Neural network using the Levenberg-Marquardt algorithm for optimal real-time operation of water distribution systems

被引：9

作者：

Moura, Geraldo de Araujo ^{[1
]}

Marques Bezerra, Saulo de Tarso ^{[2
]}

Gomes, Heber Pimentel ^{[3
]}

da Silva, Simplicio Arnaud ^{[4
]}

机构：

[1] Inst Fed Paraiba, Dept Design Infrastruct & Environm, Joao Pessoa, Paraiba, Brazil

[2] Univ Fed Pernambuco, Ctr Agreste Reg, Dept Technol, Caruaru, PE, Brazil

[3] Univ Fed Paraiba, Dept Civil & Environm Engn, Joao Pessoa, Paraiba, Brazil

[4] Univ Fed Paraiba, Dept Elect Engn, Joao Pessoa, Paraiba, Brazil

来源：

URBAN WATER JOURNAL | 2018年 / 15卷 / 07期

关键词：

Water supply; control system; pressure control; hydraulic and energy efficiency; artificial neural network; SUPPLY NETWORKS; PRESSURE CONTROL; REDUCTION; LEAKAGE; OPTIMIZATION; RTC;

D O I：

10.1080/1573062X.2018.1539503

中图分类号：

TV21 [水资源调查与水利规划];

学科分类号：

081501 ;

摘要：

This paper proposes an Adaptive Neural Network (NN) controller for the real-time pressure control in water distribution systems. Pressure control is one of the main technical options that can be implemented by a water utility to increase the hydraulic and energy efficiency of systems. The network adopted the Levenberg-Marquardt backpropagation algorithm, being responsible for maintaining the pump head at an optimal value, eliminating the excess pressure of the system. The advantage of the approach is that, once the network is trained, it allows instantaneous evaluation of solutions at any desired number of points; thus, spending little computing time. The controller was applied in the experimental setup, and the results showed excellent performance regarding pressure regulation. Finally, it is expected that the NN controller can be easily implemented in similar water distribution systems.

引用

页码：692 / 699

页数：8

共 30 条

[1] Artificial neural network application for modeling the rail rolling process [J].

Altinkaya, Huseyin ;

Orak, Ilhami M. ;

Esen, Ismail .

EXPERT SYSTEMS WITH APPLICATIONS, 2014, 41 (16) :7135-7146

[2]

[Anonymous], 8506 ICS U CAL SAN D

[3] Intelligent system for control of water distribution networks [J].

Barros Filho, Emanuel Guerra ;

Salvino, Lais Regis ;

Marques Bezerra, Saulo de Tarso ;

Salvino, Moises Menezes ;

Gomes, Heber Pimentel .

WATER SCIENCE AND TECHNOLOGY-WATER SUPPLY, 2018, 18 (04) :1270-1281

[4] Robust learning algorithm for multiplicative neuron model artificial neural networks [J].

Bas, Eren ;

Uslu, Vedide Rezan ;

Egrioglu, Erol .

EXPERT SYSTEMS WITH APPLICATIONS, 2016, 56 :80-88

[5] Hybrid integration of Multilayer Perceptron Neural Networks and machine learning ensembles for landslide susceptibility assessment at Himalayan area (India) using GIS [J].

Binh Thai Pham ;

Dieu Tien Bui ;

Prakash, Indra ;

Dholakia, M. B. .

CATENA, 2017, 149 :52-63

[6] Field-Oriented Methodology for Real-Time Pressure Control to Reduce Leakage in Water Distribution Networks [J].

Campisano, A. ;

Modica, C. ;

Reitano, S. ;

Ugarelli, R. ;

Bagherian, S. .

JOURNAL OF WATER RESOURCES PLANNING AND MANAGEMENT, 2016, 142 (12)

[7] Calibration of Proportional Controllers for the RTC of Pressures to Reduce Leakage in Water Distribution Networks [J].

Campisano, A. ;

Modica, C. ;

Vetrano, L. .

JOURNAL OF WATER RESOURCES PLANNING AND MANAGEMENT, 2012, 138 (04) :377-384

[8] RTC of Valves for Leakage Reduction in Water Supply Networks [J].

Campisano, A. ;

Creaco, E. ;

Modica, C. .

JOURNAL OF WATER RESOURCES PLANNING AND MANAGEMENT, 2010, 136 (01) :138-141

[9] A new algorithm for real-time pressure control in water distribution networks [J].

Creaco, E. ;

Franchini, M. .

WATER SCIENCE AND TECHNOLOGY-WATER SUPPLY, 2013, 13 (04) :875-882

[10] Unsteady Flow Modeling of Pressure Real-Time Control in Water Distribution Networks [J].

Creaco, Enrico ;

Campisano, Alberto ;

Franchini, Marco ;

Modica, Carlo .

JOURNAL OF WATER RESOURCES PLANNING AND MANAGEMENT, 2017, 143 (09)

← 1 2 3 →