Modeling the effect of non‐linear process parameters on the prediction of hydrogen production by steam reforming of bio‐oil and glycerol using artificial neural network

Abstract

Biomass-derived substrates such as bio-oil and glycerol are gaining wide acceptability as feedstocks to produce hydrogen using a steam reforming process. The wide acceptability can be attributed to a huge amount of glycerol and bio-oil obtained as by-products of biodiesel production and pyrolysis processes. Several parameters have been reported to affect the production of hydrogen by biomass steam reforming. This study investigates the effect of non-linear process parameters on the prediction of hydrogen production by biomass (bio-oil and glycerol) steam reforming using artificial neural network (ANN) modeling technique. Twenty different multilayer ANN model architectures were tested using datasets obtained from the bio-oil and glycerol steam reforming. Two algorithms namely Levenberg-Marquardt and Bayesian regularization were employed for the training of the ANNs. An optimized network configuration consisting of 3 input layer 14 hidden neurons, 1 output layer, and 3 input layer, 5 hidden neurons, and 1 output layer were obtained for the Levenberg-Marquardt and Bayesian regularization trained network, respectively for hydrogen production by bio-oil steam reforming. While an optimized network configuration consisting of 5 input nodes, 9 hidden neurons, 1 output node, and 5 input nodes, 8 hidden neurons, and 1 output node were obtained for Levenberg-Marquardt and Bayesian regularization trained network, respectively for hydrogen production by glycerol steam reforming. Based on the optimized network, the predicted hydrogen production from the bio-oil and glycerol steam agreed with the actual values with the coefficient of determination (R 2) > 0.9. A low mean square error of 3.024 × 10 −24 and 6.22 × 10 −15 for the optimized for Levenberg-Marquardt and Bayesian regularization-trained ANN, respectively. The neural network analyses of the two processes showed that reaction temperature and glycerol-to-water molar ratio were the most relevant factors that influenced the production of hydrogen by bio-oil and glycerol steam reforming, respectively. This study has demonstrated the robustness of the ANN as a technique for investigating the effect of non-linear process parameters on hydrogen production by bio-oil and glycerol steam reforming.

Modeling the prediction of hydrogen production by co‐gasification of plastic and rubber wastes using machine learning algorithms

“…As indicated by the R 2 of .981, the 2-LMLP neural network model can generalize 98.1% of the data set with minimal residuals (Figure 8B). The MLP model performance in this study is consistent with that reported by Karaci et al, 37 Syed et al, 38 Alsaffar et al, 39 and Mageed et al 40 for modeling hydrogen dual fueled diesel engine characteristic, hydrogen-rich syngas production from pyrolysis, prediction of carbon deposition from methane dry reforming and hydrogen-rich syngas production from bio-oil and glycerol pyrolysis, respectively. The one-layer MLP neural network model reported by Syed et al 38 was robust in predicting the characteristics of the hydrogen dual fueled diesel with a minimal prediction error.…”

“…With an R 2 of .950, the predicted hydrogen‐rich syngas was in proximity to the observed values. Similarly, the MLP neural network model was robust in predicting hydrogen production from the pyrolysis of bio‐oil and glycerol 40 . Using a topology of 3‐16‐1 for the MLP neural network model, the amount of carbon deposited on Ni catalysts during methane dry reforming was well modeled as evident by the close agreement between the predicted carbon deposited and the observed values.…”

“…Similarly, the MLP neural network model was robust in predicting hydrogen production from the pyrolysis of bio-oil and glycerol. 40 Using a topology of 3-16-1 for the MLP neural network model, the amount of carbon deposited on Ni catalysts during methane dry reforming was well modeled as evident by the close agreement between the predicted carbon deposited and the observed values. The MLP neural network model has the advantage of directly attaining the expected decision function without any prior assumption on the probabilistic information about the problem under consideration.…”

Investigating the effect of TiO2-based nanofluids in the stability of crude oil flow: parametric analysis and Gaussian process regression modeling

“…Similarly, GPR has also been used to model the relationship between capacity, storage temperature, and state-of-charge (Liu et al 2020). The GPR model displayed a robust prediction performance of high accuracy and accurate generalization ability (Mageed et al 2020;Shnain et al 2022). Extensive literature search shows that the use of GPR for modeling the relationship between parameters such as the pH, salinity, and the ratio of TiO 2 /SiO 2 nanoparticle in the nanofluids and the amount of n-heptane in crude oil has not been reported.…”

Mechanism of CaO catalyst deactivation with unconventional monitoring method for glycerol carbonate production via transesterification of glycerol with dimethyl carbonate

“…Glycerol can be converted to fuel extender 4,5 and various chemicals such as hydrogen/syngas, propanediol, acrolein, propylene glycol, and glycerol carbonate through different pathways, steam [6][7][8] /dry reforming, 9 hydrogenolysis, 10 dehydration, oxidation, and transesterification, respectively. 11 One of the most promising products is glycerol carbonate (4-hydroxymethyl-1, 3-dioxolan-2-one, CAS #931-40-8) due to its excellent biodegradability, high boiling point, high flash point, low toxicity, and water solubility.…”