Exergy analysis of an ejector-absorption heat transformer using artificial neural network approach

This paper proposes artificial neural networks (ANNs) technique as a new approach to determine the exergy losses of an ejector-absorption heat transformer (EAHT). Thermodynamic analysis of the EAHT is too complex due to complex differential equations and complex simulations programs. ANN technique facilitates these complicated situations. This study is considered to be helpful in predicting the exergetic performance of components of an EAHT prior to its setting up in a thermal system where the working temperatures are known. The best approach was investigated using different algorithms with developed software. The best statistical coefficient of multiple determinations (R²-value) for training data equals to 0.999715, 0.995627, 0.999497, and 0.997648 obtained by different algorithms with seven neurons for the non-dimensional exergy losses of evaporator, generator, absorber and condenser, respectively. Similarly these values for testing data are 0.999774, 0.994039, 0.999613 and 0.99938, respectively. The results show that this approach has the advantages of computational speed, low cost for feasibility, rapid turnaround, which is especially important during iterative design phases, and easy of design by operators with little technical experience.     

Optimal COP prediction of a solar intermittent refrigeration system for ice production by means of direct and inverse artificial neural networks

A direct and inverse artificial neural network (ANN and ANNi) approach were developed to predict the required coefficient of performance (COP) of a solar intermittent refrigeration system for ice production under various experimental conditions. Ammonia/lithium nitrate was used as a working fluid considering different solution concentrations. The configuration 6-6-1 (6 inputs, 6 hidden and 1 output neurons) presented an excellent agreement (R > 0.986) between experimental and simulated values. The used inputs parameters were: the solution concentration, the cooling water temperature, the generation temperature, the ambient temperature, the generation pressure and the solar radiation. The sensitivity analysis showed that all studied input variables have effect on the COP prediction but the generation pressure is the most influential parameter on the COP, while the rest of input parameters were less significant. COP performance was also determined by inverting ANN to calculate the unknown input parameter from a required COP. Because of the high accuracy and short computing time makes this methodology useful to simulate and to optimize the solar refrigerator system.     

Exergy analysis of a heat transformer for water purification increasing heat source temperature

In the present study, the first and second laws of thermodynamic have been used to analyse in detail the performance of a heat transformer used for water purification. The heat delivered in the auxiliary condenser is recycled into the system increasing the heat source temperatures and therefore the coefficient of performance (COP) and the exergy coefficient of performance (ECOP). Plots of COP, ECOP, the improvement potential (IP) and the cycle irreversibility (I_CYCLE) are shown against the main operating temperatures of the system, the gross temperature lift (GTL), the flow ratio (FR) and the effectiveness of the economiser (EF_EC). In order to found the components of the system with the highest irreversibilities, plots of the irreversibilities for each one of the main components of the system are reported against the main temperatures and operating parameters of the heat transformer. The results showed that the highest irreversibilities occurred in the absorber contributing with more than the 30% of the irreversibilities of the entire system, followed by the auxiliary condenser with about the 25%. The lowest irreversibilities were found in the pumps which are almost negligible and in the economiser which were in general lower than 5%.     

Energy and exergy analysis of an experimental single‐stage heat transformer operating with the water/lithium bromide mixture

The first and second law of thermodynamics have been used to analyze the performance of an experimental single‐stage heat transformer operating with the water/lithium bromide mixture. Enthalpy coefficients of performance (COP), external coefficients of performance (COP_EXT), exergy coefficient of performance (ECOP), exergy destruction or irreversibility in the system and components (I) and the improvement potential (Pot) have been calculated against the gross temperature lift and the main operating temperatures of the system. The results showed that the highest COP, COP_EXT and ECOP values are obtained at the highest solution concentrations meanwhile the Pot and the I of the cycle remain almost constant against these parameters. Also it was shown that the COP, COP_EXT and ECOP decrease with an increase with the absorber temperature, meanwhile the Pot and the I increase. Moreover, it was observed that in all the cases independently of the operating temperatures of the system, the absorber accounts with most of the half of the total irreversibility in the system. Finally, it was shown that the improvement potential is considerable for the system. Copyright © 2009 John Wiley & Sons, Ltd.     

Energy and exergy analysis of a double absorption heat transformer operating with water/lithium bromide

In the present study, the first and second law of thermodynamics have been used to analyze in detail the performance of a double absorption (lift) heat transformer operating with the water–lithium bromide mixture. A mathematical model was developed to estimate the coefficient of performance (COP), the exergy coefficient of performance (ECOP), the total exergy destruction in the system (Ψ_TD) and the exergy destruction (Ψ_D) in each one of the main components, as a function of the system temperatures, the efficiency of the economizer (EF_EC), the gross temperature lift and flow ratio (FR). The results showed that the generator is the component with the highest irreversibilities or exergy destruction contributing to about 40% of the total exergy destruction in the whole system, reason why this component should be carefully designed and optimized. The results also showed that the COP and ECOP increase with increase in the generator, the evaporator and the absorber–evaporator temperatures and decrease with the absorber and condenser temperatures. Finally, it was observed that the COP and ECOP are very dependent of the FR and the economizer efficiency (EF_EC) values. Also the optimum operating region of the analyzed system is shown in the present study. Copyright © 2009 John Wiley & Sons, Ltd.     

Exergy analysis of double effect vapor absorption refrigeration system

Energy and exergy analyses previously performed by the authors for a single effect absorption refrigeration system have been extended to double effect vapor absorption refrigeration system with the expectation of reducing energy supply as well as an interest in the diversification of the motive power employed by HVAC technologies. The total exergy destruction in the system as a percentage of the exergy input from a generator heating water over a range of operating temperatures is examined for a system operating on LiBr–H₂O solution. The exergy destruction in each component, the coefficient of performance (COP) and the exergetic COP of the system are determined. It is shown that exergy destructions occur significantly in generators, absorbers, evaporator2 and heat exchangers while the exergy destructions in condenser1, evaporator1, throttling valves, and expansion valves are relatively smaller within the range of 1–5%. The results further indicate that with an increase in the generator1 temperature the COP and ECOP increase, but there is a significant reduction in total exergy destruction of the system for the same. On the other hand, the COP and ECOP decrease with an increase in the absorber1 temperature while the total exergy destruction of the system increases significantly with a small increase in the absorber1 temperature. The results show that the exergy method can be used as an effective criterion in designing an irreversible double effect absorption refrigeration system and may be a good tool for the determination of the optimum working conditions of such systems. Copyright © 2007 John Wiley & Sons, Ltd.     

Performance analysis of single-stage refrigeration system with internal heat exchanger using neural network and neuro-fuzzy

In this study, artificial neural networks (ANNs) and adaptive neuro-fuzzy (ANFIS) have been used for performance analysis of single-stage vapour compression refrigeration system with internal heat exchanger using refrigerants R134a, R404a, R407c which do not damage to ozone layer. It is well known that the evaporator temperature, condenser temperature, subcooling temperature, superheating temperature and cooling capacity affect the coefficient of performance (COP) of single-stage vapour compression refrigeration system with internal heat exchanger. In this study, COP is estimated depending on the above temperatures and cooling capacity values. The results of ANN are compared with ANFIS in which the same data sets are used. ANN model is slightly better than ANFIS for R134a whereas ANFIS model is slightly better than ANN for R404a and R407c. In addition, new formulations obtained from ANN for three refrigerants are presented for the calculation of the COP. The R² values obtained when unknown data were used to the networks were 1, 0.999998 and 0.999998 for the R134a, R404a and R407c respectively which is very satisfactory.     

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.     

Daily means ambient temperature prediction using artificial neural network method: A case study of Turkey

The objective of this paper is to develop an artificial neural network (ANN) model which can be used to predict daily mean ambient temperatures in Denizli, south-western Turkey. In order to train the model, temperature values, measured by The Turkish State Meteorological Service over three years (2003–2005) were used as training data and the values of 2006 were used as testing data.In order to determine the optimal network architecture, various network architectures were designed; different training algorithms were used; the number of neuron and hidden layer and transfer functions in the hidden layer/output layer were changed. The predictions were performed by taking different number of hidden layer neurons between 3 and 30. The best result was obtained when the number of the neurons is 6. The selected ANN model of a multi-layer consists of 3 inputs, 6 hidden neurons and 1 output. Training of the network was performed by using Levenberg–Marquardt (LM) feed-forward backpropagation algorithms. A computer program was performed under Matlab 6.5 software. For each network, fraction of variance (R²) and root-mean squared error (RMSE) values were calculated and compared. The results show that the ANN approach is a reliable model for ambient temperature prediction.     

Artificial neural network analysis of heat pumps using refrigerant mixtures

In this study, we have investigated the performance of a vapor compression heat pump with different ratios of R12/R22 refrigerant mixtures using artificial neural networks (ANN). Experimental studies were completed to obtain training and test data. Mixing ratio, evaporator inlet temperature and condenser pressure were used as input layer, while the outputs are coefficient of performance (COP) and rational efficiency (RE). The back propagation learning algorithm with three different variants and logistic sigmoid transfer function were used in the network. It is shown that the R² values are about 0.9999 and the RMS errors are smaller than 0.006. With these results, we believe that the ANN can be used for prediction of COP and RE as an accurate method in a heat pump.     

Artificial neural networks for automotive air-conditioning systems performance prediction

In this study, ANN model for a standard air-conditioning system for a passenger car was developed to predict the cooling capacity, compressor power input and the coefficient of performance (COP) of the automotive air-conditioning (AAC) system. This paper describes the development of an experimental rig for generating the required data. The experimental rig was operated at steady-state conditions while varying the compressor speed, air temperature at evaporator inlet, air temperature at condenser inlet and air velocity at evaporator inlet. Using these data, the network using Lavenberg–Marquardt (LM) variant was optimized for 4–3–3 (neurons in input–hidden–output layers) configuration. The developed ANN model for the AAC system shows good performance with an error index in the range of 0.65–1.65%, mean square error (MSE) between 1.09 × 10^?5 and 9.05 × 10^?5 and the root mean square error (RMSE) in the range of 0.33–0.95%. Moreover, the correlation which relates the predicted outputs of the ANN model to the experimental results has a high coefficient in predicting the AAC system performance.     

Comprehensive performance analysis and optimization of 1,3-dimethylimidazolylium dimethylphosphate-water binary mixture for a single effect absorption refrigeration system

The energy and exergy analyses of the absorption refrigeration system (ARS) using H₂O-[mmim][DMP] mixture were investigated for a wide range of temperature. The equilibrium Dühring (P-T-X_IL) and enthalpy (h-T-X_IL) of mixture were assessed using the excess Gibbs free non-random two liquid (NRTL) model for a temperature range of 20°C to 140°C and X_IL from 0.1 to 0.9. The performance validation of the ARS cycle showed a better coefficient of performance (COP) of 0.834 for H₂O-[mmim][DMP] in comparison to NH₃-H₂O, H₂O-LiBr, H₂O-[emim][DMP], and H₂O-[emim][BF4]. Further, ARS performances with various operating temperatures of the absorber (T_a), condenser (T_c), generator (T_g), and evaporator (T_e) were simulated and optimized for a maximum COP and exergetic COP (ECOP). The effects of T_g from 50°C to 150°C and T_a and T_c from 30°C to 50°C on COP and ECOP, the X_a, X_g, and circulation ratio (CR) of the ARS were evaluated and optimized for T_e from 5°C to 15°C. The optimization revealed that T_g needed to achieve a maximum COP which was more than that for a maximum ECOP. Therefore, this investigation provides criteria to select low grade heat source temperature. Most of the series flow of the cases of cooling water from the condenser to the absorber was found to be better than the absorber to the condenser.     

Performance prediction of a direct expansion solar assisted heat pump using artificial neural networks

This paper presents the suitability of artificial neural network (ANN) to predict the performance of a direct expansion solar assisted heat pump (DXSAHP). The experiments were performed under the meteorological conditions of Calicut city (latitude of 11.15 °N, longitude of 75.49 °E) in India. The performance parameters such as power consumption, heating capacity, energy performance ratio and compressor discharge temperature of a DXSAHP obtained from the experimentation at different solar intensities and ambient temperatures are used as training data for the network. The back propagation learning algorithm with three different variants (such as, Lavenberg–Marguardt (LM), scaled conjugate gradient (SCG) and Pola-Ribiere conjugate gradient (CGP)) and logistic sigmoid transfer function were used in the network. The results showed that LM with 10 neurons in the hidden layer is the most suitable algorithm with maximum correlation coefficients (R²) of 0.999, minimum root mean square (RMS) value and low coefficient of variance (COV). The reported results conformed that the use of ANN for performance prediction of DXSAHP is acceptable.     

Ecological coefficient of performance analysis and optimization of an irreversible regenerative-Brayton heat engine

In this paper, a performance optimization based on the ecological coefficient of performance (ECOP) criterion has been carried out for an irreversible regenerative Brayton heat-engine. The results obtained were compared with those using the power-output criterion and alternative ecological performance objective-function defined in the literature. The design parameters, under the optimal conditions, have been derived analytically and their effects on the engine’s performance have been discussed. It is shown that, for the regenerative Brayton-engine, a design based on the maximum ECOP conditions is more advantageous from the point-of-view of entropy generation rate, thermal efficiency and investment cost.     

Wind power forecast using neural networks: Tuning with optimization techniques and error analysis

The increased integration of wind power into the power system implies many challenges to the network operators, mainly due to the hard to predict and variability of wind power generation. Thus, an accurate wind power forecast is imperative for systems operators, aiming at an efficient and economical wind power operation and integration into the power system. This work addresses the issue of forecasting short‐term wind speed and wind power for 1 hour ahead, combining artificial neural networks (ANNs) with optimization techniques on real historical wind speed and wind power data. Levenberg‐Marquardt (LM) and particle swarm optimization (PSO) are used as training algorithms to update the weights and bias of the ANN applied to wind speed predictions. The forecasting performance produced by the proposed models are compared with each other, as well as with the benchmark persistence model. Test results show higher performance for ANN‐LM wind speed forecasting model, outperforming both ANN‐PSO and persistence. The application of ANN‐LM to wind power forecast revealed also a good performance, with an average improvement of 2.8% in relation to persistence. An innovative analysis of mean absolute percentage error (MAPE) behaviour in time and in typical days is finally offered in the paper.     

Use of artificial neural networks for mapping of solar potential in Turkey

Turkey has sufficient solar radiation intensities and radiation durations for solar thermal applications since Turkey lies in a sunny belt, between 36° and 42° N latitudes. The yearly average solar-radiation is 3.6 kWh/m²day, and the total yearly radiation period is ∼2610 h. The main focus of this study is to determine the solar-energy potential in Turkey using artificial neural-networks (ANNs). Scaled conjugate gradient (SCG), Pola-Ribiere conjugate gradient (CGP), and Levenberg-Marquardt (LM) learning algorithms and a logistic sigmoid transfer function were used in the network. In order to train the neural network, meteorological data for the last 3 years (2000–2002) from 17 stations (namely cities) spread over Turkey were used as training (11 stations) and testing (6 stations) data. Meteorological and geographical data (latitude, longitude, altitude, month, mean sunshine duration, and mean temperature) are used as inputs to the network. Solar radiation is in the output layer. The maximum mean absolute percentage error was found to be less than 6.7% and R² values to be about 99.8937% for the testing stations. However, the respective values were found to be 2.41 and 99.99658% for the training stations. The trained and tested ANN models show greater accuracies for evaluating solar resource posibilities in regions where a network of monitoring stations has not been established in Turkey. The predicted solar-potential values from the ANN were given in the form of monthly maps. These maps are of prime importance for different working disciplines, like those of scientists, architects, meteorologists, and solar engineers in Turkey. The predictions from ANN models could enable scientists to locate and design solar-energy systems in Turkey and determine the appropriate solar technology.     

Performance improvement of absorption refrigeration system using triple-pressure-level

In the absorption refrigeration system (ARS) working with aqua–ammonia, the ejector is commonly located at the condenser inlet. In this study, the ejector was located at the absorber inlet. Therefore, the absorber pressure becomes higher than the evaporator pressure and the system works with triple-pressure-level. The ejector has two main functions: (i) aiding pressure recovery from the evaporator, (ii) upgrading the mixing process and the pre-absorption by the weak solution of the ammonia coming from the evaporator. In addition to these functions, it can also act to lower the refrigeration and heat-source temperatures. Energy analyses show that the system’s coefficient of performance (COP) and exergetic coefficient of performance (ECOP) were improved by 49% and 56%, respectively and the circulation ratio (f) was reduced by 57% when ARS is initiated at lower generator temperatures. Due to the reduced circulation ratio, the system dimensions can be reduced; consequently, this decreases overall cost. The heat source and refrigeration temperatures decreased in the range of 5–15 °C and 1–3 °C, respectively. Exergy analyses show that the exergy loss of the absorber of ARS with ejector had a higher exergy loss than those of the other components. Therefore, a multiple compartment absorber can be proposed to reduce the exergy loss of the absorber of ARS with ejector.     

Error propagation on COP prediction by artificial neural network in a water purification system integrated to an absorption heat transformer

Numerous authors have reported heat transfer prediction using artificial neural network (ANN). However, the precision or accuracy of the calculation is generally unknown. Error propagation from Monte Carlo method is applied to the coefficient of performance (COP) predicted by ANN. This COP permitted us to evaluate a water purification process integrated into a heat transformer. A feedforward network with a hidden layer was used in order to obtain error propagation in COP prediction. This model used the input and output-temperatures for each component (absorber, generator, evaporator, and condenser), as well as two pressure parameters from the absorption heat transformer and LiBr + H₂O mixture with different LiBr concentrations. The hyperbolic tangent sigmoid transfer-function and the linear transfer-function were used for the network. A new correlation for calculating relative standard deviation (%RSD_COP) of COP as a function of COP_EXP and %RSD_instrument was obtained. This study shows that %RSD_COP of ANN prediction decreased when the experimental COP is increased. The range of COP operations was from 0.21 to 0.39.     

Performance assessment of hybrid desiccant cooling system at various climates

In our work, operation of hybrid desiccant cooling system (HDCS) has been investigated based on experimental studies. Different climates have been created by changing the temperature and humidity of HDCS inlet air, using an electrical heater and a centrifuge humidifier. Input energies, temperature of various points, and their relative humidity have been measured at the created climates. Coefficient of performance (COP), thermal coefficient of performance, and electrical coefficient of performance (ECOP) of the HDCS have been calculated. As a reference situation, vapor compression system (VCS) was examined at the same condition as HDCS. Results show that COP of HDCS in comparison with VCS decreased about 36% and 28% in hot-dry and hot-humid climates, respectively, which is due to the thermal energy consumption in HDCS. In contrast its ECOP increased, which means that by using HDCS some electrical energy would be saved. Defining operating cost index (OCI) parameter, operation costs of VCS and HDCS have been compared. Analyzing the OCI results shows that in HDCS, although decreasing the electricity consumption results in more usage of natural gas, these systems are economical especially in those countries with low natural gas prices.     

Effects of variation in working fluids and operating conditions on the performance of a thermoacoustic refrigerator

This study reports on a numerical investigation of the effects of variation in working fluids and operating conditions on the performance of a thermoacoustic refrigerator. The performance of a thermoacoustic refrigerator is evaluated based on the cooling power, coefficient of performance (COP), and the entropy generation rate within the device. The effect of the variation of the working fluid is observed by changing the Prandtl number (Pr) between 0.7 and 0.28. The operating conditions investigated are drive ratio (DR), stack plate spacing (y₀), and mean pressure (p_m). The present research shows that lowering the Pr of the working fluid does not improve the performance of a thermoacoustic refrigerator for all of the selected operating conditions. COP increases 78% by reducing the Pr from 0.7 to 0.28 at y₀ = 3.33δ_k, at atmospheric pressure and a DR of 1.7%. While the COP decreases by reducing the Pr from 0.7 to 0.28 at y₀ = 1.0δ_k, at atmospheric pressure, and a DR of 1.7%. The results are compared with the available experimental data and found good agreement.