Design and implementation of hydrogen economy using artificial neural network on field programmable gate array

In this study, economic analysis of the hydrogen generation and liquefaction system has been modeled using Multi-Layer Feed-Forward Artificial Neural Network (MLFFANN) and implemented on Field Programmable Gate Array (FPGA). Firstly, the 100X6 data set has been created to be used in the ANN-based modeling of the system using the Engineering Equation Solver (EES) program. This data set has been divided into two data sets as 80X6 for training and 20X6 for testing. The structure of the ANN-based economic analysis of hydrogen generation and liquefaction has been composed of 3 neurons in the input layer, ten neurons in the hidden layer, and three neurons in the output layer. Elliott-2-based TanSig transfer function and Purelin transfer function have been used in the neurons of the hidden layer and the output layer, respectively. Then, the ANN-model has been trained and tested using the Matlab program. The MSE values, 1.40x10E-7 and 2.07x10E-5, have been obtained as the results of the training phase and test phase of the ANN-based system, respectively. After getting fruitful results from training and testing phases, the economic analyses of hydrogen generation and liquation systems have been modeled in VHDL using bias and weight values located in the constructed ANN-based system using Matlab. The modeling has been performed in the Xilinx ISE Design Tools program using a 32-bit IEEE-754-1985 floating-point number standard. Then, the modeled ANN-based economic analysis of the hydrogen generation and liquation system has been implemented on the Xilinx Virtex-7 FPGA chip by performing the Place&Route process. The maximum operating frequency of the ANN-based hydrogen generation and liquefaction economy system implemented on FPGA has been obtained as 281.702 MHz using Xilinx ISE Design Tools.     

Thermoeconomic analysis and artificial neural network based genetic algorithm optimization of geothermal and solar energy assisted hydrogen and power generation

The study aims to optimize the geothermal and solar-assisted sustainable energy and hydrogen production system by considering the genetic algorithm. The study will be useful by integrating hydrogen as an energy storage unit to bring sustainability to smart grid systems. Using the Artificial Neural Network (ANN) based Genetic Algorithm (GA) optimization technique in the study will ensure that the system is constantly studied in the most suitable under different climatic and operating conditions, including unit product cost and the plant's power output. The water temperature of the Afyon Geothermal Power Plant varies between 70 and 130 °C, and its mass flow rate varies between 70 and 150 kg/s. In addition, the solar radiation varies between 300 and 1000 W/m² for different periods. The net power generated from the region's geothermal and solar energy-supported system is calculated as 2900 kW. If all of this produced power is used for hydrogen production in the electrolysis unit, 0.0185 kg/s hydrogen can be produced. The results indicated that the overall energy and exergy efficiencies of the integrated system are 4.97% and 16.0%, respectively. The cost of electricity generated in the combined geothermal and solar power plant is 0.027 $/kWh if the electricity is directly supplied to the grid and used. The optimized cost of hydrogen produced using the electricity produced in geothermal and solar power plants in the electrolysis unit is calculated as 1.576 $/kg H₂. The optimized unit cost of electricity produced due to hydrogen in the fuel cell is calculated as 0.091 $/kWh.     

Modeling and prediction of Turkey’s electricity consumption using Artificial Neural Networks

Artificial Neural Networks are proposed to model and predict electricity consumption of Turkey. Multi layer perceptron with backpropagation training algorithm is used as the neural network topology. Tangent-sigmoid and pure-linear transfer functions are selected in the hidden and output layer processing elements, respectively. These input–output network models are a result of relationships that exist among electricity consumption and several other socioeconomic variables. Electricity consumption is modeled as a function of economic indicators such as population, gross national product, imports and exports. It is also modeled using export–import ratio and time input only. Performance comparison among different models is made based on absolute and percentage mean square error. Electricity consumption of Turkey is predicted until 2027 using data from 1975 to 2006 along with other economic indicators. The results show that electricity consumption can be modeled using Artificial Neural Networks, and the models can be used to predict future electricity consumption.     

A novel fault diagnosis technique for photovoltaic systems based on artificial neural networks

This work proposes a novel fault diagnostic technique for photovoltaic systems based on Artificial Neural Networks (ANN). For a given set of working conditions - solar irradiance and photovoltaic (PV) module's temperature - a number of attributes such as current, voltage, and number of peaks in the current–voltage (I–V) characteristics of the PV strings are calculated using a simulation model. The simulated attributes are then compared with the ones obtained from the field measurements, leading to the identification of possible faulty operating conditions. Two different algorithms are then developed in order to isolate and identify eight different types of faults. The method has been validated using an experimental database of climatic and electrical parameters from a PV string installed at the Renewable Energy Laboratory (REL) of the University of Jijel (Algeria). The obtained results show that the proposed technique can accurately detect and classify the different faults occurring in a PV array. This work also shows the implementation of the developed method into a Field Programmable Gate Array (FPGA) using a Xilinx System Generator (XSG) and an Integrated Software Environment (ISE).     

Energy input–output analysis and application of artificial neural networks for predicting greenhouse basil production

In this study, various Artificial Neural Networks (ANNs) were developed to estimate the production yield of greenhouse basil in Iran. For this purpose, the data collected by random method from 26 greenhouses in the region during four periods of plant cultivation in 2009–2010. The total input energy and energy ratio for basil production were 14,308,998 MJ ha^?1 and 0.02, respectively. The developed ANN was a multilayer perceptron (MLP) with seven neurons in the input layer, one, two and three hidden layer(s) of various numbers of neurons and one neuron (basil yield) in the output layer. The input energies were human labor, diesel fuel, chemical fertilizers, farm yard manure, chemicals, electricity and transportation. Results showed, the ANN model having 7-20-20-1 topology can predict the yield value with higher accuracy. So, this two hidden layer topology was selected as the best model for estimating basil production of regional greenhouses with similar conditions. For the optimal model, the values of the models outputs correlated well with actual outputs, with coefficient of determination (R²) of 0.976. For this configuration, RMSE and MAE values were 0.046 and 0.035, respectively. Sensitivity analysis revealed that chemical fertilizers are the most significant parameter in the basil production.     

B-P网络隐含层对水质评价结果的影响分析

运用人工神经网络理论和方法，建立了水质评价的B－P网络模型；重点探讨了隐含层节点数的确定方法。通过对某市不同水域水质评价及多个实例的检验分析表明，隐含层节点数在一定范围内取值对水质评价结果无影响。     

The integration of parabolic trough solar collectors and evacuated tube collectors to geothermal resource for electricity and hydrogen production

In this study, electricity and hydrogen production of an integrated system with energy and exergy analyses are investigated. The system also produces clean water for the water electrolysis system. The proposed system comprises evacuated tube solar collectors (ETSCs), parabolic trough solar collectors (PTSCs), flash turbine, organic Rankine cycles (ORC), a reverse osmosis unit (RO), a water electrolysis unit (PEM), a greenhouse and a medium temperature level geothermal resource. The surface area of each collector is 500 m². The thermodynamics analysis of the integrated system is carried out under daily solar radiation for a day in August. The fluid temperature of the medium temperature level geothermal resource is upgraded by ETSCs and PTSCs to operate the flash turbine and the ORCs. The temperature of the geothermal fluid is upgraded from 130 °C to 323.6 °C by the ETSCs and PTSCs. As a result, it is found that the integrated system generates 162 kg clean water, 1215.63 g hydrogen, and total electrical energy of 2111.04 MJ. The maximum energy and exergy efficiencies of the overall system are found as 10.43% and 9.35%, respectively.     

Performance analysis and optimization of a hydrogen liquefaction system assisted by geothermal absorption precooling refrigeration cycle

The present paper deals with the hydrogen liquefaction with absorption precooling cycle assisted by geothermal water is modeled and analyzed. Uses geothermal heat in an absorption refrigeration process to precool the hydrogen gas is liquefied in a liquefaction cycle. High-temperature geothermal water using the absorption refrigeration cycle is used to decrease electricity work consumption in the gas liquefaction cycle. The thermoeconomic optimization procedure is applied using the genetic algorithm method to the hydrogen liquefaction system. The objective is to minimize the unit cost of hydrogen liquefaction of the composed system. Based on optimization calculations, hydrogen gas can be cooled down to ?30 °C in the precooling cycle. This allows the exergetic cost of hydrogen gas to be reduced to be 20.16 $/GJ (2.42 $/kg LH₂). The optimized exergetic cost of liquefied hydrogen is 4.905 $/GJ (1.349 $/kg LH₂), respectively.     

Optimum energy evaluation and life cycle cost assessment of a hydrogen liquefaction system assisted by geothermal energy

In this study, analyses of the thermodynamic performance and life cycle cost of a geothermal energy-assisted hydrogen liquefaction system were performed in a computer environment. Geothermal water at a temperature of 200 °C and a flow rate of 100 kg/s was used to produce electricity. The produced electricity was used as a work input to liquefy the hydrogen in the advanced liquefaction cycle. The net work requirement for the liquefaction cycle was calculated as 8.6 kWh/kg LH₂. The geothermal power plant was considered as the work input in the liquefaction cycle. The hydrogen could be liquefied at a mass flow rate of 0.2334 kg/s as the produced electricity was used directly to produce liquid hydrogen in the liquefaction cycle. The unit costs of electricity and liquefied hydrogen were calculated as 0.012 $/kWh and 1.44 $/kg LH₂. As a result of the life cycle cost analysis of the system, the net present value (NPV) and levelized annual cost (LAC) were calculated as 123,100,000 and 14,450,000 $/yr. The simple payback period (N_spp) and discount payback period (N_dpp) of the system were calculated as 2.9 and 3.6 years, respectively.     

Management of photovoltaic excess electricity generation via the power to hydrogen concept: A year-round dynamic assessment using Artificial Neural Networks

This paper assesses energetically and economically the power-to-hydrogen concept by exploring the excess power resulting from the mismatch between the photovoltaic (PV) generation and the electric demand of a medium-size commercial structure located in Morocco. The variability in the building electric load is considered and the power flows from the PV field to the building are predicted using Artificial Neural Networks for a time-resolution of 15 min. A MATLAB code was implemented to estimate the instantaneous hydrogen production based on a semi-empirical mathematical formulation of an Alkaline type electrolyzer with a nominal capacity of 15 kW. These combined approaches are for the first time adopted to evaluate the feasibility of integrated PV hydrogen systems under the Moroccan context. Using a set of 5 electrolyzers coupled to the 104 kW_p currently installed solar PV field, it was possible to generate about 18,622 Nm³/year of hydrogen by exploring the PV excess power. The overall efficiency of the integrated system ranged from 9.5% (in March) to 10.1% (in May). Such an approach allowed enhancing the effective efficiency and capacity factor to values of 9.873% and 26.87%, respectively compared to 6.325% and 10.163% for the base case scenario without hydrogen systems. From an economic perspective, it was found that the integrated PV-hydrogen plant engendered levelized cost of electricity and hydrogen of 12.56 c$/kWh and 21.55 $/kg, respectively.     

Potential methods for geothermal-based hydrogen production

In this study, four potential methods are identified for geothermal-based hydrogen production, namely, (i) directly from the geothermal steam, (ii) through conventional water electrolysis using the electricity generated from geothermal power plant, (iii) using both geothermal heat and electricity for high temperature steam electrolysis and/or hybrid processes, (iv) using the heat available from geothermal resource in thermochemical processes to disassociate water into hydrogen and oxygen. Here we focus on relatively low-temperature thermochemical and hybrid cycles, due to their greater application possibility, and examine them as a potential option for hydrogen production using geothermal heat. We also present a brief thermodynamic analysis to assess their performance through energy and exergy efficiencies for comparison purposes. The results show that these cycles have good potential and become attractive due to the overall system efficiencies over 50%. The copper–chlorine cycle is identified as a highly promising cycle for geothermal hydrogen production. Furthermore, three types of industrial electrolysis methods, which are generally considered for hydrogen production currently, are also discussed and compared with the above mentioned cycles.     

Investigation of hydrogen production performance of chlor-alkali cell integrated into a power generation system based on geothermal resources

In present study, hydrogen production performance of chlor-alkali cell integrated into a power generation system based on geothermal resource is studied. The basic elements of the novel system are a separator, a steam power turbine, an organic Rankine cycle (ORC), an air cooled condenser, a saturated NaCl solution reservoir tank and a chlor-alkali cell. To enhance the performance of the cell, the saturated NaCl solution is heated by the waste heat from the ORC. So, this integrated system generates significant amount of electricity for the city grid and also yields three main products those are hydrogen, chlorine and sodium hydroxide. According to the parametric study, when the temperature of a geothermal resource varies from 140 to 155 °C, the electrical power generation increases from nearly 2.5 MW to 3.9 MW and hydrogen production increases from 10.5 to 21.1 kg-h. Thus, when the geothermal resource temperature of 155 °C, the energy efficiency of the system is 6.2% and the exergetic efficiency is 22.4%. As a result, the geothermal energy potential plays a key role on the integrated system performance and the hydrogen production rate.     

Comparison of three different solar collectors integrated with geothermal source for electricity and hydrogen production

In this study, an integrated system is proposed for mainly electricity and hydrogen production. Energy and exergy analyses of the system are also examined by using Engineering Equation Solver (EES, version 2019) under solar radiation during day time on 1st July. The proposed system consists of a middle-temperature geothermal source with fluid temperature 93 °C, three solar collectors (SCs of 300 m²) namely parabolic trough solar collectors (PTSCs), evacuated tube solar collectors (ETSCs), flat plate solar collectors (FPSCs), an organic Rankine cycle (ORC), proton exchange membrane (PEM), a compressor, hot water storage tank and a mushroom cultivation room. The temperature of the geothermal fluid is upgraded via solar collectors by harvesting solar radiation to operate the ORC. Thus the generated electricity is used in the PEM electrolysis system for producing hydrogen. When the PTSCs, ETSCs, and FPSCs are integrated with the geothermal source separately, it is found that 2758.69 g, 1585.27 g, and 634.42 g of hydrogen can be produced, respectively for a day. The highest overall energetic and exergetic performance of the system is calculated as to be 5.67% and 7.49%, respectively.     

Recent advances in artificial neural network research for modeling hydrogen production processes

Artificial Neural Networks (ANN) have been widely used by scientists in a variety of energy modes (biomass, wind, solar, geothermal, and hydroelectric). This review highlights the assistance of ANN for researchers in the quest for discovering more advanced materials/processes for efficient hydrogen production (HP). The review is divided into two parts in this context. The first section briefly mentions, in terms of technologies, economy, energy consumption, and costs symmetrically outlined the advantages and disadvantages of various HP routes such as fossil fuel/biomass conversion, water electrolysis, microbial fermentation, and photocatalysis. Subsequently, ANN and ANN hybrid studies implemented in HP research were evaluated. Finally, statistics of hybrid studies with ANN are given, and future research proposals and hot research topics are briefly discussed. This research, which touches upon the types of ANNs applied to HP methods and their comparison with other modeling techniques, has an essential place in its field.     

A new solar and geothermal based integrated ammonia fuel cell system for multigeneration

In this study, a new solar and geothermal based integrated system is developed for multigeneration of electricity, fresh water, hydrogen and cooling. The system also entails a solar integrated ammonia fuel cell subsystem. Furthermore, a reverse osmosis desalination system is used for fresh water production and a proton exchange membrane based hydrogen production system is employed. Moreover, an absorption cooling system is utilized for district cooling via available system waste heat. The system designed is assessed thermodynamically through approaches of energy and exergy analyses. The overall energy efficiency is determined to be 42.3%. Also, the overall exergy efficiency is assessed, and it is found to be 21.3%. The exergy destruction rates in system components are also analysed and the absorption cooling system generator as well as geothermal flash chamber are found to have comparatively higher exergy destruction rates of 2370.2 kW and 643.3 kW, respectively. In addition, the effects of varying system parameters on the system performance are studied through a parametric analyses of the overall system and associated subsystems.     

Geothermal‐based hydrogen production using thermochemical and hybrid cycles: A review and analysis

Geothermal‐based hydrogen production, which basically uses geothermal energy for hydrogen production, appears to be an environmentally conscious and sustainable option for the countries with abundant geothermal energy resources. In this study, four potential methods are identified and proposed for geothermal‐based hydrogen production, namely: (i) direct production of hydrogen from the geothermal steam, (ii) through conventional water electrolysis using the electricity generated through geothermal power plant, (iii) by using both geothermal heat and electricity for high temperature steam electrolysis and/or hybrid processes, and (iv) by using the heat available from geothermal resource in thermochemical processes. Nowadays, most researches are focused on high‐temperature electrolysis and thermochemical processes. Here we essentially discuss some potential low‐temperature thermochemical and hybrid cycles for geothermal‐based hydrogen production, due to their wider practicality, and examine them as a sustainable option for hydrogen production using geothermal heat. We also assess their thermodynamic performance through energy and exergy efficiencies. The results show that these cycles have good potential and attractive overall system efficiencies over 50% based on a complete reaction approach. The copper‐chlorine cycle is identified as a highly promising cycle for geothermal‐hydrogen production. Copyright © 2009 John Wiley & Sons, Ltd.     

Performance evaluation of an integrated hydrogen production system with LNG cold energy utilization

This study aims to develop a novel integrated geothermal based system by the application of different thermodynamic cycles such as Kalina, liquefied natural gas (LNG), Stirling and proton exchange membrane electrolyzer (PEME) to produce cooling, hydrogen, and electricity. Energy and exergy analyses of the system are performed to evaluate the performance of the system. Additionally, the effects of five different input variables are investigated to determine their impacts on the corresponding values of net power and cooling, exergy efficiency, hydrogen production, and sustainability index. In a defined condition, the exergy efficiency of the suggested system is computed around 43%. The cycle net generated power is 10.69 MW, which is the generated power by the Stirling, LNG, and Kalina turbines each by 8.07 MW, 1.13 MW, and 1.49 MW, respectively. The produced cooling load by the cooling unit of the LNG stream is also 6.09 MW, while the rate of hydrogen production in the electrolyzer is 204.77 kg/h by consuming all the generated power. Additionally, a sensitivity analysis is performed to study the effects of each design parameters on the system performance.     

Assessment of power and hydrogen production performance of an integrated system based on middle-grade geothermal source and solar energy

In this study, power and hydrogen production performance of an integrated system is investigated. The system consists of an organic Rankine cycle (ORC), parabolic trough solar collectors (PTSCs) having a surface area of 545 m², middle-grade geothermal source (MGGS), cooling tower and proton exchange membrane (PEM). The final product of this system is hydrogen that produced via PEM. For this purpose, the fluid temperature of the geothermal source is upgraded by the solar collectors to drive the ORC. To improve the electricity generation efficiency, four working fluids namely n-butane, n-pentane, n-hexane, and cyclohexane are tried in the ORC. The mass flow rate of each working fluid is set as 0.1, 0.2, 0.3, 0.4 kg/s and calculations are made for 16 different situations (four types of working fluids and four different mass flow rates for each). As a result, n-butane with a mass flow rate of 0.4 kg/s is found to be the best option. The average electricity generation is 66.02 kW between the hours of 11⁰⁰-13⁰⁰. The total hydrogen production is 9807.1 g for a day. The energy and exergy efficiency is calculated to be 5.85% and 8.27%, respectively.     

Hybrid systems to address seasonal mismatches between electricity production and demand in nuclear renewable electrical grids

A strategy to enable zero-carbon variable electricity production with full utilization of renewable and nuclear energy sources has been developed. Wind and solar systems send electricity to the grid. Nuclear plants operate at full capacity with variable steam to turbines to match electricity demand with production (renewables and nuclear). Excess steam at times of low electricity prices and electricity demand go to hybrid fuel production and storage systems. The characteristic of these hybrid technologies is that the economic penalties for variable nuclear steam inputs are small. Three hybrid systems were identified that could be deployed at the required scale. The first option is the gigawatt-year hourly-to-seasonal heat storage system where excess steam from the nuclear plant is used to heat rock a kilometer underground to create an artificial geothermal heat source. The heat source produces electricity on demand using geothermal technology. The second option uses steam from the nuclear plant and electricity from the grid with high-temperature electrolysis (HTR) cells to produce hydrogen and oxygen. Hydrogen is primarily for industrial applications; however, the HTE can be operated in reverse using hydrogen for peak electricity production. The third option uses variable steam and electricity for shale oil production.     

Economics of hydrogen production and liquefaction by geothermal energy

Seven models are considered for the production and liquefaction of hydrogen by geothermal energy. In these models, we use electrolysis and high-temperature steam electrolysis processes for hydrogen production, a binary power plant for geothermal power production, and a pre-cooled Linde–Hampson cycle for hydrogen liquefaction. Also, an absorption cooling system is used for the pre-cooling of hydrogen before the liquefaction process. A methodology is developed for the economic analysis of the models. It is estimated that the cost of hydrogen production and liquefaction ranges between 0.979 $/kg H₂ and 2.615 $/kg H₂ depending on the model. The effect of geothermal water temperature on the cost of hydrogen production and liquefaction is investigated. The results show that the cost of hydrogen production and liquefaction decreases as the geothermal water temperature increases. Also, capital costs for the models involving hydrogen liquefaction are greater than those for the models involving hydrogen production only.