scholarly journals Real-time neuro-fuzzy controller for pressure adjustment in water distribution systems

Author(s):  
Hugo Augusto Marinho Moreira ◽  
Heber Pimentel Gomes ◽  
Juan Moises Mauricio Villanueva ◽  
Saulo de Tarso Marques Bezerra

Abstract This work applied a neuro-fuzzy technique for real-time pressure control in water distribution systems with variable demand. The technique acted to control the rotation speed of the pumping system, aiming mainly at increasing energy efficiency. Fuzzy, neural and neuro-fuzzy controllers were tested in an experimental setup to compare their performances in a transient regime, a permanent regime, and with respect to disturbances applied to the system. To evaluate the efficiency of the system, a demand variation curve was emulated for different operating conditions. The results demonstrate that the neuro-fuzzy controller (NFC) presented a significant increase in pumping system efficiency and a reduction in specific energy consumption of up to 392% when compared to the other controllers. Target pressures were kept close to the set-point values with low hydraulic transients and maintained satisfactory stability (error <8%) under severe situations of demand variation. It is concluded that the NFC presented superior results when compared with the other analyzed controllers.

Water ◽  
2021 ◽  
Vol 13 (4) ◽  
pp. 463
Author(s):  
Gopinathan R. Abhijith ◽  
Leonid Kadinski ◽  
Avi Ostfeld

The formation of bacterial regrowth and disinfection by-products is ubiquitous in chlorinated water distribution systems (WDSs) operated with organic loads. A generic, easy-to-use mechanistic model describing the fundamental processes governing the interrelationship between chlorine, total organic carbon (TOC), and bacteria to analyze the spatiotemporal water quality variations in WDSs was developed using EPANET-MSX. The representation of multispecies reactions was simplified to minimize the interdependent model parameters. The physicochemical/biological processes that cannot be experimentally determined were neglected. The effects of source water characteristics and water residence time on controlling bacterial regrowth and Trihalomethane (THM) formation in two well-tested systems under chlorinated and non-chlorinated conditions were analyzed by applying the model. The results established that a 100% increase in the free chlorine concentration and a 50% reduction in the TOC at the source effectuated a 5.87 log scale decrement in the bacteriological activity at the expense of a 60% increase in THM formation. The sensitivity study showed the impact of the operating conditions and the network characteristics in determining parameter sensitivities to model outputs. The maximum specific growth rate constant for bulk phase bacteria was found to be the most sensitive parameter to the predicted bacterial regrowth.


2018 ◽  
Vol 54 (8) ◽  
pp. 5536-5550 ◽  
Author(s):  
Xiao Zhou ◽  
Weirong Xu ◽  
Kunlun Xin ◽  
Hexiang Yan ◽  
Tao Tao

Author(s):  
Philip R. Page ◽  
Adnan M. Abu-Mahfouz ◽  
Olivier Piller ◽  
Matome L. Mothetha ◽  
Muhammad S. Osman

2011 ◽  
Vol 77 (8) ◽  
pp. 2813-2816 ◽  
Author(s):  
Syreeta L. Miles ◽  
Ryan G. Sinclair ◽  
Mark R. Riley ◽  
Ian L. Pepper

ABSTRACTThis study evaluated real-time sensing ofEscherichia colias a microbial contaminant in water distribution systems. Most sensors responded to increasedE. coliconcentrations, showing that select sensors can detect microbial water quality changes and be utilized as part of a contaminant warning system.


Sign in / Sign up

Export Citation Format

Share Document