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.     

Model of a total momentum filtered energy selective electron heat pump affected by heat leakage and its performance characteristics

A total momentum filtered energy selective electron (ESE) heat pump model with heat leakage is established in this paper. The analytical expressions of heating load and coefficient of performance (COP) for both the total momentum filtered (k_r-filtered) ESE heat pump and the conventionally filtered (k_x-filtered) ESE heat pump in which the electrons are transmitted according to the momentum in the direction of transport only are derived, respectively. The optimal performance of the k_r-filtered ESE heat pump is analyzed by using the theory of finite time thermodynamics (FTT). The optimal regions of COP and heating load for the k_r-filtered heat pump are obtained. By comparing the performance of the k_r-filtered device with that of the k_x-filtered device, it is found that the heating load performance and the COP versus heating load characteristic curves of the k_r-filtered heat pump are totally different from those of the k_x-filtered device; and the maximum COP and maximum heating load of the k_r-filtered device are generally higher than those of the k_x-filtered device. The influences of heat leakage, resonance width, hot reservoir temperature and chemical potential on the performance of the total momentum filtered ESE heat pump are further analyzed by numerical calculations. The obtained results can provide some theoretical guidelines for the design of practical electron systems such as solid-state thermionic heat pump devices.     

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.     

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.     

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 comparison of CFCs with their substitutes using artificial neural network

In order to decrease global pollution due to chlorofluorocarbons (CFCs), the usage of HFC‐ and HC‐based refrigerants and their mixtures are considered instead of CFCs (R12, R22, and R502). This was confirmed by an international consensus (i.e. Montreal Protocol signed in 1987). This paper offers to determine coefficient of performance (COP) and total irreversibility (TI) values of vapour‐compression refrigeration system with different refrigerants and their mixtures mentioned above using artificial neural networks (ANN). In order to train the network, COPs and TIs of refrigerants and their some binary, ternary and quartet mixtures of different ratios have been calculated in a vapour‐compression refrigeration system with liquid/suction line heat exchanger. In the calculations thermodynamic properties of refrigerants have been taken from REFPROP 6.01 which was prepared based on Helmholtz energy equation of state. To achieve this, a new software has been written in FORTRAN programming language using sub‐programs of REFPROP, and all related calculations have been performed using this software using constant temperature method as reference. Scaled conjugate gradient, Pola–Ribiere conjugate gradient, and Levenberg–Marquardt learning algorithms and logistic sigmoid transfer function were used in the network. Mixing ratios of refrigerants, and evaporator temperature were used as input layer; COP and TI values were used as output layer. It is shown that R² values are about 0.9999, maximum errors for training and test data are smaller than 2 and 3%, respectively. It is concluded that, ANNs can be used for prediction of COP and TI as an accurate method in the systems. Copyright © 2004 John Wiley & Sons, Ltd.     

Exergetic performance evaluation of heat pump systems having various heat sources

In this study heat pump systems having different heat sources were investigated experimentally. Solar‐assisted heat pump (SAHP), ground source heat pump (GSHP) and air source heat pump (ASHP) systems for domestic heating were tested. Additionally, their combination systems, such as solar‐assisted‐ground source heat pump (SAGSHP), solar‐assisted‐air source heat pump (SAASHP) and ground–air source heat pump (GSASHP) were tested. All the heat pump systems were designed and constructed in a test room with 60 m² floor area in Firat University, Elazig (38.41°N, 39.14°E), Turkey. In evaluating the efficiency of heat pump systems, the most commonly used measure is the energy or the first law efficiency, which is modified to a coefficient of performance for heat pump systems. However, for indicating the possibilities for thermodynamic improvement, inadequate energy analysis and exergy analysis are needed. This study presents an exergetic evaluation of SAHP, GSHP and ASHP and their combination systems. The exergy losses in each of the components of the heat pump systems are determined for average values of experimentally measured parameters. Exergy efficiency in each of the components of the heat pump systems is also determined to assess their performances. The coefficient of performance (COP) of the SAHP, GSHP and ASHP were obtained as 2.95, 2.44 and 2.33, whereas the exergy losses of the refrigerant subsystems were found to be 1.342, 1.705 and 1.942 kW, respectively. The COP of SAGSHP, SAASHP and GSASHP as multiple source heat pump systems were also determined to be 3.36, 2.90 and 2.14, whereas the exergy losses of the refrigerant subsystems were approximately 2.13, 2.996 and 3.113 kW, respectively. In addition, multiple source heat pump systems were compared with single source heat pump systems on the basis of the COP. Exergetic performance coefficient (EPC) is introduced and is applied to the heat pump systems having various heat sources. The results imply that the functional forms of the EPC and first law efficiency are different. Results show that Ex_loss,total becomes a minimum value when EPC has a maximum value. Copyright © 2008 John Wiley & Sons, Ltd.     

Modeling of a mechanical cooling system with variable cooling capacity by using artificial neural network

Capacity modification in mechanical cooling systems can be performed by various methods. Changing condenser temperature also changes the capacity of the cooling system. In this study, a series of experiments were performed in order to determine the effects of changing cooling water flow rate (changing condenser temperature) in a mechanical heat pump experimental setup on the cooling capacity of the system. Power consumption, thermal efficiency, coefficient of performance (COP) of the system in various cooling capacities were estimated theoretically by using the data acquired from the experiments performed. Performance values obtained were used for training Artificial neural network (ANN) whose structure was designed for this operation. The Network, which has three layers as input, output, and hidden layer, has one input and four output cells. Six cells were used in hidden layers. Training was continued until the square error became (ε ⩽ 0.005) in this ANN, for which back propagation algorithm was used for training. Desired error value was achieved in ANN and, ANN was tested with both data used for training ANN and data not used. Resultant low relative error value of the test indicates the usability of ANNs in this area.     

Exergoeconomic performance of an endoreversible Carnot heat pump with complex heat transfer law

The finite-time exergoeconomic performance of an endoreversible Carnot heat pump with a complex heat transfer law, including generalized convective heat transfer law and generalized radiative heat transfer law q∝ (Δ T ⁿ ) ^m , is investigated in this paper. The focus of this paper is to obtain the compromised optimization between economics (profit) and the energy utilization factor (coefficient of performance, COP) for the endoreversible Carnot heat pump, by searching the optimum COP at maximum profit, which is termed as the finite-time exergoeconomic performance bound. The obtained results include those obtained in much of the literature and can provide some theoretical guidance for the design of practical heat pumps.     

Neural networks—a new approach to model vapour‐compression heat pumps

The aim of this paper is to model the steady‐state performance of a vapour‐compression liquid heat pump with the use of neural networks. The model uses a generalized radial basis function (GRBF) neural network. Its input vector consists only of parameters that are easily measurable, i.e. the chilled water outlet temperature from the evaporator, the cooling water inlet temperature to the condenser and the evaporator capacity. The model then predicts relevant performance parameters of the heat pump, especially the coefficient of performance (COP). Models are developed for three different refrigerants, namely LPG, R22 and R290. It is found that not every model achieves the same accuracy. Predicted COP values, when LPG or R22 are used as refrigerant, are usually accurate to within 2 per cent, whereas many predictions for R290 deviate more than ±10 per cent. Copyright © 2001 John Wiley & Sons, Ltd.     

Heat pump assisted distillation. III: Experimental studies using an external heat pump

An experimental study has been carried out on a continuously operated pilot fractional distillation column equipped with an external heat pump. The distillation column was a 15 cm diameter glass unit containing eleven single bubble cap plates. A methanol-water mixture was fed to the column and the heat pump working fluid was R114. The actual coefficient of performance (COP)_A of the heat pump increased with an increase in the mass flow rate of the working fluid. A maximum (COP)_A value of 4–3 was obtained with a gross temperature lift of 41–3°C. The performance of two reciprocating compressors was compared. The experiments have shown that continuous heat pump assisted distillation using an external working fluid can greatly reduce the energy used in a distillation process. No control problems were encountered in the experiments.     

Experimental investigation of a vapor compression heat pump used for cooling and heating applications

The present work aims at evaluating the performance characteristics of a vapor compression heat pump (VCHP) for simultaneous space cooling (summer air conditioning) and hot water supply. In order to achieve this objective, a test facility was developed and experiments were performed over a wide range of evaporator water inlet temperature (14:26 °C) and condenser water inlet temperature (22:34 °C). R134a was used as a primary working fluid whereas water was adopted as a secondary heat transfer fluid at both heat source (evaporator) and heat sink (condenser) of the heat pump. Performance characteristics of the considered heat pump were characterized by outlet water temperatures, water side capacities and coefficient of performance (COP) for various operating modes namely: cooling, heating and simultaneous cooling and heating. Results showed that COP increases with the evaporator water inlet temperature while decreases as the condenser water inlet temperature increases. However, the evaporator water inlet temperature has more effect on the performance characteristics of the heat pump than that of condenser water inlet temperature. Actual COP of cooling mode between 1.9 to 3.1 and that of heating mode from 2.9 to 3.3 were obtained. Actual simultaneous COP between 3.7 and 4.9 was achieved.     

Thermodynamic analysis of absorption systems using artificial neural network

Thermodynamic analysis of absorption systems is a very complex process, mainly because of the limited experimental data and analytical functions required for calculating the thermodynamic properties of fluid pairs, which usually involves the solution of complex differential equations. In order to simplify this complex process, Artificial Neural Networks (ANNs) are used. In this study, ANNs are used as a new approach for the determination of the thermodynamic properties of LiBr–water and LiCl–water solutions which have been the most widely used in the absorption heat pump systems. Instead of complex differential equations and limited experimental data, faster and simpler solutions were obtained by using equations derived from the ANN model. It was found that the coefficient of multiple determination (R²-value) between the actual and ANN predicted data is equal to about 0.999 for the enthalpy of both LiBr–water and LiCl–water solutions. As seen from the results obtained, the calculated thermodynamic properties are obviously within acceptable limits. In addition, the coefficient of performance (COP) of absorption systems operating under different conditions with LiBr–water and LiCl–water solutions is calculated. The use of the derived equations, which can be employed with any programming language or spreadsheet program for the estimation of the enthalpy of the solutions, as described in this paper, may make the use of dedicated ANN software unnecessary.     

Performance parameters of an ejector-absorption heat transformer

Ejector-absorption heat transformers (EAHTs) are attractive for increasing a solar-pond's temperature and for recovering low-level waste-heat. Thermodynamic analysis of the performance of an EAHT is complicated due to the associated complex differential equations and simulation programs. This paper proposes the use of artificial neural-networks (ANNs) as a new approach to determine the performance parameters, as functions of only the working temperatures of the EAHT, which is used to increase the solar pond's temperature under various working conditions. Thus, this study is helpful in predicting the performance of an EAHT where the temperatures are known. Scaled conjugate gradient (SCG) and Levenberg–Marquardt (LM) learning algorithms and a logistic sigmoid transfer-function were used in the network. The best approach was investigated for performance parameters with developed software using various algorithms. The best statistical coefficients of multiple determinations (R²-values) equal 0.99995, 0.99997 and 0.99995 for the coefficient of performance (COP), exergetic coefficient of performance (ECOP) and circulation ratio (F), respectively obtained by the LM algorithm with seven neurons. In the comparison of performances, results obtained via analytic equations and by means of the ANN, the COP, ECOP and F for all working situations differ by less than 1.05%, 0.7% and 3.07%, respectively. These accuracies are acceptable in the design of the EAHT. The ANN approach greatly reduces the time required by design engineers to find the optimum solution. Apart from reducing the time required, it is possible to find solutions that make solar-energy applications more viable and thus more attractive to potential users. Also, this approach has the advantages of high computational speed, low cost for feasibility, rapid turn-around, which is especially important during iterative design phases, and ease of design by operators with little technical experience.     

Experimental performance evaluation of a closed‐loop vertical ground source heat pump in the heating mode using energy analysis method

An experimental study is performed to determine the performance of a ground source heat pump (GSHP) system in the heating mode in the city of Erzurum, Turkey. The GSHP system using R‐134a as refrigerant has a single U‐tube ground heat exchanger (GHE) made of polyethylene pipe with a 16 mm inside diameter. The GHE was placed in a vertical borehole with 55 m depth and 203.2 mm diameter. The average coefficients of performance (COP) of the GSHP system and heat pump in heating mode are calculated as 2.09 and 2.57, respectively. The heat extraction rate per meter of the borehole is determined as 33.60 W m^?1. Considering the current gas and electric prices in Erzurum city, the equivalent COP of the GSHP system should be 2.92 for the same energy cost comparing with natural gas. The virgin ground in Erzurum basin has high permeability and low thermal conductivity. In order to improve the thermal efficiency of GHE and thus improve COP of a GSHP in the basin, the borehole should be backfilled with sand as low‐cost backfill material and a 1 to 2 m thick surface plug of clay should be inserted. Copyright © 2007 John Wiley & Sons, Ltd.     

PERFORMANCE OF A HEAT PUMP USING DIRECT EXPANSION SOLAR COLLECTORS

Theoretical and experimental studies were made on the thermal performance of a heat pump that used a bare flat-plate collector as the evaporator. The analysis used empirical equations to express the electric power consumption of the compressor and coefficient of performance (COP), as functions of temperature of evaporation at the evaporator and that of the heat transfer medium (water) at the inlet of the condenser. The experimental heat pump had a compressor with a rated capacity of 350 W and collectors with the total area of 3.24 m². Around noon in winter the evaporator temperature was found to be about 17°C higher than the ambient air temperature of 8°C, and a COP of about 5.3 was obtained when the water temperature at the condenser inlet was 40°C. These measured evaporation temperatures and COPs were in good agreement with those predicted by the analysis. According to the analysis, the total area of the collectors in the experiment was appropriate for the heat pump system. Also, the 1-mm thickness of the collector's copper plate used in the experiment could be 0.5 mm with little reduction of COP. The pitch of the tube soldered to the copper plate for the refrigerant flow was 100 mm in the experiment, but the COP would only be reduced by about 4% if the pitch were changed to 190 mm.     

Experimental investigation and a dynamic simulation of the solar-assisted energy-storaged heat pump system

In order to improve the performance of the solar-assisted and energy-storaged heat pump system, an experimental setup was constructed. In this study, the solar-assisted energy-storaged series heat pump system and other conventional heat pump systems with no energy storage (series and parallel heat pump systems) are experimentally investigated and compared. The experiments were made in July, August, September, October, November, and December in 1990, under the clear-sky conditions for three heat pump systems. The experimentally obtained results are used to calculate the collector efficiency n_k, heat pump COP, and system COP_sys (coefficient of performance). On the other hand, a dynamic simulation program has been developed for a solar-assisted and energy-storaged heat pump system. The experimental results were compared with the dynamic simulation results.     

The potential for heat pumps in drying and dehumidification systems II: An experimental assessment of the heat pump characteristics of a heat pump dehumidification system using R114

An experimental heat pump dehumidifier is described. Actual coefficients of performance (COP)_A are plotted against the gross temperature lift (T_CO - T_EV) for various bypass ratios and air velocities. Interpolated values of (COP)_A for a specified temperature lift were obtained by fitting each set for various dry bulb temperatures of air leaving the humidifier using a linear equation. These values of (COP)_A are plotted against the linear velocity of the air stream approaching the evaporator at different dry bulb temperatures. The curves show a maximum of (COP)_A at approach velocities in the region of 1·6 ms^?1.     

Performance of ammonia–water refrigeration systems using artificial neural networks

In this paper, a new formulation, based on artificial neural network (ANN) model, is presented for the analysis of ammonia–water absorption refrigeration systems (AWRS). Performance analysis of the AWRS is very complex because of analytic functions used for calculating the properties of fluid couples and simulation programs. Therefore, it is extremely difficult to perform analysis of this system. It is well known that the generator temperature, evaporator temperature, condenser temperature, absorber temperature, poor and rich solution concentration affect the AWRS's coefficient of performance (COP) and circulation ratio (f). In this study, COP and f are estimated depending on the above temperatures and concentration values. Using the weights obtained from the trained network a new formulation is presented for the calculation of the COP and f; the use of ANN is proliferating with high speed in simulation. The R²-values obtained when unknown data were used to the networks was 0.9996 and 0.9873 for the circulation ratio and COP, respectively which is very satisfactory. The use of this new formulation, which can be employed with any programming language or spreadsheet program for the estimation of the circulation ratio and COP of AWRS, as described in this paper, may make the use of dedicated ANN software unnecessary.     

Numerical simulation and experimental validation of indirect expansion solar-assisted multi-functional heat pump

A novel indirect expansion solar-assisted multi-functional heat pump (IX-SAMHP) system which composes of the multi-functional heat pump system and solar thermal collecting system is proposed and studied in this paper. This system can fulfill space heating, space cooling and water heating with high energy efficiency by utilizing solar energy. For solar water heating mode and solar space heating mode, a dynamic model is presented and validated with the experimental results. The simulation results show good consistency with the experimental data, and the established model is able to predict the system performance at a reasonable accuracy (with the root mean square deviations less than 5%). On this basis, the performances of the IX-SAMHP system are investigated under different parametric conditions. For solar water heating mode, simultaneously operating the solar thermal collecting system and multi-functional heat pump system can be an energy efficiency method. With the solar irradiation rising from 0W/m² to 800W/m², the COP increases from 2.35 to 2.57. In solar space heating mode, the effect of the mass flow rate of water in evaporator is investigated. To balance the heating capacity and COP, the mass flow rate of water should be adjusted according to different temperature demands and heat load.