Neural network-based modelling of the adequate chlorine dosage for drinking water disinfection

1996 ◽  
Vol 23 (3) ◽  
pp. 621-631 ◽  
Author(s):  
Manuel J. Rodriguez ◽  
Jean-B. Sérodes
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Water Quality ◽  
Drinking Water ◽  
Distribution System ◽  
Distribution Systems ◽  
Water Disinfection ◽  
Network Modelling ◽  
Chlorination Process ◽  
Routine Tasks

A neural network modelling approach has been developed to estimate the disinfectant dose adjustments required during water re-chlorination in storage tanks. The approach is based on representative operational and water quality historical data which intrinsically characterize the operators' use of know-how in their routine tasks. The development of the model requires the elimination of the historical cases in which re-chlorination results were inadequate. The results obtained for the model demonstrate that neural networks are capable of satisfactorily identifying the knowledge patterns contained in data with regard to the re-chlorination process for both winter and summer conditions. The practical use of such a model may assist operators in adjusting re-chlorination doses and may favour chlorine economization and the improvement of the water quality in the distribution system. Key words: drinking water, neural networks, distribution systems, chlorination, modelling, water quality.

Sensory aspects of drinking water in contact with epoxy lined copper pipe

2007 ◽  
Vol 55 (5) ◽  
pp. 161-168 ◽  
Author(s):  
T.H. Heim ◽  
A.M. Dietrich
Keyword(s):  
Water Quality ◽  
Drinking Water ◽  
Organic Compounds ◽  
Sensory Analysis ◽  
Water Samples ◽  
Distribution System ◽  
Distribution Systems ◽  
Free Chlorine ◽  
Copper Pipe

Pipe relining via in situ epoxy lining is used to remediate corroded plumbing or distribution systems. This investigation examined the effects on odour, TOC, THM formation and disinfectant demand in water exposed to epoxy-lined copper pipes used for home plumbing. The study was conducted in accordance with the Utility Quick Test, a migration/leaching method for utilities to conduct sensory analysis of materials in contact with drinking water. The test was performed using water with no disinfectant and levels of chlorine and monochloramines representative of those found in the distribution system. Panelists repeatedly and consistently described a “plastic/adhesive/putty” odour in the water from the pipes. The odour intensity remained relatively constant for each of two subsequent flushes. Water samples stored in the epoxy-lined pipes showed a significant increase in the leaching of organic compounds (as TOC), and this TOC was demonstrated to react with free chlorine to form trichloromethane. Water stored in the pipes also showed a marked increase in disinfectant demand relative to the water stored in glass control flasks. A study conducted at a full scale installation at an apartment demonstrated that after installation and regular use, the epoxy lining did not yield detectable differences in water quality.

Suspended particles in the drinking water of two distribution systems

2001 ◽  
Vol 1 (4) ◽  
pp. 237-245 ◽  
Author(s):  
V. Gauthier ◽  
B. Barbeau ◽  
R. Millette ◽  
J.-C. Block ◽  
M. Prévost
Keyword(s):  
Water Quality ◽  
Drinking Water ◽  
Organic Matter ◽  
Distribution System ◽  
Distribution Systems ◽  
Suspended Solids ◽  
Suspended Particles ◽  
Raw Water ◽  
Remote Locations ◽  
Dissolved Matter

The concentrations of suspended particles were measured in the drinking water of two distribution systems, and the nature of these particles documented. The concentrations of particulate matter were invariably found to be small (maximum 350 μg/L). They are globally in the very low range in comparison with dissolved matter concentrations, which are measured in several hundreds of mg/L. Except during special water quality events, such as turnover of the raw water resource, results show that organic matter represents the most important fraction of suspended solids (from 40 to 76%) in treated and distributed water. Examination of the nature of the particles made it possible to develop several hypotheses about the type of particles penetrating Montreal's distribution system during the turnover period (algae skeleton, clays). These particles were found to have been transported throughout the distribution systems quite easily, and this could result in the accumulation of deposits if their surface charge were ever even slightly destabilised, or if the particles were to penetrate the laminar flow areas that are fairly typical of remote locations in distribution systems.

scholarly journals Water quality event detection and customer complaint clustering analysis in distribution systems

2012 ◽  
Vol 12 (5) ◽  
pp. 580-587 ◽  
Author(s):  
Stephen Mounce ◽  
John Machell ◽  
Joby Boxall
Keyword(s):  
Water Quality ◽  
Drinking Water ◽  
Distribution System ◽  
Distribution Systems ◽  
Water Distribution ◽  
Water Source ◽  
Water Quality Monitoring ◽  
Water Utility ◽  
Drinking Water Distribution ◽  
Historic Data

Safe, clean drinking water is a foundation of society and water quality monitoring can contribute to ensuring this. A case study application of the CANARY software to historic data from a UK drinking water distribution system is described. Sensitivity studies explored appropriate choice of algorithmic parameter settings for a baseline site, performance was evaluated with artificial events and the system then transferred to all sites. Results are presented for analysis of nine water quality sensors measuring six parameters and deployed in three connected district meter areas (DMAs), fed from a single water source (service reservoir), for a 1 year period and evaluated using comprehensive water utility records with 86% of event clusters successfully correlated to causes (spatially limited to DMA level). False negatives, defined by temporal clusters of water quality complaints in the pilot area not corresponding to detections, were only approximately 25%. It was demonstrated that the software could be configured and applied retrospectively (with potential for future near real time application) to detect various water quality event types (with a wider remit than contamination alone) for further interpretation.

Drinking Water Biofilm Management and Monitoring

2020 ◽  
Author(s):  
Frances Pick ◽  
Katherine Fish ◽  
Stewart Husband ◽  
Joby Boxall
Keyword(s):  
Water Quality ◽  
Drinking Water ◽  
Asset Management ◽  
Distribution System ◽  
Biofilm Formation ◽  
Distribution Systems ◽  
Intact Cell ◽  
Line Pipe ◽  
Biofilm Growth ◽  
The Impact

<p>Biofilms within drinking water distribution systems can pose risks to consumers, especially when mobilised, as high concentrations of microorganisms and associated material can be released leading to degradation of water quality. Access and sampling of biofilms within drinking water pipelines can be difficult without disrupting supply in these extensive and buried systems. A novel biofilm monitoring device was developed to determine if biofilm formation rates can be used to assess microbiological water quality, track fouling rates and ultimately indicate distribution system performance. The device comprises a sample-line pipe with multiple, independent removable sections (allowing for biofilm sampling) that can be easily connected to sampling points in the distribution system. Biofilm is removed from the device and flow cytometry used to determine total and intact cell concentrations. The biomonitoring device was tested in a series of laboratory trials, to establish the impact of different flow rates and orientations on biofilm formation and to determine the optimum configuration that achieves accurate and repeatable results. Subsequently, these devices were installed in two operational systems, with different water qualities, and biofilms were sampled for two months to obtain biofilm growth rates. The results provide the first direct evidence of different biofilm formation rates in distribution systems with different water qualities. This evidence is now being used to investigate fouling rates via risk analysis and modelling. The use of the device has potential to improve understanding of biofilm behaviour and help inform biofilm and asset management to safeguard the quality of delivered drinking water.</p>

Residual-chlorine concentration impacts the ecology of biofilms in drinking water pipes and their water quality response

2020 ◽  
Author(s):  
Katherine Fish ◽  
Paul Gaskin ◽  
Joby Boxall
Keyword(s):  
Water Quality ◽  
Drinking Water ◽  
Distribution Systems ◽  
Water Disinfection ◽  
Test Facility ◽  
Residual Chlorine ◽  
Internal Diameter ◽  
Shear Stresses ◽  
Chlorine Residual ◽  
The Impact

<p>Drinking water distribution systems (DWDS) are an engineered system designed to protect water quality during delivery from treatment works to consumers’ taps. Biofilms form on the vast internal surfaces of DWDS, impacting water quality by their activity and/or mobilisation into the bulk-water. Disinfection-residuals are often maintained in drinking water to mitigate planktonic microbial contamination (and associated water quality/health risks). However, the impact of residual-disinfection upon biofilms, and the subsequent unintended risk they may present to water quality, is unclear.</p> <p>To address this, an internationally-unique, temperature-controlled, full-scale DWDS test facility, fed with water from the local DWDS, was used to grow biofilms (for 28 days). The facility enables three simultaneous conditions to be run in replicate pipe loops (each ~200m long, 79mm internal diameter, PE100 pipe). Conditions studied were Low-, Medium- and High-chlorine regimes. Various water quality parameters were monitored throughout, biofilms were sampled every two weeks (n=5). Physical, chemical and molecular analyses were applied to characterise the matrix (structure and composition) and microbial communities (via analysis of bacterial 16S rRNA and fungal ITS genes) of biofilms developed under the different chlorine regimes. After growth, a “mobilisation” test was conducted simulating hydraulic changes that occur in DWDS. Biofilms from each chlorine regime were exposed to increasing shear stresses to determine any water quality degradation as a consequence of biofilm mobilisation.</p> <p>High-chlorine residual concentration during development reduced biofilm bacterial concentrations but increased inorganics and selected for unique bacterial and fungal communities. Ultimately the biofilms developed under a High-chlorine residual resulted in the greatest decrease in water quality, in response to mobilisation, and the Low-chlorine regime resulted in biofilms which had the lowest impact on water quality. These unanticipated findings suggest chlorine-boosting should be considered carefully and may actually exacerbate water quality issues. The derived understanding could impact the long-term management of DWDS water quality and biofilm, whilst challenging the current mind-set of continuous residual-disinfection control strategies.</p>

scholarly journals Evaluation of potential human health risk and investigation of drinking water quality in Isparta city center (Turkey)

2015 ◽  
Vol 14 (3) ◽  
pp. 471-488 ◽  
Author(s):  
Simge Varol ◽  
Aysen Davraz
Keyword(s):  
Water Quality ◽  
Drinking Water ◽  
Health Risk ◽  
Distribution System ◽  
Distribution Systems ◽  
Tap Water ◽  
Human Health Risk ◽  
World Health ◽  
City Center ◽  
Rock Interaction

Isparta city center is selected as a work area in this study because the public believes that the tap water is dirty and harmful. In this study, the city's drinking water in the distribution system and other spring waters which are used as drinking water in this region were investigated from the point of water quality and health risk assessment. Water samples were collected from major drinking water springs, tap waters, treatment plants and dam pond in the Isparta province center. Ca-Mg-HCO3, Mg-Ca-HCO3, Ca-Na-HCO3, Ca-HCO3, Ca-HCO3-SO4 and Ca-Mg-HCO3-SO4 are dominant water types. When compared to drinking water guidelines established by World Health Organization and Turkey, much greater attention should be paid to As, Br, Fe, F, NH4, PO4 through varied chemicals above the critical values. The increases of As, Fe, F, NH4 and PO4 are related to water–rock interaction. In tap waters, the increases of As and Fe are due to corrosion of pipes in drinking water distribution systems. The major toxic and carcinogenic chemicals within drinking water are As and Br for both tap water and spring water. Also, F is the non-carcinogenic chemical for only spring waters in the study area.

scholarly journals Outage Estimation in Electric Power Distribution Systems Using a Neural Network Ensemble

Energies ◽  
2021 ◽  
Vol 14 (16) ◽  
pp. 4797
Author(s):  
Sanjoy Das ◽  
Padmavathy Kankanala ◽  
Anil Pahwa
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Power Distribution ◽  
Distribution System ◽  
Distribution Systems ◽  
Deep Neural Network ◽  
Neural Network Ensemble ◽  
Power Distribution Systems ◽  
Power Distribution System ◽  
Input Space

Outages in an overhead power distribution system are caused by multiple environmental factors, such as weather, trees, and animal activity. Since they form a major portion of the outages, the ability to accurately estimate these outages is a significant step towards enhancing the reliability of power distribution systems. Earlier research with statistical models, neural networks, and committee machines to estimate weather-related and animal-related outages has reported some success. In this paper, a deep neural network ensemble model for outage estimation is proposed. The entire input space is partitioned with a distinct neural network in the ensemble performing outage estimate in each partition. A novel algorithm is proposed to train the neural networks in the ensemble, while simultaneously partitioning the input space in a suitable manner. The proposed approach has been compared with the earlier approaches for outage estimation for four U.S. cities. The results suggest that the proposed method significantly improves the estimates of outages caused by wind and lightning in power distribution systems. A comparative analysis with a previously published model for animal-related outages further establishes the overall effectiveness of the deep neural network ensemble.

scholarly journals DRINKING WATER QUALITY IN DISTRIBUTION SYSTEMS OF SURFACE AND GROUND WATERWORKS IN FINLAND

2017 ◽  
Vol 3 (1) ◽  
Author(s):  
Jenni Meirami Ikonena ◽  
Anna-Maria Hokajärvi ◽  
Jatta Heikkinen ◽  
Tarja Pitkänen ◽  
Robert Ciszek ◽  
...  
Keyword(s):  
Water Quality ◽  
Drinking Water ◽  
Distribution System ◽  
Distribution Systems ◽  
Water Distribution ◽  
Water Source ◽  
Bulk Water ◽  
Available Phosphorus ◽  
Raw Water ◽  
Drinking Water Distribution Systems

Physico-chemical and microbiological water quality in the drinking water distribution systems (DWDSs) of five waterworks in Finland with different raw water sources and treatment processes was explored. Water quality was monitored during four seasons with on-line equipment and bulk water samples were analysed in laboratory. Seasonal changes in the water quality were more evident in DWDSs of surface waterworks compared to the ground waterworks and artificially recharging ground waterworks (AGR). Between seasons, temperature changed significantly in every sys-tem but pH and EC changed only in one AGR system. Seasonal change was seen also in the absorbance values of all sys-tems. The concentration of microbially available phosphorus (MAP, μg PO₄-P/l) was the highest in drinking water origi-nating from the waterworks supplying groundwater. Total assimilable organic carbon (AOC, μg AOC-C/l) concentrations were significantly different between the DWDSs other than between the two AGR systems. This study reports differences in the water quality between surface and ground waterworks using a wide set of parameters commonly used for monitor-ing. The results confirm that every distribution system is unique, and the water quality is affected by environmental fac-tors, raw water source, treatment methods and disinfection.

Artificial neural networks: applications in the drinking water sector

2018 ◽  
Vol 18 (6) ◽  
pp. 1869-1887 ◽  
Author(s):  
G. O'Reilly ◽  
C. C. Bezuidenhout ◽  
J. J. Bezuidenhout
Keyword(s):  
Neural Networks ◽  
Water Quality ◽  
Drinking Water ◽  
Artificial Neural Networks ◽  
Membrane Filtration ◽  
Distribution Systems ◽  
Water Quality Management ◽  
Future Research ◽  
Water Sector ◽  
Artificial Neural

Abstract Artificial neural networks (ANNs) could be used in effective drinking water quality management. This review provides an overview about the history of ANNs and their applications and shortcomings in the drinking water sector. From the papers reviewed, it was found that ANNs might be useful modelling tools due to their successful application in areas such as pipes/infrastructure, membrane filtration, coagulation dosage, disinfection residuals, water quality, etc. The most popular ANNs applied were feed-forward networks, especially Multi-layer Perceptrons (MLPs). It was also noted that over the past decade (2006–2016), ANNs have been increasingly applied in the drinking water sector. This, however, is not the case for South Africa where the application of ANNs in distribution systems is little to non-existent. Future research should be directed towards the application of ANNs in South African distribution systems and to develop these models into decision-making tools that water purification facilities could implement.

scholarly journals Pattern matching and associative artificial neural networks for water distribution system time series data analysis

2013 ◽  
Vol 16 (3) ◽  
pp. 617-632 ◽  
Author(s):  
S. R. Mounce ◽  
R. B. Mounce ◽  
T. Jackson ◽  
J. Austin ◽  
J. B. Boxall
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Water Quality ◽  
Time Series ◽  
Pattern Matching ◽  
Distribution Systems ◽  
Water Distribution ◽  
Quality Data ◽  
Series Data ◽  
Artificial Neural

Water distribution systems, and other infrastructures, are increasingly being pervaded by sensing technologies, collecting a growing volume of data aimed at supporting operational and investment decisions. These sensors monitor system characteristics, i.e. flows, pressures and water quality, such as in pipes. This paper presents the application of pattern matching techniques and binary associative neural networks for novelty detection in such data. A protocol for applying pattern matching to automatically recognise specific waveforms in time series based on their shapes is described together with a system called Advanced Uncertain Reasoning Architecture (AURA) Alert for autonomous determination of novelty. AURA is a class of binary neural network that has a number of advantages over standard artificial neural network techniques for condition monitoring including a sound theoretical basis to determine the bounds of the system operation. Results from application to several case studies are provided including both hydraulic and water quality data. In the case of pattern matching, the results demonstrated some transferability of burst patterns across District Metered Areas; however limitations in performance and difficulties with assembling pattern libraries were found. Results for the AURA system demonstrate the potential for robust event detection across multiple parameters providing valuable information for diagnosis; one example also demonstrates the potential for detection of precursor information, vital for proactive management.

Sign in / Sign up

Export Citation Format

Share Document