Improvement of Artificial Neural Network Model for the Prediction of Wastewater Treatment Plant Performance

Jami, Mohammed Saedi; Kabashi, Nassereldeen Ahmed; Husain, Iman A. F.; Abdullah, Norhafiza

doi:10.2316/p.2011.736-050

Cited by 11 publications

(13 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Removal efficiencies of the plant for BOD, COD and total suspended solids (TSS) were 85%, 78% and 75%, respectively [35]. Jami et al (2012) used ANN for Sewage Treatment Plant in Malaysia. Single input-single output results were compared with those of single input-multiple output for BOD, SS, and COD [36].…”

Section: Model Theorymentioning

confidence: 99%

See 1 more Smart Citation

Modeling of copper removal from aqueous solutions by using carbon-based adsorbents derived from hazelnut and walnut shells by artificial neural network

Kaya¹

2022

Sigma J Eng Nat Sci - Sigma Müh Fen Bil Derg

View full text Add to dashboard Cite

The aim o f this study is to model the removal of copper from an aqueous solution using Artificial Neural Network ( ANN). Two different carbon-based materials (biochar) obtained by pyrolysis of hazelnut and walnut shells were used as adsorbents in a batch adsorption system. The surface area of biochars with a porous structure obtained from hazelnut and walnut shells were 124.347 m 2 /g and 256.931 m 2 /g, respectively. In adsorption experiments, initial copper concentration, adsorbent amount, temperature, pH, contact time and mixing speed were the adsorption parameters considered for the system and defined as inputs in the modeling studies. Experimental results for removing copper ions were found by changing pH 2.5-5, initial heavy metal concentration 15-45 ppm, adsorbent amount 1-3 g/L, mixing speed 200-600 rpm and temperature between 25-45°C. The %copper removal, which is tried to be maximized during the modeling phase, was selected as the model estimation parameter and defined as output to the system. ANN training was done with the Levenberg-Marquardt (LM) feed-forward algorithm and the data was categorised into 50% training, 25% validation and 25% testing. The maximum epoch value was determined as 8 iterations. Correlation coefficient (R 2 ) values of the system were determined as 99% for education, validation and testing for the two different carbon-based adsorbents.

show abstract

Section: Model Theorymentioning

confidence: 99%

“…Jami et al (2012) used ANN for Sewage Treatment Plant in Malaysia. Single input-single output results were compared with those of single input-multiple output for BOD, SS, and COD [36]. Bilgin Şimşek and Alkay (2020) used ANN for the prediction of effluent stream parameters of two different WWTPs in Kocaeli.…”

Section: Model Theorymentioning

confidence: 99%

Modeling of copper removal from aqueous solutions by using carbon-based adsorbents derived from hazelnut and walnut shells by artificial neural network

Kaya¹

2022

Sigma J Eng Nat Sci - Sigma Müh Fen Bil Derg

View full text Add to dashboard Cite

show abstract

“…In the literature, the designation "polyphenol oxidases" is sometimes used for both tyrosinase and laccase enzymes. These enzymes react with oxygen atoms, and catalyze the oxidative transformation of several phenols and non-phenolic compounds to their corresponding o-quinones (which are insoluble and less toxic) without requiring any additives [27,83].…”

Section: Oxidoreductase Enzymes and Their Mechanisms Of Actionmentioning

confidence: 99%

Applications of Biocatalysts for Sustainable Oxidation of Phenolic Pollutants: A Review

et al. 2021

View full text Add to dashboard Cite

Phenol and its derivatives are hazardous, teratogenic and mutagenic, and have gained significant attention in recent years due to their high toxicity even at low concentrations. Phenolic compounds appear in petroleum refinery wastewater from several sources, such as the neutralized spent caustic waste streams, the tank water drain, the desalter effluent and the production unit. Therefore, effective treatments of such wastewaters are crucial. Conventional techniques used to treat these wastewaters pose several drawbacks, such as incomplete or low efficient removal of phenols. Recently, biocatalysts have attracted much attention for the sustainable and effective removal of toxic chemicals like phenols from wastewaters. The advantages of biocatalytic processes over the conventional treatment methods are their ability to operate over a wide range of operating conditions, low consumption of oxidants, simpler process control, and no delays or shock loading effects associated with the start-up/shutdown of the plant. Among different biocatalysts, oxidoreductases (i.e., tyrosinase, laccase and horseradish peroxidase) are known as green catalysts with massive potentialities to sustainably tackle phenolic contaminants of high concerns. Such enzymes mainly catalyze the o-hydroxylation of a broad spectrum of environmentally related contaminants into their corresponding o-diphenols. This review covers the latest advancement regarding the exploitation of these enzymes for sustainable oxidation of phenolic compounds in wastewater, and suggests a way forward.

show abstract

“…In the paper, the RMSE (Root Mean Square Error), standard error, was adopted as the standard of evaluating the curacy of the model [15]. The RMSE can be computed from the definition of it in Eq.…”

Section: Figure I Flowchart Of Analysis and Processmentioning

confidence: 99%

Comparison and Verification of Methods for Multivariate Statistical Analysis and Regression in Crop Modelling

Jiang¹,

Zhang²,

Yang³

et al. 2015

Proceedings of the 2015 International Conference on Electrical, Automation and Mechanical Engineering

View full text Add to dashboard Cite

-In crop modelling, factor analysis and regression type have direct influence on the accuracy of model, but the application of these methods usually depends on the experience. In this paper, the performance of some common methods of statistical analysis and regression model was compared and verified, in order to avoid the blindness in crop modelling. The monitoring data of growth environment and photosynthesis of tomato, pumpkin and cucumber was obtained by PTM-48A, for the object variable of CO 2 exchange rate, selectivity on the main environmental factors by correlation analysis and path analysis were quantify compared, the performance of four kinds of multivariate binomial regression equations was compared in respects of complexity and accuracy, then the effectiveness of modelling was verified with the selected optimized multivariate statistical analysis and regression equation. Results showed that path analysis was more comprehensive than correlation to discrimination the variables, and the pure quadratic was more suitable to crop modelling because of its simple structure and high accuracy. The conclusion of the paper has general applicability, and offers a useful reference and guide for the other crops' modelling.

show abstract

Improvement of Artificial Neural Network Model for the Prediction of Wastewater Treatment Plant Performance

Cited by 11 publications

References 0 publications

Modeling of copper removal from aqueous solutions by using carbon-based adsorbents derived from hazelnut and walnut shells by artificial neural network

Modeling of copper removal from aqueous solutions by using carbon-based adsorbents derived from hazelnut and walnut shells by artificial neural network

Applications of Biocatalysts for Sustainable Oxidation of Phenolic Pollutants: A Review

Comparison and Verification of Methods for Multivariate Statistical Analysis and Regression in Crop Modelling

Contact Info

Product

Resources

About