Optimization of fermentative hydrogen production process using genetic algorithm based on neural network and response surface methodology

A central composite design was carried out to investigate the effect of temperature, initial pH and glucose concentration on fermentative hydrogen production by mixed cultures in batch test. The modeling abilities of the response surface methodology model and neural network model, as well as the optimizing abilities of response surface methodology and the genetic algorithm based on a neural network model were compared. The results showed that the root mean square error and the standard error of prediction for the neural network model were much smaller than those for the response surface methodology model, indicting that the neural network model had a much higher modeling ability than the response surface methodology model. The maximum hydrogen yield of 289.8 mL/g glucose identified by response surface methodology was a little lower than that of 360.5 mL/g glucose identified by the genetic algorithm based on a neural network model, indicating that the genetic algorithm based on a neural network model had a much higher optimizing ability than the response surface methodology. Thus, the genetic algorithm based on a neural network model is a better optimization method than response surface methodology and is recommended to be used during the optimization of fermentative hydrogen production process.     

Ni–Mo nanoparticles stabilized by ether functionalized ionic polymer: A novel and efficient catalyst for hydrodeoxygenation of 4-methylanisole as a representative of lignin-derived pyrolysis bio-oils

In the present study, nickel-molybdenum nanoparticles stabilized with ether functionalized ionic polymer were synthesized and utilized as a novel and efficient catalyst for hydrodeoxygenation of 4-methylanisole as a representative of lignin-derived bio-oil. The catalytic upgrading process was performed in the presence of hydrogen with a batch reactor at temperature of 80–200 °C, hydrogen pressure of 10–50 bar, reaction time of 0.5–15 h and catalyst loading of 1–5 mol%. The major reaction classes during 4-methylanisole upgrading were hydrodeoxygenation and hydrogenolysis which resulted in production of 4-methylphenol, toluene, phenol and benzene as the main products. The experimental results indicated that the catalytic activity of Ni–Mo (20%–80%) nanoparticles stabilized with ionic polymer is superior to that with low Mo content. Also, it is observed that the selectivity of deoxygenated products including toluene and benzene improves with increasing the Mo content of the catalyst. Finally, regarding to the excellent catalytic activity of synthesized nanocatalyst during upgrading process of bio-oil at mild operating condition, ether functionalized ionic polymer was introduced as an applicable and effective stabilizers for nickel-molybdenum nanoparticles.     

Process modeling and optimization of PECVD silicon nitride coated on silicon solar cell using neural networks

The process of plasma enhanced chemical vapor deposition silicon nitride films coated on silicon solar cells as antireflection layers is modeled and optimized using neural networks. This neural network model is built based on the robust design technique with process input–output experimental data. The input parameters selected are as substrate temperature, SiH₄ and NH₃ flow rates, and RF power; while the output parameters are deposition rate, refractive index, and short circuit current. This model can then be applied to predict the input–output relationships of the process. Optimal operating conditions of this process can be determined using this model.     

Optimization of hydrogen production via toluene steam reforming over Ni–Co supported modified-activated carbon using ANN coupled GA and RSM

Hydrogen (H₂) is a clean fuel that can be produced from various resources including biomass. Optimization of H₂ production from catalytic steam reforming of toluene using response surface methodology (RSM) and artificial neural network coupled genetic algorithm (ANN-GA) models has been investigated. In RSM model, the central composite design (CCD) is employed in the experimental design. The CCD conditions are temperature (500–900 °C), feed flow rate (0.006–0.034 ml/min), catalyst weight (0.1–0.5 g) and steam-to-carbon molar ratio (1–9). ANN model employs a three-layered feed-forward backpropagation neural network in conjugation with the tangent sigmoid (tansig) and linear (purelin) as the transfer functions and Levenberg-Marquardt training algorithm. Best network structure of 4-14-1 is developed and utilized in the GA optimization for determining the optimum conditions. An optimum H₂ yield of 92.6% and 81.4% with 1.19% and 6.02% prediction error are obtained from ANN-GA and RSM models, respectively. The predictive capabilities of the two models are evaluated by statistical parameters, including the coefficient of determination (R²) and root mean square error (RMSE). Higher R² and lower RSME values are reported for ANN-GA model (R² = 0.95, RMSE = 4.09) demonstrating the superiority of ANN-GA in determining the nonlinear behavior compared to RSM model (R² = 0.87, RMSE = 6.92). These results infer that ANN-GA is a more reliable and robust predictive steam reforming modelling tool for H₂ production optimization compared to RSM model.     

Application of response surface methodology and artificial neural network on pyrolysis of safflower seed press cake

In this study, mathematical correlation between the process variables and product yields for pyrolysis of safflower seed press cake (SPC) in fixed-bed reactor was investigated by using the response surface methodology (RSM) and artificial neural networks (ANNs). The RSM results showed that the second-order response model can be used to describe the relationship between the various factors and the response. Several feed-forward fully connected neural networks were investigated and optimal configuration of the ANN model was obtained. The results revealed that the ANN model could be considered as an alternative to RSM and practical modeling technique for the pyrolysis product yields.     

Artificial neural network modelling and experimental verification of the operating current of mono-crystalline photovoltaic modules

This article presents the artificial neural network modelling of the operating current of a 120 Wp of mono-crystalline photovoltaic module. As an alternative method to analytical modelling approaches, this study uses the advantages of neural networks such as no required knowledge of internal system parameters, less computational effort and a compact solution for multivariable problems. Generalised regression neural network model is used in the present article to predict the operating current of the photovoltaic module. To show its merit, the current predicted from the artificial neural network modelling is compared to that from the analytical model. The five-parameter analytical model is drawn from the equivalent electrical circuit that includes light-generated current, diode reverse saturation current, and series and shunt resistances. The operating current predicted from both the neural and analytical models are compared to the measured current. Results have shown that the artificial neural network modelling provides a better prediction of the current than the five-parameter analytical model.     

Prediction of dynamic viscosity of a hybrid nano-lubricant by an optimal artificial neural network

In this paper, at first, a new correlation was proposed to predict the relative viscosity of MWCNTs-SiO₂/AE40 nano-lubricant using experimental data. Then, considering minimum prediction error, an optimal artificial neural network was designed to predict the relative viscosity of the nano-lubricant. Forty-eight experimental data were used to feed the model. The data set was derived to training, validation and test sets which contained 70%, 15% and 15% of data points, respectively. The correlation outputs showed that there is a deviation margin of 4%. The results obtained from optimal artificial neural network presented a deviation margin of 1.5%. It can be found from comparisons that the optimal artificial neural network model is more accurate compared to empirical correlation.     

Optimum operating conditions for a water purification process integrated to a heat transformer with energy recycling using neural network inverse

Artificial neural network inverse (ANNi) is applied to calculate the optimal operating conditions on the coefficient of performance (COP) for a water purification process integrated to an absorption heat transformer with energy recycling. An artificial neural network (ANN) model is developed to predict the COP which was increased with energy recycling. This ANN model takes into account the input and output temperatures for each one of the four components (absorber, generator, evaporator, and condenser), as well as two pressures and LiBr + H₂O concentrations. For the network, a feedforward with one hidden layer, a Levenberg–Marquardt learning algorithm, a hyperbolic tangent sigmoid transfer function and a linear transfer function were used. The best fitting training data set was obtained with three neurons in the hidden layer. On the validation data set, simulations and experimental data test were in good agreement (R > 0.99). This ANN model can be used to predict the COP when the input variables (operating conditions) are well known. However, to control the COP in the system, we developed a strategy to estimate the optimal input variables when a COP is required from ANNi. An optimization method (the Nelder–Mead simplex method) is used to fit the unknown input variable resulted from the ANNi. This methodology can be applied to control on-line the performance of the system.     

Air-steam gasification of municipal solid wastes (MSWs) for hydrogen production

Gasification process can be considered as a partial thermal oxidation, which results in the production of a mixture of useful gases (CO, H₂, CH₄, and other gaseous hydrocarbons), little quantities of carbon black (char), ash, and several organic impurities (tar). In this study, we introduced an artificial neural network (ANN) model to simulate the influence of operating conditions on the concentration of products during the gasification process of municipal solid wastes (MSW). Results showed when increasing the residence time, more char is gasified, leading to an increase in the greenhouse gas emissions. It is also found that a further increase in the residence time results in a constant rate of products due to the heat and mass transfer limitations.     

Neural network observers for on-line tracking of synchronousgenerator parameters

This paper presents a methodology for implementing artificial neural network (ANN) observers in estimating and tracking synchronous generator parameters from time-domain online disturbance measurements. Data for training the neural network observers are obtained through offline simulations of a synchronous generator operating in a one-machine-infinite-bus environment. Nominal values of parameters are used in the machine model. After training, the ANN observer is tested with simulated online measurements to provide estimates of unmeasurable rotor body currents and in tracking simulated changes in machine parameters     

Investigation of optimum H2 production from date palm waste leaves using different modeling tools

Globally, the productive utilization of biomass has paid serious attention to fulfilling the energy requirements laid out by the international standards, as to reduce related carbon footprints. Therefore, this study investigates date palm waste leaves which aims to produce environment friendly H₂ gas using gasification technology. The results of 25 experimental runs exhibited that the higher H₂ produced at higher temperature which was mainly supported by water-gas-shift and steam-methane reforming reactions. H₂ prediction was modeled using response surface methodology (RSM) and artificial neural network (ANN). The RSM model exhibited a strong interaction with the regression coefficient (R²) and p-value of 0.89 and 0.000000, respectively. ANN data was disseminated thru K-fold contrivance with back-propagation algorithm. Hence, the training (80% data) and validation (20% data) datasets were found with R² and root mean squared error (RSME) of 0.90 and 0.28, and 0.86 and 0.39, respectively. Kinetics of the process estimated the activation energies (Ea) using Ozawa-Flynn-Wall (OFW), Starink (STK), and Kissinger-Akahira-Sunose (KAS) models. Hence, the values of Ea and R² at conversion degrees (α) 0.1 to 0.8 were ranged between 129.40 and 326.64 kJ/mol and 0.92 to 0.97, respectively. Optimum H₂ production of 49.03 vol% (with LHV of 11.10 MJ/Nm³) was produced. This finding is thought to be a better source of energy which can be an appropriate fuel for Fischer Tropsch process for manufacturing of transportation fuels.     

Assessment of producer gas composition in air gasification of biomass using artificial neural network model

Energy generation from renewable and carbon-neutral biomass is significant in the context of a sustainable energy framework. Hydrogen can be conveniently extracted from biomass through thermo-chemical conversion process of gasification. In the present work, an artificial neural network (ANN) model is developed using MATLAB software for gasification process simulation based on extensive data obtained from experimental investigations. Experimental investigations on air gasification are conducted in a bubbling fluidised bed gasifier with different locally available biomasses at various operating conditions to obtain the producer gas. The developed artificial neural network consists of seven input variables, output layer with four output variables and one hidden layer with fifteen neurons. The multi-layer feed-forward neural network is trained employing Levenberg–Marquardt back-propagation algorithm. Performance of the model appraised using mean squared error and regression analysis shows good agreement between the output and target values with a regression coefficient, R = 0.987 and mean squared error, MSE = 0.71. The developed model is implemented to predict the producer gas composition from selected biomasses within the operating range. This model satisfactorily predicted the effect of operating parameters on producer gas yield, and is thus a useful tool for the simulation and performance assessment of the gasification system.     

Dynamic neural network controller model of PEM fuel cell system

This paper presents the artificial intelligence techniques to control a proton exchange membrane fuel cell system process, using particularly a methodology of dynamic neural network. In this work a dynamic neural network control model is obtained by introducing a delay line in the input of the neural network. A static production system including a PEMFC is subjected to variations of active and reactive power. Therefore the goal is to make the system follow these imposed variations. The simulation requires the modelling of the principal element (PEMFC) in dynamic mode. The simulation results demonstrate that the model-based dynamic neural network control scheme is appropriate for controlling, the stability of the identification and the tracking error were analyzed, and some reasons for the usefulness of this methodology are given.     

Modeling biohydrogen production using different data driven approaches

Three modeling techniques namely multilayer perceptron artificial neural network (MLPANN), microbial kinetic with Levenberg-Marquardt algorithm (MKLMA) developed from microbial growth, and the response surface methodology (RSM) were used to investigate the biohydrogen (BioH₂) process. The MLPANN and MKLMA were used to model the kinetics of major metabolites during the dark fermentation (DF). The MLPANN and RSM were deployed to model the electron-equivalent balance (EEB) from the cumulative data (after 24 h fermentation) during the DF. With the additional experimental results of kinetic data (20 × 10) and cumulative data (18 × 9), the uncertainties of different models were compared. A new effective strategy for modeling the complex BioH₂ process during the DF is proposed: MLPANN and MKLMA are used for the investigation of kinetics of the major metabolites from the limited numbers of experimental data set, and the MLPANN and RSM are used for statistical analysis of the investigated operational parameters upon the major metabolites through EEB perspective. The proposed strategy is a useful and practical paradigm in modeling and optimizing the BioH₂ production during the dark fermentation.     

Inverse neural network for optimal performance in polygeneration systems

In this paper, inverse neural network (ANNi) is applied to optimization of operating conditions or parameters in energy processes. The proposed method ANNi is a new tool which inverts the artificial neural network (ANN), and it uses a Nelder-Mead optimization method to find the optimum parameter value (or unknown parameter) for a given required condition in the process. In order to accomplish the target, first, it is necessary to build the artificial neural network (ANN) that simulates the output parameters for a polygeneration process. In general, this class of ANN model is constituted of a feedforward network with one hidden layer to simulate output layer, considering well-known input parameters of the process. Normally, a Levenberg–Marquardt learning algorithm, hyperbolic tangent sigmoid transfer-function, linear transfer-function and several neurons in the hidden layer (due to the complexity of the process) are considered in the constructed model. After that, ANN model is inverted. With a required output value and some input parameters it is possible to calculate the unknown input parameter using the Nelder-Mead algorithm. ANNi results on three different applications in energy processes showed that ANNi is in good agreement with target and calculated input data. Consequently, ANNi is applied to determine the optimal parameters, and it already has applications in different processes with a very short elapsed time (seconds). Therefore, this methodology can be useful for the controlling of engineering processes.     

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

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.     

Prediction of the SnO2-based sensor response for hydrogen detection by artificial intelligence techniques

SnO₂-based nanocomposites are reliable sensors to detect hydrogen leakage and satisfy safety protocols. Although the hydrogen detection response (HDR) of these sensors has been deeply studied in the laboratory, there are no models to estimate this parameter. Consequently, this study uses three machine learning classes (i.e., gene expression programming, support vector regression, and artificial neural network) to calculate the HDR of pure and Ag-, Co-, Pd-, Pt-, and Ru-decorated SnO₂ nanostructures. These models only need nanocomposite chemistry and operating conditions to estimate the HDR of SnO₂-based sensors. Comparing these models’ performance by the ranking analysis and spider-graph indicates the multilayer perceptron neural network is superior to the other models. This model shows the highest accuracy (regression coefficient = 0.9882, average absolute deviation = 2.74, and root mean squared errors = 8.05) for estimating the HDR of SnO₂-based sensors. This model also anticipates that Pd and Ru are the best and worst dopants to decorate the SnO₂-based sensors.     

Performance evaluation of artificial neural network coupled with generic algorithm and response surface methodology in modeling and optimization of biodiesel production process parameters from shea tree (Vitellaria paradoxa) nut butter

This work investigated the potential of shea butter oil (SBO) as feedstock for synthesis of biodiesel. Due to high free fatty acid (FFA) of SBO used, response surface methodology (RSM) was employed to model and optimize the pretreatment step while its conversion to biodiesel was modeled and optimized using RSM and artificial neural network (ANN). The acid value of the SBO was reduced to 1.19 mg KOH/g with oil/methanol molar ratio of 3.3, H₂SO₄ of 0.15 v/v, time of 60 min and temperature of 45 °C. Optimum values predicted for the transesterification reaction by RSM were temperature of 90 °C, KOH of 0.6 w/v, oil/methanol molar ratio of 3.5, and time of 30 min with actual shea butter oil biodiesel (SBOB) yield of 99.65% (w/w). ANN combined with generic algorithm gave the optimal condition as temperature of 82 °C, KOH of 0.40 w/v, oil/methanol molar ratio of 2.62 and time of 30 min with actual SBOB yield of 99.94% (w/w). Coefficient of determination (R²) and absolute average deviation (AAD) of the models were 0.9923, 0.83% (RSM) and 0.9991, 0.15% (ANN), which demonstrated that ANN model was more efficient than RSM model. Properties of SBOB produced were within biodiesel standard specifications.     

BP人工神经网络模型在溪洛渡、向家坝两库联合优化调度规则中的应用

基于BP人工神经网络算法的基本原理,采用水库水位与出力双决策控制,建立了溪洛渡、向家坝两库联合调度函数的BP人工神经网络模型。模拟调度结果表明,该模型能更好地映射调度函数中各变量之间的非线性关系,优化运行轨迹的拟合效果明显提高。