Application of artificial neural networks for modeling of biohydrogen production

Nasr, Noha; Hafez, Hisham; Naggar, M. Hesham El; Nakhla, George

doi:10.1016/j.ijhydene.2012.12.109

Cited by 89 publications

(30 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the last few years ANN based modeling helped to develop empirical models and also achieve better statistical analysis on experimental data (Nasr et al 2013). ANN is a colossal structure of interconnected networks consisting of numerous individual elements called neurons, capable of performing parallel computations for data processing.…”

Section: Artificial Neural Network and Design Of Experimentsmentioning

confidence: 99%

Modeling of liquid hydrocarbon products from syngas

Atashi

Hajisafari

Rezaeian

et al. 2018

Int J Coal Sci Technol

View full text Add to dashboard Cite

The modeling of hydrocarbon selectivity and CO conversion of the Fischer-Tropsch synthesis over Fe-Ni/Al 2 O 3 catalyst by using coupled artificial neural networks (ANN) and design of experiment (DOE) approaches were investigated. The variable parameters for modeling consisted of the pressure range between 2 and 10 bar and the temperature range of 523-573 K. After training of data by ANN and determination of DOE points by central composite design (CCD), the results were compiled together for producing simulated data used in the response surface method (RSM). The RSM was used as an applied mathematics model to demonstrate the CO conversion and selectivity of hydrocarbons dependence on the CO hydrogenation conditions. The results indicated that CO conversion and C þ 5 selectivity increased with rising both temperature and pressure. The methane selectivity showed upward trend as the temperature increased. It also increased by decreasing pressure. Finally, the optimization of the catalytic process was carried out and conditions with maximum desired product were obtained. A comparison of experimental values and RSM values show that the RSM equations are able to predict the behavior of experimental data.

show abstract

Section: Artificial Neural Network and Design Of Experimentsmentioning

confidence: 99%

Modeling of liquid hydrocarbon products from syngas

Atashi

Hajisafari

Rezaeian

et al. 2018

Int J Coal Sci Technol

View full text Add to dashboard Cite

show abstract

“…Training the model is the process of determining the adjustable weights, and it is similar to the process of determining the coefficients of a regression model by least squares approach. The weights are initially selected randomly and an optimization algorithm is then used to find the weights that minimize the differences between the modelcalculated and the experimental outputs [15]. Across the whole modelling procedure, no physical equation is used (see Figure 2).…”

Section: Artificial Intelligence (Ai) Modelmentioning

confidence: 99%

Early Detection of Diabetes using Thermography and Artificial Neural Networks

Abdulshahed¹,

Fm²

2017

IJCNE

View full text Add to dashboard Cite

“…The International Water Association (IWA) Anaerobic Digestion Model No.1 (ADM1), a typical deterministic model, has been successfully used for modeling the whole anaerobic digestion process [19]. However, its mathematical complexity associated with extreme analytical difficulty of measuring kinetic parameters turns out to be laborious and time consuming [20,21]. On the other hand, stochastic based non-linear multiple regression model is preferably easy to handle as well as capable to estimate the relation between variables and numerical parameters [22,23].…”

Section: Introductionmentioning

confidence: 99%

Modelling Biogas Fermentation from Anaerobic Digestion: Potato Starch Processing Wastewater Treated Within an Up flow Anaerobic Sludge Blanket

Antwi¹,

Li²,

Shi³

et al. 2017

J Bioremediat Biodegrad

View full text Add to dashboard Cite

IntroductionPotato is one of the most valuable food crop grown in many countries [1]. It has been reported that, a considerable proportion of the potato cultivated globally consumed through starch processing which subsequently generates tons of wastewater that goes to pollute water bodies [1][2][3]. Wastewater of raw potato processed into starch are classified as complex wastewater [4,5], and its concentration of chemical oxygen demand (COD), total suspended solid (TSS) and volatile suspended solid of (VSS) can yield concentrations of 50000, 9700 and 9500 mg/L, respectively [6]. Arhoun et al. argued that recovering valuable resource such as bioenergy (biogas) from such wastewater to supplement energy needs will be beneficial to humans and society at large [6,7]. Anaerobic digestion has severally been reported as a successful bioprocess treating various organic wastewaters and subsequently generating biogas [7][8][9][10][11][12]. However, the biological mechanism of anaerobic digestion is not well understood due to the complexity of the bacterial community structure and bioconversion [13]. Hu et al. asserted that process modeling is a good tool for predicting and describing the performance of biological processes [13]. Other reports also confirmed that process modeling based on previously acquired data is one technical route to enhancing the performance of anaerobic processes. These process models are often developed [14,15]. Nonetheless, modeling of anaerobic digestion is quite challenging and tough because performance of anaerobic systems is complex and varies considerably with influent characteristics and operational conditions [16].Some predictive models have been developed in the past decades for biogas estimation during anaerobic treatment processes. For instance, a regression analysis model for estimating biogas generated in a landfill leachate treatment process was developed by Akaya et al. AbstractHerein, a modeling approach to predict biogas yield within a mesophilic (35 ± 1°C) upflow anaerobic sludge blanket (UASB) reactor treating potato starch processing wastewater (PSPW) for pollutant removal was conducted. HRTs and seven anaerobic process-related parameters viz; chemical oxygen demand (COD), ammonium (NH 4 + ), alkalinity, total Kjeldahl Nitrogen, total phosphorus, volatile fatty acids (VFAs) and pH with average concentration of 4028.91, 110.09, 4944.67, 510.47, 45.20, 534.44 mg/L and 7.09, respectively, were used as input variables (x) to develop stochastic models for predicting biogas yield from the anaerobic digestion of PSPW. Based on the prediction accuracy of the models, it was established that, prediction of biogas yield from the UASB with the combination of COD, NH 4 + and HRT, or COD, NH 4 + , HRT and VFAs as input variables proved more efficient as opposed to HRT, alkalinity, total Kjeldahl Nitrogen, total phosphorus and pH. Highest coefficient of determination (R 2 ) observed was 97.29%, suggesting the efficiency of the models in making predictions. The developed models efficiencies co...

show abstract

Application of artificial neural networks for modeling of biohydrogen production

Cited by 89 publications

References 27 publications

Modeling of liquid hydrocarbon products from syngas

Modeling of liquid hydrocarbon products from syngas

Early Detection of Diabetes using Thermography and Artificial Neural Networks

Modelling Biogas Fermentation from Anaerobic Digestion: Potato Starch Processing Wastewater Treated Within an Up flow Anaerobic Sludge Blanket

Contact Info

Product

Resources

About