Artificial neural network based optimization for hydrogen purification performance of pressure swing adsorption

A pressure swing adsorption (PSA) cycle model is implemented on Aspen Adsorption platform and is applied for simulating the PSA procedures of ternary-component gas mixture with molar fraction of H₂/CO₂/CO = 0.68/0.27/0.05 on Cu-BTC adsorbent bed. The simulation results of breakthrough curves and PSA cycle performance fit well with the experimental data from literature. The effects of adsorption pressure, product flow rate and adsorption time on the PSA system performance are further studied. Increasing adsorption pressure increases hydrogen purity and decreases hydrogen recovery, while prolonging adsorption time and reducing product flow rate raise hydrogen recovery and lower hydrogen purity. Then an artificial neural network (ANN) model is built for predicting PSA system performance and further optimizing the operation parameters of the PSA cycle. The performance data obtained from the Aspen model is used to train ANN model. The trained ANN model has good capability to predict the hydrogen purification performance of PSA cycle with reasonable accuracy and considerable speed. Based on the ANN model, an optimization is realized for finding optimal parameters of PSA cycle. This research shows that it is feasible to find optimal operation parameters of PSA cycle by the optimization algorithm based on the ANN model which was trained on the data produced from Aspen model.     

Machine learning–based optimization for hydrogen purification performance of layered bed pressure swing adsorption

An adsorption, heat and mass transfer model for the five-component gas from coal gas (H₂/CO₂/CH₄/CO/N₂ = 38/50/1/1/10 vol%) in a layered bed packed with activated carbon and zeolite was established by Aspen Adsorption software. Compared with published experimental results, the hydrogen purification performance by pressure swing adsorption (PSA) in a layered bed was numerically studied. The results show that there is a contradiction between the hydrogen purity and recovery, so the multi-objective optimization algorithms are needed to optimize the PSA process. Machine learning methods can be used for data analysis and prediction; the polynomial regression (PNR) and artificial neural network (ANN) were used to predict the purification performance of two-bed six-step process. Finally, two ANN models combined with sequence quadratic program (SQP) algorithm were used to achieve multi-objective optimization of hydrogen purification performance. According to the analysis of the optimization results, the ANN models are more suitable for optimizing the purification performance of hydrogen than the PNR model.     

Prediction of jatropha-algae biodiesel blend oil yield with the application of artificial neural networks technique

In this work, the experiments of the transesterification process were carried out on jatropha-algae oil blend and the prediction of the synthesized biodiesel was investigated. The study was divided into two parts. In the first part, a series of experiments were employed practically and in the second part, the prediction is made with the artificial neural network (ANN). The ANN with Levenberg–Marquardt (LM) algorithm was trained with topology 4–10-1. The estimated results were compared with the experimental results. An ANN model was developed based on a back-propagation learning algorithm. An R-square value of the model from ANN was 0.9976. The results confirmed that the use of an ANN technique is quite suitable. The artificial neural network gave acceptable results.     

Parametric analysis and optimization of regenerative Clausius and organic Rankine cycles with two feedwater heaters using artificial bees colony and artificial neural network

The present work concerns the parametric study and optimization of regenerative Clausius and organic Rankine cycles (ORC) with two feedwater heaters. For the parametric optimization, thermal efficiency, exergy efficiency and specific work are selected as the objective functions, so the mentioned parameters are calculated for different values of the outlet pressures from the second and third pumps by using EES (Engineering Equation Solver) software. Aiming at optimizing these functions, a procedure based on artificial neural network (ANN) and artificial bees colony (ABC) is proposed. The procedure includes two stages. According to the obtained data from the parametric analysis, in the first stage three different multi-layer perceptron neural networks are trained. In the next stage, three distinct artificial neural networks are used to optimize the specific network, the thermal efficiency and the exergy efficiency. Variables and fitness functions in these algorithms are the inputs and the outputs of the corresponding trained neural network, respectively. This optimization process is applied to water for a Clausius Rankine cycle and also to R717 for an ORC. It is shown that some interesting features among optimal objective functions and decision variables involved in this power cycle can be discovered consequently.     

Investigation of syngas exergy value and hydrogen concentration in syngas from biomass gasification in a bubbling fluidized bed gasifier by using machine learning

In this study, an artificial neural network (ANN) model as a machine learning method has been employed to investigate the exergy value of syngas, where the hydrogen content in syngas reached maximum in bubbling fluidized bed gasifier which is developed in Aspen Plus® and validated from experimental data in literature. Levenberg-Marquardt algorithm has been used to train ANN model, where oxygen, hydrogen and carbon contents of sixteen different biomass, gasification temperature, steam and fuel flow rates were selected as input parameters of the model. Moreover, four different biomass samples, which hadn't been used in training and testing, have been used to create second validation. The hydrogen mole fraction of syngas was also evaluated at the different steam to fuel ratio and gasification temperature and the exergy value of syngas at the point where the hydrogen content in syngas reached maximum were estimated with low relative error value.     

Development and multi-utility of an ANN model for an industrial gas turbine

Demonstration of different utilities for industrial use of an artificial neural network (ANN) model for a gas turbine has been reported in this paper. The ANN model was constructed with the multi-layer feed-forward network type and trained with operational data using back-propagation. The results showed that operational and performance parameters of the gas turbine, including identification of anti-icing mode, can be predicted with good accuracy for varying local ambient conditions. Different possible applications of this ANN model were also demonstrated. These include instantaneous gas turbine performance estimation through a graphical user interface and extrapolation beyond the range of training data.     

Artificial intelligence based structural optimization of solid oxide fuel cell with three-dimensional reticulated trapezoidal flow field

Three-dimensional Reticulated trapezoidal flow field (RTFF) is promising in improving the performance and durability of the solid oxide fuel cell (SOFC). However, the structural complexity makes it challenging for the geometry configuration of the splitter and mixer. To this end, an intelligent optimization framework is proposed by coupling artificial neural network (ANN) and non-dominated sorting genetic algorithm-II (NSGA-II), in order to maximize the net power density and oxygen uniformity simultaneously. The ANN prediction model is trained to obtain the computationally efficient surrogate model of the computational fluid dynamics (CFD) numerical simulation. NSGA-II is used for the multi-objective optimization of the RTFF structural parameters. The results illustrate that the prediction model is of high prediction precision and generalization capability. In comparison to SOFC with conventional parallel flow fields (CPFF), the degree of the performance improvement of SOFC with optimized RTFF depends on the working condition, i.e., fuel and air flow rates and operating temperatures. The SOFC with the optimal RTFF achieves a higher molar concentration of oxygen and a more uniform distribution of oxygen and current density than the CPFF SOFC. The proposed optimization framework provides an efficient design method for the development of the next-generation SOFC flow field.     

Improvement of the three-dimensional fine-mesh flow field of proton exchange membrane fuel cell (PEMFC) using CFD modeling,artificial neural network and genetic algorithm

This study proposes a systematic methodology for improving PEMFC's performance combining computational fluid dynamic (CFD), artificial neural network (ANN), and intelligent optimization algorithms. Firstly, a three-dimensional (3-D) multiphase PEMFC CFD model with 3-D fine-mesh flow field is developed. Then the key structural features of the fine-mesh flow field are extracted as optimization decision variables, and the sampling points are selected by using the Latin hypercube sampling (LHS) experimental method. The power density and oxygen uniformity index of sampling points are calculated by CFD modeling to form the database, which is used to train the artificial neural network (ANN) surrogate model. Finally, the single-objective optimization (SOO) and multi-objective optimization (MOO) are implemented by using genetic algorithm (GA) and non-dominated sorting genetic algorithm (NSGA-II), respectively. It was found that using trained ANN surrogate models can get a high prediction precision. The maximum power density of SOO is increased by 7.546% than that of base case and is 0.562% larger than that of MOO case. However, the overall pressure drop in cathode flow field of SOO case is greater than that of MOO case and the base case. Furthermore, the oxygen concentration, the oxygen uniformity index and the water removal capacity of MOO case are better than that of SOO case. It is recommended that the improved flow field structure optimized by MOO is more beneficial to improve the overall performance of PEMFC.     

Simulation model of ANN based maximum power point tracking controller for solar PV system

In this paper the simulation model of an artificial neural network (ANN) based maximum power point tracking controller has been developed. The controller consists of an ANN tracker and the optimal control unit. The ANN tracker estimates the voltages and currents corresponding to a maximum power delivered by solar PV (photovoltaic) array for variable cell temperature and solar radiation. The cell temperature is considered as a function of ambient air temperature, wind speed and solar radiation. The tracker is trained employing a set of 124 patterns using the back propagation algorithm. The mean square error of tracker output and target values is set to be of the order of 10⁻⁵ and the successful convergent of learning process takes 1281 epochs. The accuracy of the ANN tracker has been validated by employing different test data sets. The control unit uses the estimates of the ANN tracker to adjust the duty cycle of the chopper to optimum value needed for maximum power transfer to the specified load.     

Prediction of hydrogen production by magnetic field effect water electrolysis using artificial neural network predictive models

Developing an efficient water electrolysis (WE) configuration is essential for high-efficiency hydrogen evolution reaction (HER) activity. In this regard, it has been proven that adding a magnetic field (MF) to the electrolysis system greatly improves the hydrogen output rate. In this study, we developed a method based on a machine learning approach to further improve the hydrogen production (HP) system with MF effect WE. An artificial neural network (ANN) model was developed to estimate the effect of input parameters such as MF, electrode material (cathode type), electrolyte type, supplied power (onset voltage), surface area, temperature, and time on HP in different electrolyzer systems. The network was built using 104 experimental data sets from various electrolysis studies. In the study, the percentage contributions of the input parameters to the HP rate and the optimum network architecture to minimize computation time and maximize network accuracy are presented. The model architecture of 7–12–1 was obtained using the best-hidden neurons. The Levenberg-Marquardt (LM) algorithm was used to train the multi-layer feed-forward neural network. Moreover, the utilization of a range of categorical variables to improve ANN prediction accuracy is a significant novelty in this work. Results demonstrated that the output of the trained ANN model fitted well with the experimental data. The test's correlation coefficient (R) and mean squared error (MSE) were 0.973 and 0.01125, respectively, confirming its powerful predictive performance. This ANN application is the first novel viable model to perform prediction using a neural network algorithm in the electrolysis process for MF effect HP using both categorical and continuous data inputs.     

Application of artificial neural networks (ANN) for modeling of industrial hydrogen plant

A back propagation feed forward artificial neural network (ANN) with three layers is used for modeling of industrial hydrogen plant. The required operating data for training of ANN is obtained by modeling and simulation of an industrial hydrogen plant. The operating data are calculated by changing effective parameters such as feed temperature, reformer pressure, steam to carbon ratio and carbon dioxide to methane ratio in feed stream. Tangent sigmoid transfer function is used in the hidden and output layer and the proposed neural network is trained with a gradient descent algorithm. The optimum number of neurons in hidden layer is determined as optimum value with minimizing of the mean square error (MSE). With changing of effective parameters, the model predicts temperature, pressure and mole fraction of hydrogen and carbon monoxide in the product of the hydrogen plant. The result can be used to gain better knowledge and optimize of the hydrogen production plants.     

Multi-objective optimization of ANN-based PSA model for hydrogen purification from steam-methane reforming gas

A 4-bed-8-step pressure swing adsorption (PSA) process has been developed to produce high-purity hydrogen from the steam methane reforming (SMR) gas mixture. The Detailed models have been established for hydrogen purification based on the experimentally determined parameters. Two surrogate models are investigated to optimize the process performance using artificial neural networks (ANN), which have been well trained by the samples, obtaining from the Detailed models using Latin hypercube sampling strategy. The results indicate that ANNs could approximate the performance and dynamic behavior of PSA process with extremely high accuracy. Herein, a robust and fast multi-objective optimization approach of PSA process using genetic algorithm on the basis of different ANN-based surrogate models has also been proposed, in which Dual- and Tri-objective optimizations are taken into account. This research shows that the method can not only find out the optimal operating conditions of the PSA process for hydrogen production with higher than 99% accuracy, namely Pareto-Optimal Fronts, but also provide a reliable reference for operational enhancement.     

Multi-objective optimization of an experimental integrated thermochemical cycle of hydrogen production with an artificial neural network

In this study, an experimental lab-scale copper-chlorine (Cu–Cl) cycle of hydrogen production is examined and optimized in terms of exergy efficiency and operational costs of produced hydrogen. The integrated process is modeled and simulated in Aspen Plus incorporating the reaction kinetic parameters with a sensitivity analysis of a range of operating conditions. An artificial neural network (ANN) method with machine learning is used to generate a mathematical function that is optimized based on a multi-objective genetic algorithm (MOGA) method. A sensitivity analysis of variations of each design parameter for both the objective functions and the effectiveness of exergy performance relative to operational costs of produced hydrogen is demonstrated. The sensitivity analysis and optimization results are presented and discussed.     

Prediction of selected biodiesel fuel properties using artificial neural network

Biodiesel is an alternative fuel to replace fossil-based diesel fuel. It has fuel properties similar to diesel which are generally determined experimentally. The experimental determination of various properties of biodiesel is costly, time consuming and a tedious process. To solve these problems, artificial neural network (ANN) has been considered as a vital tool for estimating the fuel properties of biodiesel, especially from its fatty acid (FA) composition. In this study, four ANNs have been designed and trained to predict the cetane number (CN), flash point (FP), kinematic viscosity (KV) and density of biodiesel using ANN with logsig and purelin transfer functions in the hidden layer of all the networks. The five most prevalent FAs from 55 feedstocks found in the literature utilized as the input parameters for the model are palmitic, stearic, oleic, linoleic and linolenic acids except for density network with a sixth parameter (temperature). Other FAs that are present in the biodiesels have been considered based on the number of carbon atom chains and the level of saturation. From this study, the prediction accuracy and the average absolute deviation of the networks are CN (96.69%; 1.637%), KV (95.80%; 1.638%), FP (99.07%; 0.997%) and density (99.40%; 0.101%). These values are reasonably better compared to previous studies on empirical correlations and ANN predictions of these fuel properties found in literature. Hence, the present study demonstrates the ability of ANN model to predict fuel properties of biodiesel with high accuracy.     

Artificial neural network modeling of nanofluid flow in a microchannel heat sink using experimental data

The present paper deals with the artificial neural network modeling (ANN) of heat transfer coefficient and Nusselt number in TiO₂/water nanofluid flow in a microchannel heat sink. The microchannel comprises of 40 channels; each channel has a length of 4 cm, a width of 500 μm, and a height of 800 μm. In the ANN modeling of heat transfer coefficient and Nusselt number 23 and 72 datasets have been used, respectively. The experimental Nusselt number has been calculated based on three different thermal conductivity models, four volume fractions of 0, 0.5, 1, and 2%, two values of Reynolds number i.e. 400 and 1200 and three different heating rates including 50.6, 60.7, and 69.1 W. Therefore, the inputs that are introduced to the neural network are volume fraction of nanoparticles, Reynolds number, heating rate, and model number while the output of network is the Nusselt number. It is elucidated that an appropriately trained network can act as a good alternative for costly and time-consuming experiments on the nanofluid flow in microchannels. The average relative errors in the prediction of Nusselt number and heat transfer coefficients were 0.3% and 0.2%, respectively.     

Application of artificial neural networks for modeling of biohydrogen production

In this study, an artificial neural network (ANN) model was developed to estimate the hydrogen production profile with time in batch studies. A back propagation artificial neural network ANN configuration of 5–6–4–1 layers was developed. The ANN inputs were the initial pH, initial substrate and biomass concentrations, temperature, and time. The model training was done using 313 data points from 26 published experiments. The correlation coefficient between the experimental and estimated hydrogen production was 0.989 for training, validating, and testing the model. Results showed that the trained ANN successfully predicted the hydrogen production profile with time for new data with a correlation coefficient of 0.976.     

A simplified model for generating sequences of global solar radiation data for isolated sites: Using artificial neural network and a library of Markov transition matrices approach

The purpose of this work is to develop a hybrid model which will be used to predict the daily global solar radiation data by combining between an artificial neural network (ANN) and a library of Markov transition matrices (MTM) approach. Developed model can generate a sequence of global solar radiation data using a minimum of input data (latitude, longitude and altitude), especially in isolated sites. A data base of daily global solar radiation data has been collected from 60 meteorological stations in Algeria during 1991–2000. Also a typical meteorological year (TMY) has been built from this database. Firstly, a neural network block has been trained based on 60 known monthly solar radiation data from the TMY. In this way, the network was trained to accept and even handle a number of unusual cases. The neural network can generate the monthly solar radiation data. Secondly, these data have been divided by corresponding extraterrestrial value in order to obtain the monthly clearness index values. Based on these monthly clearness indexes and using a library of MTM block we can generate the sequences of daily clearness indexes. Known data were subsequently used to investigate the accuracy of the prediction. Furthermore, the unknown validation data set produced very accurate prediction; with an RMSE error not exceeding 8% between the measured and predicted data. A correlation coefficient ranging from 90% and 92% have been obtained; also this model has been compared to the traditional models AR, ARMA, Markov chain, MTM and measured data. Results obtained indicate that the proposed model can successfully be used for the estimation of the daily solar radiation data for any locations in Algeria by using as input the altitude, the longitude, and the latitude. Also, the model can be generalized for any location in the world. An application of sizing PV systems in isolated sites has been applied in order to confirm the validity of this model.     

Heat transfer analysis of phase change process in a finned-tube thermal energy storage system using artificial neural network

In this study, a feed-forward back-propagation artificial neural network (ANN) algorithm is proposed for heat transfer analysis of phase change process in a finned-tube, latent heat thermal energy storage system. Heat storage through phase change material (PCM) around the finned tube is experimentally studied. A numerical study is performed to investigate the effect of fin and flow parameter by the solving governing equations for the heat transfer fluid, pipe wall and phase change material. Learning process is applied to correlate the total heat stored in different fin types of tubes, various Reynolds numbers and different inlet temperatures. A number of hidden numbers of ANN are trained for the best output prediction of the heat storage. The predicted total heat storage values obtained by an ANN model with extensive sets of non-training experimental data are then compared with experimental measurements and numerical results. The trained ANN model with an absolute mean relative error of 5.58% shows good performance to predict the total amount of heat stored. The ANN results are found to be more accurate than the numerical model results. The present study using ANN approach for heat transfer analysis in phase change heat storage process appears to be significant for practical thermal energy storage applications.     

Development of an artificial neural network model for the steam process of a coal biomass cofired combined heat and power (CHP) plant in Sweden

The development of a model for any energy system is required for proper design, operation or its monitoring. Models based on accurate mathematical expressions for physical processes are mostly useful to understand the actual operation of the plant. However, for large systems like combined heat and power (CHP) plants, such models are usually complex in nature. The estimation of output parameters using these physical models is generally time consuming, as these involve many iterative solutions. Moreover, the complete physical model for new equipment may not be available. However, artificial neural network (ANN) models, developed by training the network with data from an existing plant, may be very useful especially for systems for which the full physical model is yet to be developed. Also, such trained ANN models have a fast response with respect to corresponding physical models and are useful for real-time monitoring of the plant. In this paper, the development of an ANN model for the biomass and coal cofired CHP plant of Västhamnsverket at Helsingborg, Sweden has been reported. The feed forward with back propagation ANN model was trained with data from this plant. The developed model is found to quickly predict the performance of the plant with good accuracy.