Prediction of multi-components (chlorine, biomass and substrate concentrations) in water distribution systems using artificial neural network (ANN) models

2009 ◽  
Vol 9 (3) ◽  
pp. 289-297
Author(s):  
Celia D. D'Souza ◽  
M. S. Mohan Kumar
Keyword(s):  
Distribution System ◽  
Distribution Systems ◽  
Water Distribution ◽  
Transport Model ◽  
Absolute Error ◽  
Temporal Variations ◽  
Residual Chlorine ◽  
Ann Model ◽  
Ann Models ◽  
Artificial Neural

Artificial Neural Networks (ANN) models are used to predict residual chlorine, substrate and biomass concentrations in a Water Distribution System (WDS). ANN models with different architectures are developed: a one output ANN model (predicting chlorine, substrate and biomass individually), a two output ANN model (predicting chlorine + substrate, chlorine + biomass or substrate + biomass) and a three output ANN model (chlorine + substrate + biomass). This study is carried out for the Bangalore City and North Marin WDSs. Data for these WDSs is obtained from the multi-component reaction transport model. The models are compared using the correlation coefficient (R) and the Mean Absolute Error (MAE). The models developed are able to predict, reasonably well, the temporal variations in the chlorine, substrate and biomass concentrations. Error analysis is carried out to determine the robustness of the models.

scholarly journals Optimization and Assessment of Residual Chlorine using Response Surface Methodology (RSM) and Artificial Neural Network (ANN) Modeling

2019 ◽  
Vol 8 (3) ◽  
pp. 258-263
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Distribution System ◽  
Water Distribution ◽  
Residual Chlorine ◽  
Urban Water ◽  
Ann Model ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Rsm Model

Water polluted with microorganisms and pathogens is one of the most significant hazards to public health. Potential microorganisms unsafe to human health can be destroyed through effective disinfection. To stop the re-growth of microorganisms, it is also advisable to take care of the residual disinfectant in the water distribution networks. The most frequently used cleanser material is chlorine. When the chlorine dosage is too low, there will be a deficiency of enough residues at the end of the water network system, leading to re-growth of microorganisms. Addition of an excessive amount of chlorine will lead to corrosion of the pipeline network and also the development of disinfection by-products (DBPs) including carcinogens. Thus, to determine the best rate of chlorine dosage, it is essential to model the system to forecast chlorine decay within the network. In this research study, two major modeling and optimization strategies were employed to assess the optimum dosage of chlorine for municipal water disinfection and also to predict residual chlorine at any predetermined node within the water distribution network. Artificial neural network (ANN) modeling techniques were used to forecast chlorine concentrations in different nodes in the urban water distribution system in Muscat, the capital of the Sultanate of Oman. One-year dataset from one of the distribution system was used for conducting network modeling in this study. The input factors to RSM model considered were pH, chlorine dosage and time. Response variables for RSM model were fixed as total organic carbon (TOC), Biological oxygen demand (BOD) and residual chlorine An Artificial neural network (ANN) model for residual chlorine was created with pH, inlet-concentration of chlorine and initial temperature as input parameters and residual chlorine in the piping network as an output parameter. The ANN model created using these data can be employed to forecast the residual chlorine value in the urban water network at any given specific location. The results from this study utilizing the uniqueness of an ANN model to predict residual chlorine and water quality parameters have the potential to detect complex, higher-order behavior between input and output parameters exist in urban water distribution system.

scholarly journals Artificial neural network system analysis and Kriging methodology for estimation of non-revenue water ratio

2020 ◽  
Vol 20 (5) ◽  
pp. 1871-1883 ◽  
Author(s):  
Eyüp Şişman ◽  
Burak Kizilöz
Keyword(s):  
Distribution Systems ◽  
Water Distribution ◽  
System Analysis ◽  
Kriging Model ◽  
Ann Model ◽  
Box Models ◽  
Neural Network System ◽  
Ann Models ◽  
Artificial Neural ◽  
Non Revenue Water

Abstract The non-revenue water (NRW) ratio parameter is significantly important for performance evaluation of water distribution systems. In order to evaluate the NRW ratio, the variables influencing this parameter should be determined. Therefore, the first aim of the paper is to define the variables which are influential on the estimation of the NRW ratio and then analyze these variables by using artificial neural networks (ANNs) methodology by means of 50 models with one, two, three, and four-variable input. Secondly, in this study, the NRW ratios have been predicted for the first time by using the Kriging methodology through only two variables. By using the data measured in 12 district meter areas (DMA) in Kocaeli, 60 models in total have been established for NRW ratio prediction through the ANN and Kriging methodologies. The ANN models are closed-box models and therefore the interpretation of the ANN model results requires higher expert opinion. As a consequence, the results show that Kriging model graphs produce much more useful information than ANN models in terms of application and interpretation.

Application of two approaches to model chlorine residuals in Severn Trent Water Ltd (STW) distribution systems

1997 ◽  
Vol 36 (5) ◽  
pp. 317-324 ◽  
Author(s):  
M.J. Rodriguez ◽  
J.R. West ◽  
J. Powell ◽  
J.B. Sérodes
Keyword(s):  
Distribution System ◽  
Distribution Systems ◽  
Treatment Plant ◽  
Residual Chlorine ◽  
Ann Model ◽  
Order Model ◽  
First Order ◽  
Chlorine Decay ◽  
Artificial Neural Network Ann ◽  
Key Parameter

Increasingly, those who work in the field of drinking water have demonstrated an interest in developing models for evolution of water quality from the treatment plant to the consumer's tap. To date, most of the modelling efforts have been focused on residual chlorine as a key parameter of quality within distribution systems. This paper presents the application of a conventional approach, the first order model, and the application of an emergent modelling approach, an artificial neural network (ANN) model, to simulate residual chlorine in a Severn Trent Water Ltd (U.K.) distribution system. The application of the first order model depends on the adequate estimation of the chlorine decay coefficient and the travel time within the system. The success of an ANN model depends on the use of representative data about factors which affect chlorine evolution in the system. Results demonstrate that ANN has a promising capacity for learning the dynamics of chlorine decay. The development of an ANN appears to be justifiable for disinfection control purposes, in cases when parameter estimation within the first order model is imprecise or difficult to obtain.

scholarly journals Modelling both the continual erosion and regeneration of discolouration material in drinking water distribution systems

2013 ◽  
Vol 14 (1) ◽  
pp. 81-90 ◽  
Author(s):  
W. R. Furnass ◽  
R. P. Collins ◽  
P. S. Husband ◽  
R. L. Sharpe ◽  
S. R. Mounce ◽  
...  
Keyword(s):  
Distribution System ◽  
Distribution Systems ◽  
Water Distribution ◽  
Transport Model ◽  
Water Distribution Systems ◽  
Sensitivity Analyses ◽  
Drinking Water Distribution Systems ◽  
Proactive Management ◽  
Drinking Water Distribution ◽  
Mass Transport Model

The erosion of the cohesive layers of particulate matter that causes discolouration in water distribution system mains has previously been modelled using the Prediction of Discolouration in Distribution Systems (PODDS) model. When first proposed, PODDS featured an unvalidated means by which material regeneration on pipe walls could be simulated. Field and laboratory studies of material regeneration have yielded data that suggest that the PODDS formulations incorrectly model these processes. A new model is proposed to overcome this shortcoming. It tracks the relative amount of discolouration material that is bound to the pipe wall over time at each of a number of shear strengths. The model formulations and a mass transport model have been encoded as software, which has been used to verify the model's constructs and undertake sensitivity analyses. The new formulations for regeneration are conceptually consistent with field and laboratory observed data and have potential value in the proactive management of water distribution systems, such as evaluating change in discolouration risk and planning timely interventions.

Application of Artificial Neural Network for Reducing of Chlorine Residual Concentration in Water Distribution Network

2008 ◽  
Vol 3 (2) ◽  
Author(s):  
Jayong Koo ◽  
Toyono Inakazu ◽  
Akira Koizumi ◽  
Yasuhiro Arai ◽  
Kyoungpil Kim ◽  
...  
Keyword(s):  
Distribution System ◽  
Water Distribution ◽  
Water Distribution System ◽  
Distribution Network ◽  
Water Distribution Network ◽  
Residual Chlorine ◽  
Trial And Error ◽  
Ann Model ◽  
Residual Concentration ◽  
Dead End

It is difficult to estimate residual chlorine at the dead-end area of the water distribution network because chlorine consumption is influenced by various factors. Therefore, there are many water utilities that control the amounts of chlorine in reservoirs using empirical trial-and-error methods to maintain safe levels of residual chlorine in the distribution system. In this study, an ANN model of residual chlorine concentration is proposed which could be used to reduce in chlorine use in water distribution system. The ANN model with best performance was selected by training and verification. The five scenarios for the reduction in chlorine use were analyzed by setting the input chlorine as low as 0.05~0.25 mg/L compared with the input chlorine observed in the time series. Case 4 is the best to be satisfied with the input condition (0.4 mg/L or more) and output condition (0.34 mg/L or more) at the same time. It is possible to reduce chlorine in use up to 0.2 mg/L in the maximum amount.

scholarly journals Comparative analysis of different probability distributions of random parameters in the assessment of water distribution system reliability

2013 ◽  
Vol 16 (2) ◽  
pp. 272-287 ◽  
Author(s):  
Giovanna Darvini
Keyword(s):  
Distribution System ◽  
Distribution Systems ◽  
Water Distribution ◽  
Network Reliability ◽  
Probability Distributions ◽  
Probabilistic Approach ◽  
Temporal Variations ◽  
Random Parameters ◽  
Statistical Parameters ◽  
The Impact

During recent years, several methods based on the probabilistic approach have been proposed for the analysis of the performance of water distribution systems (WDSs). Uncertain elements are described by probabilistic laws chosen and parameterised on the basis of the network characteristics. However, the choice of the most suitable probabilistic distribution and of the statistical parameters can be difficult because of the lack of information about the WDSs. Among the stochastic parameters that affect the network performance, a fundamental role is played by the times to failure and repair of the system components. The impact of the chosen probability distributions of these fundamental variables on the evaluation of water distribution network reliability is analysed. The study is performed by using a technique capable of considering the mechanical failure of the network components, the spatial and temporal variations of the water demand and the uncertain distribution of the pipe roughness. This analysis allows quantification of the effect of any inaccuracy that may occur in the probabilistic characterisation of the random parameters.

A neural network approach to burst detection

2002 ◽  
Vol 45 (4-5) ◽  
pp. 237-246 ◽  
Author(s):  
S.R. Mounce ◽  
A.J. Day ◽  
A.S. Wood ◽  
A. Khan ◽  
P.D. Widdop ◽  
...  
Keyword(s):  
Neural Network ◽  
Distribution System ◽  
Distribution Systems ◽  
Water Distribution ◽  
Time Series Data ◽  
Quality Data ◽  
Series Data ◽  
Neural Network Approach ◽  
Water Quality Data ◽  
Artificial Neural

This paper describes how hydraulic and water quality data from a distribution network may be used to provide a more efficient leakage management capability for the water industry. The research presented concerns the application of artificial neural networks to the issue of detection and location of leakage in treated water distribution systems. An architecture for an Artificial Neural Network (ANN) based system is outlined. The neural network uses time series data produced by sensors to directly construct an empirical model for predication and classification of leaks. Results are presented using data from an experimental site in Yorkshire Water's Keighley distribution system.

Investigation into biofilms in a local drinking water distribution system

Biofilms ◽  
2005 ◽  
Vol 2 (1) ◽  
pp. 19-25 ◽  
Author(s):  
J. Y. Hu ◽  
B. Yu ◽  
Y. Y. Feng ◽  
X. L. Tan ◽  
S. L. Ong ◽  
...  
Keyword(s):  
Distribution System ◽  
Distribution Systems ◽  
Water Distribution ◽  
Water Distribution System ◽  
Water Distribution Systems ◽  
Plate Count ◽  
Residual Chlorine ◽  
Biofilm Growth ◽  
Water Plant ◽  
Biofilm Development

Biofilm growth within a water distribution system could lead to operational problems such as pipe corrosion, water quality deterioration and other undesirable impacts in water distribution systems. With the high ambient temperatures experienced in Singapore, the operating environment in water distribution systems is expected to be more conducive to biofilm development. We have recently conducted a survey on biofilms potentially present in a local water distribution system.The survey results indicated that residual chlorine (±standard deviation) decreased from 1.49±0.61 mg/l (water plant outlets) to 0.82±0.21 mg/l (block pipes) or 0.18±0.06 mg/l (unit pipes), respectively. Consumed chlorine, instead of residual chlorine, was found to be correlated with biofilm bacterial population. Assimilable organic carbon (AOC) level was 160±66 μg acetate C/l, and AOC:PO4-P:NO3-N was about 8:13:1. Carbon source seemed to be the limiting nutrient for bacterial growth. The concentration of iron increased from <0.04 mg/l (water plant outlets) to 0.22±0.10 mg/l (all sites). All samples showed negative results in a coliform test. The average heterotrophic plate count (HPC) for the suspended bacteria was 20 colony-forming units (c.f.u.)/ml (2 days, 35 °C) or 290 c.f.u./ml (8 days, 35 °C). The average HPC for the biofilm bacteria was 6500 c.f.u./cm2 (2 days, 35 °C) or 29000 c.f.u./cm2 (8 days, 35 °C). High HPC values in samples B2a, B2b and B3a (representing biofilm samples at site 2 from block/unit pipes and biofilm samples at site 3 from block pipes, respectively) illustrated that the relevant sample sites had a higher probaboility of biofilm growth.

Residual chlorine management in water distribution systems using network modelling techniques: case study in Seoul City

2004 ◽  
Vol 4 (5-6) ◽  
pp. 421-429
Author(s):  
J.C. Ahn ◽  
Y.W. Kim ◽  
K.S. Lee ◽  
J.Y. Koo
Keyword(s):  
Water Treatment ◽  
Distribution System ◽  
Distribution Systems ◽  
Water Distribution ◽  
Treatment Plant ◽  
Water Treatment Plant ◽  
Residual Chlorine ◽  
Network Modelling ◽  
Using Data ◽  
One Year

Twelve sampling locations in a network from a water treatment plant to consumers' taps were selected for measuring residual chlorine loss, THMs, TOC, etc. and 24 hour sampling in the locations was conducted on a bimonthly basis for one year. Chlorine bulk decay and THM formation tests were carried out by bottle tests under controlled temperatures for three locations: a water treatment plant, a large service reservoir, and a pumping station. Water quality modelling of chlorine loss in the distribution system was performed using data collected in the field study. This study contributed to the improvement of chlorine management in the distribution system by providing information for operators to maintain a minimum level of chlorine residual in a service reservoir.

scholarly journals Application of genetic programming to modeling pipe failures in water distribution systems

2010 ◽  
Vol 13 (3) ◽  
pp. 419-428 ◽  
Author(s):  
Qiang Xu ◽  
Qiuwen Chen ◽  
Weifeng Li
Keyword(s):  
Genetic Programming ◽  
Distribution System ◽  
Distribution Systems ◽  
Water Distribution ◽  
Pipe Failure ◽  
Beijing City ◽  
Failure Data ◽  
Processing Strategies ◽  
Gis Data ◽  
Failure Models

The water loss from a water distribution system is a serious problem for many cities, which incurs enormous economic and social loss. However, the economic and human resource costs to exactly locate the leakage are extraordinarily high. Thus, reliable and robust pipe failure models are demanded to assess a pipe's propensity to fail. Beijing City was selected as the case study area and the pipe failure data for 19 years (1987–2005) were analyzed. Three different kinds of methods were applied to build pipe failure models. First, a statistical model was built, which discovered that the ages of leakage pipes followed the Weibull distribution. Then, two other models were developed using genetic programming (GP) with different data pre-processing strategies. The three models were compared thereafter and the best model was applied to assess the criticality of all the pipe segments of the entire water supply network in Beijing City based on GIS data.

Sign in / Sign up

Export Citation Format

Share Document