Artificial neural networks with response surface methodology for optimization of selective CO2 hydrogenation using K-promoted iron catalyst in a microchannel reactor

Sun, Yi; Yang, Gang; Wen, Chao; Zhang, Lian; Sun, Zhi

doi:10.1016/j.jcou.2017.11.013

Cited by 58 publications

(31 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The MSE and MARR for each training attempt in every replication for each of response (hydrogen yield, metabolites—acetic acid, propionic acid, butyric acid, and ethanol) are shown in Table S3. The MSE and MARR of each replica are close to each other indicating a good training for the established ANN structures . The multiple regression of process parameters to the corresponding response could be constructed using a second‐order polynomial expression to find the offset, linear, quadratic, and interaction terms as the following:

Y_{i} = b_{0} + \sum_{i = 1}^{4} b_{i} X_{i} + \sum_{i = 1}^{4} b_{ii} {X_{i}}^{2} + \sum_{i < j, j = 2}^{4} b_{ij} X_{i} X_{j}

where Y i represents responded value, while b 0 , b i , and b ii (b ij ) are coefficients from polynomial expression.…”

Section: Resultsmentioning

confidence: 91%

“…In this work, the experimental data sets (Table ) were employed for training ANNs. The detailed training techniques regarding the procedures and leaving one out cross validation methodology could be found in our previous report . The mean square error ( MSE ) and mean relative residual relation ( MARR ) were calculated as the following:

italicMSE % = \frac{1}{N_{italicexp}} \sum_{j = 1}^{N_{italicexp}} {(r_{i}^{italicexp} - r_{i}^{italiccal})}^{2} \times 100 %

italicMARR % = \frac{1}{N_{italicexp}} \sum_{j = 1}^{N_{italicexp}} ((), \frac{|r_{i}^{italicexp} - r_{i}^{italiccal}|}{r_{i}^{\exp}}) \times 100 %

…”

Section: Methodsmentioning

confidence: 99%

“…Due to its excellent abilities such as handling data with high dimensionality, the approximation for arbitrary nonlinear functions, and computational efficiency, the artificial neural network (ANN) system has successfully provided a good representation in biological, chemical, and physical phenomena . Recently, the advanced system that aims to balance the compromise between the accuracy of models and cost‐effectiveness of collecting limited numbers of experimental conditions, of which combines both advantages of ANNs and the response surface methodology (RSM), has been reported . Although many works have been done using the RSM as a tool for the optimization of hydrogen dark fermentation, the employment of the hybrid ANNs‐RSM system and its application in the investigation of the effect of critical operational conditions, ie, BC, metal cofactor Ni 0 , pH, and dosage of microbes upon hydrogen production, to the best of our knowledge, have never been reported before.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Optimization and kinetic modeling of an enhanced bio-hydrogen fermentation with the addition of synergistic biochar and nickel nanoparticle

et al. 2018

Self Cite

View full text Add to dashboard Cite

Summary The improvement of hydrogen production was achieved by the addition of biochar (BC) and metal co‐factor nanoparticle Ni0 during the dark fermentation. A new hybrid approach by combing the artificial neural networks with the response surface methodology was applied to optimize the hydrogen production. The effects of operating conditions, ie, BC, metal cofactor Ni0, pH, and dosage of microbes, upon the hydrogen production together with the concentrations of other metabolites such as the acetic acid, propionic acid, butyric acid, and ethanol were extensively investigated. From kinetic study of the major metabolites, the acetate pathway was found to be apparently enhanced by the addition of synergistic factors. The modified anaerobic digestion model with the consideration of inhabitation factor was found to best represent the kinetics of hydrogen production and the formation of major metabolites.

show abstract

Y_{i} = b_{0} + \sum_{i = 1}^{4} b_{i} X_{i} + \sum_{i = 1}^{4} b_{ii} {X_{i}}^{2} + \sum_{i < j, j = 2}^{4} b_{ij} X_{i} X_{j}

where Y i represents responded value, while b 0 , b i , and b ii (b ij ) are coefficients from polynomial expression.…”

Section: Resultsmentioning

confidence: 91%

italicMSE % = \frac{1}{N_{italicexp}} \sum_{j = 1}^{N_{italicexp}} {(r_{i}^{italicexp} - r_{i}^{italiccal})}^{2} \times 100 %

italicMARR % = \frac{1}{N_{italicexp}} \sum_{j = 1}^{N_{italicexp}} ((), \frac{|r_{i}^{italicexp} - r_{i}^{italiccal}|}{r_{i}^{\exp}}) \times 100 %

…”

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Optimization and kinetic modeling of an enhanced bio-hydrogen fermentation with the addition of synergistic biochar and nickel nanoparticle

et al. 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…34 The schematic diagram of the flow chart to construct data set together with statistical analysis for FT synthesis in a microchannel reactor is depicted in Figure 1. This suggests that the established data set is statistically reliable.…”

Section: Establishment Of Anns-rsm Systemmentioning

confidence: 99%

A simple coupled ANNs‐RSM approach in modeling product distribution of Fischer‐Tropsch synthesis using a microchannel reactor with Ru‐promoted Co/Al ₂ O ₃ catalyst

Sun

Yang

et al. 2019

Int J Energy Res

Self Cite

View full text Add to dashboard Cite

A simple approach using hybrid artificial neural networks (ANNs)-response surface methodology (RSM) was developed to model the detailed product distribution using Ru-promoted cobalt-based catalyst with Al 2 O 3 as the support in a microchannel reactor for Fischer-Tropsch (FT) synthesis. Using the independent process parameters for training, the established model is capable of predicting hydrocarbon production distributions, ie, paraffin formation rate (C 2 -C 15 ) and olefin to paraffin ratio (OPR C 2 -C 15 ) within acceptable uncertainties. The ANNs-RSM model and comprehensive mechanistic model using the Langmuir-Hinshelwood-Hougen-Watson (LHHW) approach were compared to identify a few inherent advantages of the proposed model in modeling complex FT synthesis. The proposed ANNs-RSM model shows its appealing merits, ie, faster converge and higher accuracy (less than ±10% uncertainties was achieved from ANNs-RSM model, while LHHW model achieved less than ±15% uncertainties except a few exceptional high errors uncertainties at certain experimental conditions). The statistical significances to the product distributions and hydrocarbon formation rate during FT synthesis could be easily identified and quantitatively analyzed by the established ANNs-RSM model.The future effective alternative of kinetic study of the complex system such as FT synthesis in the microstructured reactor might follow the methods of using empirical reliable approach for process optimization together with mechanistic kinetic study for detailed reaction pathway discrimination.

show abstract

“…These mature techniques are facing great challenge, as more stringent environmental and emission regulations are being enforced. The current proposed imminent mitigation strategy lies in simultaneous carbon capture and storage or carbon capture and utilization, which converts the captured CO 2 into hydrocarbons on industrial scale such as via Fischer‐Tropsch synthesis technology . The great barriers, that is, cost‐effectiveness, reliabilities, therefore, needed to be overcome before hydrogen energy can be maturely implemented to replace current existing infrastructures of the fossil based energy production and utilization.…”

Section: Introductionmentioning

confidence: 99%

Optimization of biohydrogen production using acid pretreated corn stover hydrolysate followed by nickel nanoparticle addition

et al. 2019

Self Cite

View full text Add to dashboard Cite

Summary The dilute acid hydrolysis using corn stover (CS) to produce reducible sugars was optimized by the response surface methodology. The electron‐equivalent balances of the main metabolites during the dark fermentation (DF) using acid hydrolysate were investigated to identify the evolutions of the electron sinks over the course of DF. The additions of nickel ion and Ni0 nanoparticles (NPs) were found to effectively enhance the hydrogen production at experimental conditions. The optimal condition (HCl 2.5 wt%, hydrolyzing duration 105 minutes, pH=5, S/B=3.5, Ni0 NPs=10 mg/L‐1) was achieved with YH2/S reaching 1.18 (mol.mol‐1‐glucose). The YH2/S increased from 0.7 (mol.mol‐1‐glucose) to 1.18 (mol.mol‐1‐glucose) reaching 40% hydrogen yield increase when Ni0 NPs was added to the fermentation broth. Among the investigated significant soluble metabolites, the butyric acid was found to serve as the largest e‐sink in the electron‐equivalent balance. The additions of Ni0 NPs at low level (below 10 mg/L) were found to appreciably increase the hydrogen production. The increased pH and substrate to biomass ratio were found to skew the metabolic balance from hydrogen production to the biosynthesis (an increase of biomass). The proposed anaerobic digestion model with consideration of the inhibitory factors model presents a good agreement with the experimental data. The chemical addition such as nickel ions, Ni0 NPs was found to be a practical approach in enhancing biohydrogen production using CS acid hydrolysate as cultivation broth.

show abstract

Artificial neural networks with response surface methodology for optimization of selective CO2 hydrogenation using K-promoted iron catalyst in a microchannel reactor

Cited by 58 publications

References 33 publications

Optimization and kinetic modeling of an enhanced bio-hydrogen fermentation with the addition of synergistic biochar and nickel nanoparticle

Optimization and kinetic modeling of an enhanced bio-hydrogen fermentation with the addition of synergistic biochar and nickel nanoparticle

A simple coupled ANNs‐RSM approach in modeling product distribution of Fischer‐Tropsch synthesis using a microchannel reactor with Ru‐promoted Co/Al ₂ O ₃ catalyst

Optimization of biohydrogen production using acid pretreated corn stover hydrolysate followed by nickel nanoparticle addition

Contact Info

Product

Resources

About

Artificial neural networks with response surface methodology for optimization of selective CO2 hydrogenation using K-promoted iron catalyst in a microchannel reactor

Cited by 58 publications

References 33 publications

Optimization and kinetic modeling of an enhanced bio-hydrogen fermentation with the addition of synergistic biochar and nickel nanoparticle

Optimization and kinetic modeling of an enhanced bio-hydrogen fermentation with the addition of synergistic biochar and nickel nanoparticle

A simple coupled ANNs‐RSM approach in modeling product distribution of Fischer‐Tropsch synthesis using a microchannel reactor with Ru‐promoted Co/Al 2 O 3 catalyst

Optimization of biohydrogen production using acid pretreated corn stover hydrolysate followed by nickel nanoparticle addition

Contact Info

Product

Resources

About

A simple coupled ANNs‐RSM approach in modeling product distribution of Fischer‐Tropsch synthesis using a microchannel reactor with Ru‐promoted Co/Al ₂ O ₃ catalyst