proposed model, with root mean square error (RMSE) metrics (MAE) for single-step prediction reaching 46.08 26.22 at 60 min, respectively. In multi-step testing, exhibits 14.71 % reduction RMSE 15-min scale 9.29 60-min compared benchmark model. improvement enhances operational efficiency reliability plant, particularly under dynamic changes series.

Language: Английский

Citations

1
Water Leakage Classification With Acceleration, Pressure, and Acoustic Data: Leveraging the Wavelet Scattering Transform, Unimodal Classifiers, and Late Fusion DOI Creative Commons
Erick Axel Martinez-Ríos, David Barrientos, Rogelio Bustamante-Bello

et al.

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 84923 - 84951

Published: Jan. 1, 2024

Language: Английский

Citations

1
An Integrated Approach to Leak Detection in Water Distribution Networks (WDNs) Using GIS and Remote Sensing DOI Creative Commons

Rabab Al Hassani,

Tarig Ali, Md Maruf Mortula

et al.

Applied Sciences, Journal Year: 2023, Volume and Issue: 13(18), P. 10416 - 10416

Published: Sept. 18, 2023

Leakages in the water distribution networks (WDNs) are real problems for utilities and other governmental agencies. Timely leak detection location identification have been challenges. In this paper, an integrated approach to geospatial infrared image processing was used robust detection. The method combines drops flow, pressure, chlorine residuals determine potential leakage locations WDN using Geographic Information System (GIS) techniques. GIS layers were created from hourly values of these three parameters city Sharjah provided by Electricity, Water, Gas Authority (SEWA). These then analyzed with dropped each overlaid other. case where there no overlaying between flow further quality analysis avoided, assuming leak. pressure layers, examined values. If found, regions considered locations. Once identified, a specialized remote sensing technique can be pinpoint location. This study also demonstrated suitability camera laboratory-based setup. paper concludes that following methodology help utility companies timely leaks, saving money, time, effort.

Language: Английский

Citations

3