Comparison between artificial neural networks and Hermia’s models to assess ultrafiltration performance

Corbatón-Báguena, María-José; Vincent‐Vela, María‐Cinta; Gozálvez-Zafrilla, José M.; Álvarez-Blanco, Silvia; Lora-García, Jaime; Catalán-Martínez, David

doi:10.1016/j.seppur.2016.07.007

Cited by 56 publications

(22 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Total data for CFMF experiments are divided into two groups: the first one for permeate flux without static mixer (NSM) and the second group data for flux with static mixer (SM). Prior to the artificial network training data sets were normalized to bring all data within a specific range [18]:…”

Section: Artificial Neural Network Architecturementioning

confidence: 99%

Dynamic Modeling of Streptomyces hygroscopicus Fermentation Broth Microfiltration by Artificial Neural Networks

Jokić¹,

Nikolić²,

Lukić³

et al. 2019

Period. Polytech. Chem. Eng.

View full text Add to dashboard Cite

Artificial neural networks (ANNs) have been used to dynamically model cross-flow microfiltration of Streptomyces hygroscopicus fermentation broths. The aim is to predict permeate flux as a function of temperature, feed flow, transmembrane pressure and processing time. Dynamic modeling of microfiltration performance of complex systems (such as broths) is very important for design of new processes and better understanding of the present. The results of ANN model analysis suggest that the coefficients of the determination have high values. The application of the Bayesian regularization gave better results to the performance of the neural network compared to the Levenberg-Marquet algorithm. The optimal number of neurons in the hidden layer is eight. Analysis of the absolute relative error showed excellent permeate flux estimates for 100 % of the data points, with an error less than 5 % for the data obtained during microfiltration in the presence of a turbulence promoter. Whilst in the case of microfiltration without turbulence promoter 90 % of predictions have an error less than 10 %. The results of applying the concept of neural networks in the dynamic modeling of microfiltration of Streptomyces hygroscopicus fermentative broths with and without a turbulence promoter clearly show the validity of proposed method for simulation and prediction of microfiltration experimental results.

show abstract

Section: Artificial Neural Network Architecturementioning

confidence: 99%

Dynamic Modeling of Streptomyces hygroscopicus Fermentation Broth Microfiltration by Artificial Neural Networks

Jokić¹,

Nikolić²,

Lukić³

et al. 2019

Period. Polytech. Chem. Eng.

View full text Add to dashboard Cite

show abstract

“…(2012) The permeability and mechanical properties of cellulose acetate membranes blended with polyethylene glycol 600 for treatment of municipal sewage Mechanical properties of semi-permeable membranes +++ I China Bi et al. (2020) Determination of the buried depth and pressure head under moistube irrigation based on principal component analysis Moistube +++ I China Corbatón-Báguena et al. (2016) Comparison between artificial neural networks and Hermia's models to assess ultrafiltration performance Semi-permeable membrane fouling +++ I Spain Castejón et al.…”

Section: Methodsmentioning

confidence: 99%

Moistube irrigation technology development, adoption and future prospects: A systematic scoping review

Dirwai

Mabhaudhi

Kanda

et al. 2021

Heliyon

View full text Add to dashboard Cite

Agriculture is the biggest consumer of fresh water in the world accounting for almost 70% of the water use. The burgeoning world population and increased demands to feed the world requires novel technologies that reconcile water consumption and food security. Moistube is a polymeric semi-permeable membrane irrigation technology that is known to improve water use efficiency and boost yields. The technology is relatively new, hence a lack of comprehensive literature regarding Moistube irrigation (MTI) technology warrants empirical investigation of the existing literature. The study performed a systematic review guided by the Preferred reporting items for systematic review and meta-analysis protocols (PRISMA-P) and the scoping studies methodological framework to compile an evidence-based literature review on Moistube irrigation. The study performed search queries in the following over-arching and comprehensive databases for grey literature: Google Scholar, Science Direct, Research Gate, CAB direct, All Journals, CNKI, FAO, SCOPUS, Web of Science, and UKZN-EFWE. DistillerSR software was used for screening, data extraction and data charting. Article screening retained one hundred and 55 (n = 155) articles. Forty-nine articles (n = 49) and information sources were found to be related directly and indirectly to Moistube. Moistube articles (n = 29, 59%) were from China were the technology originated. A bulk of literature reported Moistube irrigation use in the arid regions of China. The review revealed areas for research enquiry into the subject matter. Future research areas were fertigation performance under MTI, effects of waste-water on MTI nanopore plugging, yield response of industrial crops of economic importance under MTI and soil wetting geometries under MTI. This signified the need to perform further research enquiries into the subject matter to improve literature availability. Moistube irrigation technology has a low adoption rate in Africa with reported use in South Africa and Morocco. The technology has massive adoption potential in arid and semi-arid regions of sub-Sahara Africa.

show abstract

“…No bloqueio padrão, ocorre a adsorção do soluto nos poros, ou seja, as gotas da emulsão têm um tamanho muito menor que o poro da membrana, diminuindo seu diâmetro. A formação da torta ocorre pela deposição de gotas da emulsão na superfície da membrana, formando uma camada que dificulta ainda mais a filtração [16][17][18]. Para o caso da filtração frontal, observou-se que o modelo que melhor se ajustou aos dados experimentais foi o de bloqueio intermediário dos poros, segundo o qual há obstrução destes por espécies ou gotas de tamanhos similares a eles.…”

Section: Modelagem Dos Mecanismos De Bloqueio De Porosunclassified

Mecanismos de queda do fluxo em membranas de microfiltração de poliéterimida aplicadas à clarificação de água produzida sintética

Brandão¹,

Figueiredo²

2019

Matéria (Rio J.)

View full text Add to dashboard Cite

RESUMO Membranas de microfiltração de poliéterimida foram preparadas pelo método de inversão de fases para controlar a espessura, porosidade e tamanho de poros dos filmes. 1-metil-2-pirrolidona foi utilizada como solvente e água como não solvente. As propriedades das membranas foram avaliadas por meio de microscopia eletrônica de varredura, microfiltração de água produzida sintética em modo frontal e tangencial, bem como mecanismos de bloqueio dos poros dos sistemas conforme descrito pelo modelo de Hermia. Os resultados mostraram que a morfologia das membranas foi significativamente alterada pela cinética de precipitação. O diâmetro médio de poros variou de 1,2 a 10,4 µm, ambas com estrutura tipo dedos. Testes de permeação mostraram menor declínio do fluxo total para sistemas com escoamento tangencial (89,5%) quando comparado com o escoamento frontal (97,3%). Entretanto, o declínio reversível do fluxo foi maior do que o irreversível para ambos os sistemas. O coeficiente de rejeição foi maior do que 95,5%, medido pela turbidez. Com relação aos mecanismos para o declínio do fluxo, observou-se que o bloqueio de poros intermediário foi capaz de explicar os resultados para a filtração frontal. O modelo de Hermia não se ajustou bem ao escoamento tangencial, provavelmente devido ao fato de o fluxo ter se estabilizado com o tempo. Os resultados mostraram o potencial do sistema para ser usado em microfiltração em longos prazos, desde que a lavagem periódica das membranas seja realizada.

show abstract

Comparison between artificial neural networks and Hermia’s models to assess ultrafiltration performance

Cited by 56 publications

References 37 publications

Dynamic Modeling of Streptomyces hygroscopicus Fermentation Broth Microfiltration by Artificial Neural Networks

Dynamic Modeling of Streptomyces hygroscopicus Fermentation Broth Microfiltration by Artificial Neural Networks

Moistube irrigation technology development, adoption and future prospects: A systematic scoping review

Mecanismos de queda do fluxo em membranas de microfiltração de poliéterimida aplicadas à clarificação de água produzida sintética

Contact Info

Product

Resources

About