scholarly journals Modelo de predição de desempenho de estações de tratamento de água de pequeno porte usando redes neurais artificiais

Revista DAE ◽  
2019 ◽  
Vol 221 (68) ◽  
pp. 87-100
Author(s):  
Juscelino Alves Henriques ◽  
Marcelo Libânio ◽  
Veber Afonso Figueiredo Costa ◽  
Mariângela Dutra de Oliveira

As estações de tratamento de água (ETAs) têm um papel fundamental e estratégico no controle de doenças transmitidas pela água por meio da potabilização da água, para atender às necessidades da população que é abastecida por ela. Nesse contexto, a avaliação do desempenho dessas estações é primordial, particularmente para as entidades responsáveis pelo estágio de controle da qualidade da água, uma vez que a ETA deve apre- sentar e operar com condições mínimas necessárias para alcançar seu objetivo. Para o desenvolvimento dos modelos (Modelo 1 - com base na turbidez da água tratada e Modelo 2 - com base na cor aparente da água tratada) foram utilizados dados referentes à qualidade da água bruta e tratada, fatores operacionais e parâme- tros hidráulicos de 3 ETAs, com taxas de fluxo de 50 L.s-1 ou menos. Os modelos foram desenvolvidos usando a caixa de ferramentas do Matlab®, a partir da rede neural do tipo de camadas recorrentes, com função de ativação tansig e purelin. Como resultados, os modelos apresentaram coeficientes de determinação de 0,928 e 0,823 para turbidez e cor aparente da água tratada, respectivamente. Os resultados corroboram a aplicação da Inteligência Artificial em estações de tratamento de água, com o objetivo de otimizar processos e garantir uma maior operabilidade da ETAs, gerando um produto cada vez mais confiável. Palavras-chave: Desempenho da planta de tratamento de água. Processos de otimização. Rede neural artificial. Abstract The water treatment plants (WTP) have a fundamental and strategic role in the control of waterborne diseases through the potabilization of water, to meet the needs of the population that is supplied by it. In this context, evaluating the performance of these stations is paramount, particularly for the entities responsible for the water quality control stage, since WTP must present and operate with minimum conditions necessary to achieve its ob- jective. For the development of the models (Model 1 - based on turbidity of treated water and Model 2 - based on the apparent color of the treated water) data were used referring to raw and treated water quality, operational factors and hydraulic parameters of 3 WTPs, with flow rates of 50 L.s-1 or less. The models were developed usingthe Matlab® toolbox, from the neural network of the recurrent layers type, with activation function tansig and purelin. As results, the models presented regression coefficients of 0.928 and 0.823 for turbidity and apparent color of treated water, respectively. The results corroborate for the application of Artificial Intelligence in water treatment plants, with a view to optimizing processes and guaranteeing greater WTPs operability, generating an increasingly reliable product. Keywords: Water treatment plant performance. Optimization processes. Artificial Neural Network.

2019 ◽  
Vol 19 (7) ◽  
pp. 2098-2106
Author(s):  
Chelsea W. Neil ◽  
Yingying Zhao ◽  
Amy Zhao ◽  
Jill Neal ◽  
Maria Meyer ◽  
...  

Abstract Source water quality can significantly impact the efficacy of water treatment unit processes and the formation of chlorinated and brominated trihalomethanes (THMs). Current water treatment plant performance models may not accurately capture how source water quality variations, such as organic matter variability, can impact treatment unit processes. To investigate these impacts, a field study was conducted wherein water samples were collected along the treatment train for 72 hours during a storm event. Systematic sampling and detailed analyses of water quality parameters, including non-purgeable organic carbon (NPOC), UV absorbance, and THM concentrations, as well as chlorine spiking experiments, reveal how the THM formation potential changes in response to treatment unit processes. Results show that the NPOC remaining after treatment has an increased reactivity towards forming THMs, and that brominated THMs form more readily than chlorinated counterparts in a competitive reaction. Thus both the reactivity and quantity of THM precursors must be considered to maintain compliance with drinking water standards, a finding that should be incorporated into the development of model-assisted treatment operation and optimization. Advanced granular activated carbon (GAC) treatment beyond conventional coagulation–flocculation–sedimentation processes may also be necessary to remove the surge loading of THM-formation precursors during a storm event.


2008 ◽  
Vol 8 (3) ◽  
pp. 297-304 ◽  
Author(s):  
A. W. C. van der Helm ◽  
L. C. Rietveld ◽  
Th. G. J. Bosklopper ◽  
J. W. N. M. Kappelhof ◽  
J. C. van Dijk

Optimization for operation of drinking water treatment plants should focus on water quality and not on environmental impact or costs. Using improvement of water quality as objective for optimization can lead to new views on operation, design and concept of drinking water treatment plants. This is illustrated for ozonation in combination with biological activated carbon (BAC) filtration at drinking water treatment plant Weesperkarspel of Waternet, the water cycle company for Amsterdam and surrounding areas. The water quality parameters that are taken into account are assimilable organic carbon (AOC), dissolved organic carbon (DOC) and pathogens. The operational parameters that are taken into account are the ozone dosage and the regeneration frequency of the BAC filters. It is concluded that ozone dosage and regeneration frequency should be reduced in combination with application of newly developed insights in design of ozone installations. It is also concluded that a new concept for Weesperkarspel with an additional ion exchange (IEX) step for natural organic matter (NOM) removal will contribute to the improvement of the disinfection capacity of ozonation and the biological stability of the produced drinking water.


2016 ◽  
Vol 12 (12) ◽  
pp. 4749-4763
Author(s):  
Sridhar Natarajan ◽  
S. Senthil Kumaar

This paper aims at presenting a new optimization proposal to enhance the flocculation process in Water Treatment (WT) plant using a better flash mixing, located at KELAVERAPALLY, in Krishnagiri district, Tamil Nadu, India. Further, Sludge removal is done efficiently which decreases the water wastage as well as improvement in output water quality. Though WT plants are already equipped with systematic and sequential physicochemical processes, still they need to be optimized to obtain a better treated drinking water to maintain the quality standards as prescribed by World Health Organization. Chaotic behavior in chemical systems has been used to optimize the performance of WT plant. Measurement systems implemented in WT plant yield several chaotic based measurement parameters which are used to control the system operations to maintain the target water quality.  This intelligible data extraction through the proposed measurement  systems in a short span of time improves the plant performance without adding any costly systems except few changes in the existing plant setup.  Chaotic behavior is ensured through Lyapunov Exponents and Kolmogorov-Sinai Entropies. Both, water quality improvement and water wastage reduction is achieved simultaneously in the proposed work when a dosage prediction is done using Feed Forward Neural Networks. The treatment plant investigated has a maximum capacity of 14 MLD (Million litres per day) using two parallel streams with 7 MLD each


2019 ◽  
Vol 6 (2) ◽  
pp. 121-138
Author(s):  
Imad Ali Omar

Abstract: Water treatment plant (WTP) is essential for providing clean and safe water to the habitants. There is a necessity to evaluate the performance of (WTP) for proper treatment of raw water. The purpose of the present study is to evaluate the quality of treated water by investigating the performance of Ifraz-2 (WTP) units located in Erbil City, Iraq. For assessment of the (WTP) units, samples were taken for a duration of five months from different locations: raw water (the source), post-clarification processes, post-filtration processes, and from the storage tank. Removal efficiencies for the units, and for the whole (WTP) were calculated and presented. Obtained removal efficiencies for the sedimentation unit; filtration unit; and the entire Ifraz-2 (WTP) were 91.51 %, 64.71 %, and 97.29 %, respectively. After the process of disinfection and storage, the valued of the turbidity of the treated water were ranged from 1.2 to 9.7 (Nephelometric Turbidity Units) NTU. Besides, water quality index (WQI) for the (WTP) was studied and calculated for 14 physicochemical water quality parameters. WQI for Ifraz-2 (WTP) was 51.87 and it is regarded as a good level. Also, operational problems have been detected and reported during the research period, especially during sedimentation, filtration, and disinfection. Suitable solutions have been reported to the operational team.


Author(s):  
Mohamed Deyab ◽  
Magda El-Adl ◽  
Fatma Ward ◽  
Eman Omar

Abstract This work aims to study the seasonal fluctuation in physicochemical characteristics, trophic status, and some pollutants influencing phytoplankton diversity, and water quality at a compact Kafr El-Shinawy drinking-water treatment plant, Damietta – Egypt seasonally during 2018. Phytoplankton distribution was affected by the trophic status of water, level of pollutants, and physicochemical treatment processes of water. The predominance of phytoplankton species, especially Aphanizomenon flos aquae (Cyanophyta), Gomphosphaeria lacustris (Cyanophyta), Microcystis aeruginosa (Cyanophyta), Nostoc punctiforme (Cyanophyta), Oscillatoria limnetica (Cyanophyta), Pediastrum simplex (Chlorophyta), and Melosira granulata (Bacillariophyta) in treated water was much less than that in raw water. Trihalomethanes (THMs) levels in treated waters were higher than in raw water, while lower concentrations of heavy metals were recorded in treated water. Intracellular levels of microcystins were lower, whereas the extracellular levels were higher in treated water than raw water, and the former recorded the highest level in raw water during summer. Hence, the levels of dissolved microcystins and THMs in treated water were higher especially during summer, the season of luxurious growth of Microcystis species. Trophic state index (TSI) was relatively high in raw water compared with treated water due to high concentrations of nutrients (total-P, total-N, nitrite, nitrate, and ammonia) in raw water.


Sign in / Sign up

Export Citation Format

Share Document