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

ABSTRACT 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.

[1]  Simplício Arnaud da Silva,et al.  Operational optimisation of water supply networks using a fuzzy system , 2012 .

[2]  Alberto Campisano,et al.  Field-Oriented Methodology for Real-Time Pressure Control to Reduce Leakage in Water Distribution Networks , 2016 .

[3]  Ruben Ruiz-Gonzalez,et al.  An Artificial Neural Network based expert system fitted with Genetic Algorithms for detecting the status of several rotary components in agro-industrial machines using a single vibration signal , 2015, Expert Syst. Appl..

[4]  Sigurd Skogestad,et al.  Simple analytic rules for model reduction and PID controller tuning , 2003 .

[5]  Kan-Jian Zhang,et al.  Theoretical and numerical analysis of learning dynamics near singularity in multilayer perceptrons , 2015, Neurocomputing.

[6]  Armando Carravetta,et al.  Hydropower Potential in Water Distribution Networks: Pressure Control by PATs , 2015, Water Resources Management.

[7]  Ismail Esen,et al.  Artificial neural network application for modeling the rail rolling process , 2014, Expert Syst. Appl..

[8]  Miguel Pinzolas,et al.  Neighborhood based Levenberg-Marquardt algorithm for neural network training , 2002, IEEE Trans. Neural Networks.

[9]  Enrico Creaco,et al.  RTC of Valves for Leakage Reduction in Water Supply Networks , 2010 .

[10]  Ahmed El-Shafie,et al.  Influence of bed deposit in the prediction of incipient sediment motion in sewers using artificial neural networks , 2018 .

[11]  Kevin James,et al.  Watergy: taking advantage of untapped energy and water efficiency opportunities in municipal water systems , 2002 .

[12]  B. Karney,et al.  Intrinsic relationship between energy consumption, pressure, and leakage in water distribution systems , 2017 .

[13]  Alberto Campisano,et al.  Calibration of Proportional Controllers for the RTC of Pressures to Reduce Leakage in Water Distribution Networks , 2012 .

[14]  Erol Egrioglu,et al.  Robust learning algorithm for multiplicative neuron model artificial neural networks , 2016, Expert Syst. Appl..

[15]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[16]  Enrico Creaco,et al.  Unsteady Flow Modeling of Pressure Real-Time Control in Water Distribution Networks , 2017 .

[17]  J. M. Cecilia,et al.  Estimation of Instantaneous Peak Flow Using Machine-Learning Models and Empirical Formula in Peninsular Spain , 2017 .

[18]  Enrico Creaco,et al.  A new algorithm for real-time pressure control in water distribution networks , 2013 .

[19]  Ivan Stoianov,et al.  Pipe Failure Analysis and Impact of Dynamic Hydraulic Conditions in Water Supply Networks , 2015 .

[20]  Jeehyun Jung,et al.  Modeling and parameter optimization for cutting energy reduction in MQL milling process , 2016 .

[21]  Ben Scheres,et al.  The plant perceptron connects environment to development , 2017, Nature.

[22]  Helena M. Ramos,et al.  Energy Cost Optimization in a Water Supply System Case Study , 2013 .

[23]  Dieu Tien Bui,et al.  Hybrid integration of Multilayer Perceptron Neural Networks and machine learning ensembles for landslide susceptibility assessment at Himalayan area (India) using GIS , 2017 .

[24]  Luis Garrote,et al.  Pressure Management in Water Distribution Systems: Current Status, Proposals, and Future Trends , 2016 .

[25]  Ioan Sarbu,et al.  A Study of Energy Optimisation of Urban Water Distribution Systems Using Potential Elements , 2016 .

[26]  Heber Pimentel Gomes,et al.  Intelligent system for control of water distribution networks , 2018 .

[27]  Luis Garrote,et al.  Use of Pressure Management to Reduce the Probability of Pipe Breaks: A Bayesian Approach , 2015 .

[28]  Philip R. Page,et al.  Real-time Adjustment of Pressure to Demand in Water Distribution Systems: Parameter-less P-controller Algorithm☆ , 2016 .

[29]  Luigi Glielmo,et al.  Real-Time Control of a PRV in Water Distribution Networks for Pressure Regulation: Theoretical Framework and Laboratory Experiments , 2018 .