Limits...
Degradation and mineralization of phenol compounds with goethite catalyst and mineralization prediction using artificial intelligence.

Tisa F, Davoody M, Abdul Raman AA, Daud WM - PLoS ONE (2015)

Bottom Line: The efficiency of phenol degradation via Fenton reaction using mixture of heterogeneous goethite catalyst with homogeneous ferrous ion was analyzed as a function of three independent variables, initial concentration of phenol (60 to 100 mg /L), weight ratio of initial concentration of phenol to that of H2O2 (1: 6 to 1: 14) and, weight ratio of initial concentration of goethite catalyst to that of H2O2 (1: 0.3 to 1: 0.7).Two separate models were developed using artificial neural networks to predict degradation percentage by a combination of Fe3+ and Fe2+ catalyst.Satisfactory agreement was observed between testing data and the predicted values (R2Phenol = 0.9214 and R2TOC= 0.9082).

View Article: PubMed Central - PubMed

Affiliation: Department of Chemical Engineering, Faculty of Engineering, University of Malaya,50603 Kuala Lumpur, Malaysia.

ABSTRACT
The efficiency of phenol degradation via Fenton reaction using mixture of heterogeneous goethite catalyst with homogeneous ferrous ion was analyzed as a function of three independent variables, initial concentration of phenol (60 to 100 mg /L), weight ratio of initial concentration of phenol to that of H2O2 (1: 6 to 1: 14) and, weight ratio of initial concentration of goethite catalyst to that of H2O2 (1: 0.3 to 1: 0.7). More than 90 % of phenol removal and more than 40% of TOC removal were achieved within 60 minutes of reaction. Two separate models were developed using artificial neural networks to predict degradation percentage by a combination of Fe3+ and Fe2+ catalyst. Five operational parameters were employed as inputs while phenol degradation and TOC removal were considered as outputs of the developed models. Satisfactory agreement was observed between testing data and the predicted values (R2Phenol = 0.9214 and R2TOC= 0.9082).

No MeSH data available.


Contribution of input parameters on outputs based on PaD method.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4388832&req=5

pone.0119933.g010: Contribution of input parameters on outputs based on PaD method.

Mentions: Combination of (Equation 12) and (13) and incorporation of them to (Equation 11) results in (Equation 14):Si=1N∑p∂ok∂oj∂oj∂xi=1N∑pf2℩(∑jwkjoj)∑jwkjf1℩(∑iwijxi)wij(14)Since the activation functions are sigmoid:f1=f(1−f)And (Equation 14) can be updated to (Equation 15):Si=1N∑pok(1−ok)∑jwkjoj(1−oj)wij(15)Moreover, the relative contribution of input parameters can be calculated by computing the sum of the squares of the partial derivatives:SSDi=∑P(∂okp∂xiP)2(16)And contribution of each input parameter is given by:Contributionofithvariable=SSDi∑iSSDi(17)Higher value of SSD indicates higher influence of the input variable on the output. Therefore, input variables can be ranked according to their impact on the target. Fig. 10 presents the contributions of the input variables based on PaD sensitivity analysis.


Degradation and mineralization of phenol compounds with goethite catalyst and mineralization prediction using artificial intelligence.

Tisa F, Davoody M, Abdul Raman AA, Daud WM - PLoS ONE (2015)

Contribution of input parameters on outputs based on PaD method.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4388832&req=5

pone.0119933.g010: Contribution of input parameters on outputs based on PaD method.
Mentions: Combination of (Equation 12) and (13) and incorporation of them to (Equation 11) results in (Equation 14):Si=1N∑p∂ok∂oj∂oj∂xi=1N∑pf2℩(∑jwkjoj)∑jwkjf1℩(∑iwijxi)wij(14)Since the activation functions are sigmoid:f1=f(1−f)And (Equation 14) can be updated to (Equation 15):Si=1N∑pok(1−ok)∑jwkjoj(1−oj)wij(15)Moreover, the relative contribution of input parameters can be calculated by computing the sum of the squares of the partial derivatives:SSDi=∑P(∂okp∂xiP)2(16)And contribution of each input parameter is given by:Contributionofithvariable=SSDi∑iSSDi(17)Higher value of SSD indicates higher influence of the input variable on the output. Therefore, input variables can be ranked according to their impact on the target. Fig. 10 presents the contributions of the input variables based on PaD sensitivity analysis.

Bottom Line: The efficiency of phenol degradation via Fenton reaction using mixture of heterogeneous goethite catalyst with homogeneous ferrous ion was analyzed as a function of three independent variables, initial concentration of phenol (60 to 100 mg /L), weight ratio of initial concentration of phenol to that of H2O2 (1: 6 to 1: 14) and, weight ratio of initial concentration of goethite catalyst to that of H2O2 (1: 0.3 to 1: 0.7).Two separate models were developed using artificial neural networks to predict degradation percentage by a combination of Fe3+ and Fe2+ catalyst.Satisfactory agreement was observed between testing data and the predicted values (R2Phenol = 0.9214 and R2TOC= 0.9082).

View Article: PubMed Central - PubMed

Affiliation: Department of Chemical Engineering, Faculty of Engineering, University of Malaya,50603 Kuala Lumpur, Malaysia.

ABSTRACT
The efficiency of phenol degradation via Fenton reaction using mixture of heterogeneous goethite catalyst with homogeneous ferrous ion was analyzed as a function of three independent variables, initial concentration of phenol (60 to 100 mg /L), weight ratio of initial concentration of phenol to that of H2O2 (1: 6 to 1: 14) and, weight ratio of initial concentration of goethite catalyst to that of H2O2 (1: 0.3 to 1: 0.7). More than 90 % of phenol removal and more than 40% of TOC removal were achieved within 60 minutes of reaction. Two separate models were developed using artificial neural networks to predict degradation percentage by a combination of Fe3+ and Fe2+ catalyst. Five operational parameters were employed as inputs while phenol degradation and TOC removal were considered as outputs of the developed models. Satisfactory agreement was observed between testing data and the predicted values (R2Phenol = 0.9214 and R2TOC= 0.9082).

No MeSH data available.