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.     

Artificial neural networks for the performance prediction of heat pump hot water heaters

The rapid progression in the use of heat pumps, due to the decrease in the equipment cost, together with the favourable economics of the consumed electrical energy, has been combined with the wide dissemination of air-to-water heat pumps (AWHPs) in the residential sector. The entrance of the respective systems in the commercial sector has made important the modelling of the processes. In this work, the suitability of artificial neural networks (ANN) in the modelling of AWHPs is investigated. The ambient air temperature in the evaporator inlet and the water temperature in the condenser inlet have been selected as the input variables; energy performance indices and quantities characterising the operation of the system have been selected as output variables. The results verify that the, easy-to-implement, trained ANN can represent an effective tool for the prediction of the AWHP performance in various operation conditions and the parametrical investigation of their behaviour.     

Energy analysis of hazelnut drying system‐assisted heat pump

In this experimental study, a proportional integral derivative (PID) controlled heat pump dryer was designed and manufactured. Heat pump dryer was tested drying of hazelnut and energy analyses were made. Drying air temperatures were changed as 50,45 and 40°C in the drying system. Drying air velocities were changed as 0.25 m s^?1 for 50°C, 0.32 m s^?1 for 45°C and 0.38 m s^?1 for 40°C. Heating coefficient of performance of whole system (COP_ws) of the heat pump dryer was calculated as 1.70 for 50°C, 1.58 for 45°C and 1.40 for 40°C drying air temperatures. Energy utilization ratio changed between 24 and 65% for 50°C, 17 and 63% for 45°C and 14 and 43% for 40°C drying air temperatures in the heat pump dryer. Copyright © 2008 John Wiley & Sons, Ltd.     

Applications of artificial neural networks for refrigeration, air-conditioning and heat pump systems—A review

In this paper, an attempt has been made to review the applications of artificial neural networks (ANN) for energy and exergy analysis of refrigeration, air conditioning and heat pump (RACHP) systems. The studies reported are categorized into eight groups as follows: (i) vapour compression systems (ii) RACHP systems components, (iii) vapour absorption systems, (iv) prediction of refrigerant properties (v) control of RACHP systems, (vi) phase change characteristics of refrigerants, (vii) heat ventilation air conditioning (HVAC) systems and (viii) other special purpose heating and cooling applications. More than 90 published articles in this area are reviewed. Additionally, the limitations with ANN models are highlighted. This paper concludes that ANN can be successfully applied in the field of RACHP systems with acceptable accuracy.     

Modeling solar still production using local weather data and artificial neural networks

A study has been performed to predict solar still distillate production from single examples of two different commercial solar stills that were operated for a year and a half. The purpose of this study was to determine the effectiveness of modeling solar still distillate production using artificial neural networks (ANNs) and local weather data. The study used the principal weather variables affecting solar still performance, which are the daily total insolation, daily average wind velocity, daily average cloud cover, daily average wind direction and daily average ambient temperature. The objectives of the study were to assess the sensitivity of the ANN predictions to different combinations of input parameters as well as to determine the minimum amount of inputs necessary to accurately model solar still performance. It was found that 31-78% of ANN model predictions were within 10% of the actual yield depending on the input variables that were selected. By using the coefficient of determination, it was found that 93-97% of the variance was accounted for by the ANN model. About one half to two thirds of the available long term input data were needed to have at least 60% of the model predictions fall within 10% of the actual yield. Satisfactory results for two different solar stills suggest that, with sufficient input data, the ANN method could be extended to predict the performance of other solar still designs in different climate regimes.     

Estimation of global solar radiation using artificial neural networks

This paper introduces a neural network technique for the estimation of global solar radiation. There are 41 radiation data collection stations spread all over the kingdom of Saudi Arabia where the radiation data and sunshine duration information are being collected since 1971. The available data from 31 locations is used for training the neural networks and the data from the other 10 locations is used for testing. The testing data was not used in the modeling to give an indication of the performance of the system in unknown locations. Results indicate the viability of this approach for spatial modeling of solar radiation.     

Optimal operation conditions for a single-stage heat transformer by means of an artificial neural network inverse

Analysis based on first and second law of thermodynamics together with direct and artificial neural networks inverse (ANNi) have been used to develop a methodology to decrease the total irreversibility of an experimental single-stage heat transformer. With the proposed methodology it is possible to calculate the optimal input parameters that should be used in order to operate the heat transformer with the lower irreversibilities. Mathematical validation of ANNi was carried out together with the comparison between the total cycle irreversibility (I_cycle) obtained thermodynamically and the I_cycle determined by using the ANNi. The results showed a mean discrepancy of 0.9% of the I_cycle values. The proposed new methodology can be very useful to control on-line the performance of a single-state heat transformer obtaining lower I_cycle values.     

Solar radiation estimation using artificial neural networks

Artificial Neural Network Methods are discussed for estimating solar radiation by first estimating the clearness index. Radial Basis Functions, RBF, and Multilayer Perceptron, MLP, models have been investigated using long-term data from eight stations in Oman. It is shown that both the RBF and MLP models performed well based on the root-mean-square error between the observed and estimated solar radiations. However, the RBF models are preferred since they require less computing power. The RBF model, obtained by training with data from the meteorological stations at Masirah, Salalah, Seeb, Sur, Fahud and Sohar, and testing with those from Buraimi and Marmul, was the best. This model can be used to estimate the solar radiation at any location in Oman.     

Prediction of heat transfer and flow characteristics in helically coiled tubes using artificial neural networks

In this study, Artificial Neural Network (ANN) models were developed to predict the heat transfer and friction factor in helically coiled tubes. The experiments were carried out with hot fluid in coiled tubes which placed in a cold bath. Coiled tubes with various curvature ratios and coil pitches (nine Layouts) were used. The output data of the ANNs were Nusselt number and friction factor. The validity of the method was evaluated through a test data set, which were not employed in the training stage of the network. Moreover, the performance of the ANN model for estimating the Nusselt number and friction factor in the coiled tubes was compared with the existing empirical correlations. The results of this comparison show that the ANN models have a superior performance in predicting Nusselt number and friction factor in the coiled tubes.     

Predicting total solar irradiation values using artificial neural networks

This study explores the possibility of developing an artificial neural networks model that could be used to predict monthly average daily total solar irradiation on a horizontal surface for locations in Uganda based on geographical and meteorological data: latitude, longitude, altitude, sunshine duration, relative humidity and maximum temperature. Results have shown good agreement between the predicted and measured values of total solar irradiation. A correlation coefficient of 0.997 was obtained with mean bias error of 0.018 MJ/m² and root mean square error of 0.131 MJ/m². Overall, the artificial neural networks model predicted with an accuracy of 0.1% of the mean absolute percentage error.     

Exergy analysis of direct expansion solar‐assisted heat pumps using artificial neural networks

Artificial neural network (ANN) is applied for exergy analysis of a direct expansion solar‐assisted heat pump (DXSAHP) in the present study. The experiments were conducted in a DXSAHP under the meteorological conditions of Calicut city in India. An ANN model was developed based on backpropagation learning algorithm for predicting the exergy destruction and exergy efficiency of each component of the system at different ambient conditions (ambient temperature and solar intensity). The experimental data acquired are used for training the network. The results showed that the network yields a maximum correlation coefficient with minimum coefficient of variance and root mean square values. The results confirmed that the use of an ANN analysis for the exergy evolution of DXSAHP is quite suitable. Copyright © 2009 John Wiley & Sons, Ltd.     

Daily solar irradiation estimation over a mountainous area using artificial neural networks

In order to design both active and passive solar energy systems, radiation data are needed for the studied location. The implementation of such renewable energy systems is especially important in places like natural parks, where acoustic and fossil fuel derived contamination has to be completely avoided. Measure of solar radiation is usually accomplished by means of radiometric station nets with a low spatial resolution. To estimate the radiation in sites located away from the stations, different interpolation/extrapolation techniques may be used. These methods are valid on places where the spatial variability of radiation is not significant, but becomes less accurate if complex terrain areas are present in between the radiometric stations. As an alternative, artificial intelligence techniques have been used in this work, along with a 20 m resolution digital model of terrain. The inputs to the network have been selected using the automatic relevance determination methodology. The data set contains 3 years’ data of daily global radiation measured at 12 different stations located in the north face of the Sierra Nevada National Park in the surroundings of Huéneja (Granada), a town located in the South East of Spain. The stations altitude varies from 1000 to 1700 m. The goal of this work has been to estimate daily global irradiation on stations located in a complex terrain, and the values estimated by the neural network model have been compared with the measured ones leading to a root mean square error (RMSE) of 6.0% and a mean bias error (MBE) of 0.2%, both expressed as a percentage of the mean value. Performance achieved individually for each of the stations lies in the range [5.0–7.5]% for the RMSE and [−1.2 to +2.1]% for the MBE. Results point out artificial neural networks as an efficient and easy methodology for calculating solar radiation levels over complex mountain terrains from only one radiometric station data. In addition, this methodology can be applied to other areas with a complex topography.     

The prediction of convective heat transfer in floor-heating systems by artificial neural networks

In this study the floor Nusselt and Rayleigh numbers for the floor-heating systems are estimated by the artificial neural networks (ANN). Numerical data for the floor Nusselt and Rayleigh numbers are available in the literature. A piece of the numerical values are used for training the ANN. The values estimated by the ANN are compared with the numerical values and the results of an equation given in the literature. It has been seen that the results of the ANN are very close to the numerical data and the results of the equation.     

Prediction of flat-plate collector performance parameters using artificial neural networks

The objective of this work is to use Artificial Neural Networks (ANN) for the prediction of the performance parameters of flat-plate solar collectors. ANNs have been used in diverse applications and they have been shown to be particularly useful in system modeling and system identification. Six ANN models have been developed for the prediction of the standard performance collector equation coefficients, both at wind and no-wind conditions, the incidence angle modifier coefficients at longitudinal and transverse directions, the collector time constant, the collector stagnation temperature and the collector heat capacity. Different networks were used due to the different nature of the input and output required in each case. The data used for the training, testing and validation of the networks were obtained from the LTS database. The results obtained when unknown data were presented to the networks are very satisfactory and indicate that the proposed method can successfully be used for the prediction of the performance parameters of flat-plate solar collectors. The advantages of this approach compared to the conventional testing methods are speed, simplicity, and the capacity of the network to learn from examples. This is done by embedding experiential knowledge in the network.     

Modeling of a continuous fluidized bed dryer using artificial neural networks

The work involves experimentation on drying of solids in a continuous fluidized bed dryer covering different variables like bed temperature, gas flow rate, solids flow rate and initial moisture content of solids. The data are modeled using artificial neural networks. The results obtained from artificial neural networks are compared with those obtained using Tanks-in-series model. It was found that results obtained from ANN fit the experimental data more accurately compared to the RTD model with less percentage error. This indicates a better fit of artificial neural networks to experimental data compared to various mathematical models.     

Experimental verification of a heat pump assisted continuous dryer simulation model

The experimental and predicted performance of a prototype heat pump assisted continuous dryer is reported. The dryer was shown to be capable of specific moisture extraction rates (SMERs) of between 1.5 and 2.5 kg/kWh using wetted foam rubber as the test material being dried. The results highlight the importance of maintaining conditions of high relative humidity within the air stream entering the evaporator; an increase in the relative humidity from 30 to 80% was shown to give a two-fold increase in the SMER. An optimum evaporator bypass air ratio of between 60 and 70% was observed for this dryer. The effects on performance of deviations from this optimum condition were found to be less significant than had been indicated by earlier models. The predicted performance of the dryer using a simulation model developed previously by the authors was in good agreement with the corresponding measured values.     

Performance of evaporator-collector and air collector in solar assisted heat pump dryer

A solar assisted heat pump dryer has been designed, fabricated and tested. This paper presents the performance of the evaporator-collector and the air collector when operated under the same meteorological conditions. ASHRAE standard procedure for collector testing has been followed. The evaporator-collector of the heat pump is acting directly as the solar collector, and the temperature of the refrigerant at the inlet to the evaporator-collector always remained below the ambient temperature. Because of the rejection of sensible and latent heats of air at the dehumidifier, the temperature at the inlet to the air collector is lower than that of the ambient air. Hence, the thermal efficiency of the air collector also increases due to a reduction of losses from the collector. The efficiencies of the evaporator-collector and the air collector were found to vary between 0.8–0.86 and 0.7–0.75, respectively, when operated under the meteorological conditions of Singapore.     

Performance analysis of a heat pump assisted drying system

The paper describes a simulation model developed to predict the performance of drying systems assisted by vapour-compression heat pumps. The heat is used to preheat the air stream before it enters the drying chamber. Energy consumption is thus reduced, as the heat pump is capable of delivering more energy as heat than it in fact consumes as input work. Ambient air provides the heat source. A computer program, based on simplified modelling of components (compressor, heat exchangers and drying chamber) has been developed. Results have been produced for a typical application, revealing that a considerable reduction in energy consumption can be obtained with the use of a heat pump. The effect of air flow rate on system performance is also studied.     

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.     

Transient analysis of heat pump assisted distillation systems. 1 The heat pump

A simple algorithm to simulate the transient behaviour of a vapour compression heat pump is described. Individual models are developed for various components of the heat pump such as compressor, evaporator, condenser and expansion valve. The components are simulated separately and are combined to form the total system. The compressor is a hermetically sealed, reciprocating piston type with adiabatic compression, the evaporator and condenser are coiled copper tubes, and the expansion valve is assumed to be adiabatic. The transport and thermodynamic properties of the refrigerant used are obtained from empirical equations. The total system is viewed in a simplified manner in order to apply the results of this transient analysis to the behaviour of a chemical process operation, namely, distillation.