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.     

Modeling of a hazelnut dryer assisted heat pump by using artificial neural networks

The artificial neural network (ANN) approach is generic technique for mapping non-linear relationships between inputs and outputs without knowing the details of these relationships. In this paper, an application of the ANN has been presented for a PID controlled heat pump dryer. In PID controlled heat pump dryer, air velocity changed according to the temperature value which is set in process control device. Heat pump dryer was tested drying of hazelnut at 40 °C, 45 °C and 50 °C drying air temperatures. By training the experiment results with ANN, drying air velocities, moisture content of hazelnuts and total drying time were predicted for 42 °C, 44 °C, 46 °C and 48 °C drying air temperatures.     

Performance of a multi-functional direct-expansion solar assisted heat pump system

This paper reports on the long-term performance of a direct-expansion solar assisted heat pump (DX-SAHP) system for domestic use, which can offer space heating in winter, air conditioning in summer and hot water during the whole year. The system employs a bare flat-plate collector array with a surface area of 10.5 m², a variable speed compressor, a storage tank with a total volume of 1 m³ and radiant floor heating unit. The performance under different operation modes is presented and analyzed in detail. For space-heating-only mode, the daily-averaged heat pump COP varied from 2.6 to 3.3, while the system COP ranged from 2.1 to 2.7. For water-heating-only mode, the DX-SAHP system could supply 200 l or 1000 l hot water daily, with the final temperature of about 50 °C, under various weather conditions in Shanghai, China. For space-cooling-only mode, the compressor operates only at night to take advantage of a utility’s off-peak electrical rates by chilling water in the thermal storage tank for the daytime air-conditioning. It shows that, the multi-functional DX-SAHP system could guarantee a long-term operation under very different weather conditions and relatively low running cost for a whole year.     

辐照强度对直膨式太阳能热泵性能影响的研究

文章搭建了直膨式太阳能热泵热水系统实验装置,研究了辐照强度对直膨式太阳能热泵性能的影响。结果表明,在环境温度及冷凝温度不变的情况下,蒸发温度及性能系数(COP)值随着辐照强度的增大而升高,且辐照强度增加200 W/m2,蒸发温度升高3~5℃,COP值升高0.8~1.2;得热效率随着辐照强度的增大而降低,其降低速率随着辐照强度的增大而逐渐减小。     

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.     

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.     

直膨式太阳能热泵运行特性的实验研究

对直接膨胀式太阳能热泵热水系统进行了实验研究,实验期间,太阳能辐照度变化范围为143.12~664.6 W/m2,分别采用三种不同结构的集热器和蒸发器,得出系统COP为2.49~3.47,表明该系统在各种天气情况下均能够可靠地生产45℃的生活热水,热性能稳定,可以全天候地提供生活热水且具有节能效果;同时选取双集热器的两组数据,分析了太阳辐照度对热泵系统运行的影响。     

Study on a direct‐expansion solar‐assisted heat pump water heating system

Analytical and experimental studies were performed on a direct‐expansion solar‐assisted heat pump (DX‐SAHP) water heating system, in which a 2 m² bare flat collector acts as a source as well as an evaporator for the refrigerant. A simulation model was developed to predict the long‐term thermal performance of the system approximately. The monthly averaged COP was found to vary between 4 and 6, while the collector efficiency ranged from 40 to 60%. The simulated results were used to obtain an optimum design of the system and to determinate a proper strategy for system operating control. The effect of various parameters, including solar insolation, ambient temperature, collector area, storage volume and speed of compressor, had been investigated on the thermal performance of the DX‐SAHP system, and the results had indicated that the system performance is governed strongly by the change of solar insolation, collector area and speed of compressor. The experimental results obtained under winter climate conditions were shown to agree reasonably with the computer simulation. Copyright © 2003 John Wiley & Sons, Ltd.     

State-of-charge prediction of batteries and battery-supercapacitor hybrids using artificial neural networks

The state-of-charge (SOC) of batteries and battery-supercapacitor hybrid systems is predicted using artificial neural networks (ANNs). Our technique is able to predict the SOC of energy storage devices based on a short initial segment (less than 4% of the average lifetime) of the discharge curve. The prediction shows good performance with a correlation coefficient above 0.95. We are able to improve the prediction further by considering readily available measurements of the device and usage. The prediction is further shown to be resilient to changes in operating conditions or physical structure of the devices.     

太阳能辅助供暖的地源热泵经济性分析

在冬季土壤温度较低，而且以热负荷为主的北方地区，若完全采用地源热泵来供暖，则地热换热器和机组的初投资均比较高，连续运行的效率也较低，因此，可利用太阳能集热器作为辅助能源。白天完全依靠地源热泵供暖，夜间利用太阳能集热器蓄存的热量，使地热换热器与太阳能集热器串联运行，通过分析比较，该方案比完全用地源热泵供暖更经济。     

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.     

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.     

Performance study of a photovoltaic solar assisted heat pump with variable-frequency compressor – A case study in Tibet

The performance of a photovoltaic solar assisted heat pump (PV-SAHP) with variable-frequency compressor is reported in this paper. The system is a direct integration of photovoltaic/thermal solar collectors and heat pump. The solar collectors extract the required thermal energy from the heat pump and at the same time, the cooling effect of the refrigerant lowers the working temperature of the solar cells. So this combined system has a relatively high thermal performance with an improved photovoltaic efficiency. To adapt to the continuously changing solar radiation and ambient temperature conditions, the refrigerant mass flow rate should match the heat gain at the evaporator accordingly. A variable-frequency compressor and an electricity-operated expansion valve were used in the proposed system. Mathematical models were developed to evaluate the energy performance of the combined system based on the weather conditions of Tibet. The simulation results indicated that on a typical sunny winter day with light breeze, the average COP could reach 6.01, and the average electricity efficiency, thermal efficiency and overall efficiency were 0.135, 0.479 and 0.625 respectively.     

Estimation of monthly average daily global solar irradiation using artificial neural networks

This study explores the possibility of developing a prediction model using artificial neural networks (ANN), which could be used to estimate monthly average daily global solar irradiation on a horizontal surface for locations in Uganda based on weather station data: sunshine duration, maximum temperature, cloud cover and location parameters: latitude, longitude, altitude. Results have shown good agreement between the estimated and measured values of global solar irradiation. A correlation coefficient of 0.974 was obtained with mean bias error of 0.059 MJ/m² and root mean square error of 0.385 MJ/m². The comparison between the ANN and empirical method emphasized the superiority of the proposed ANN prediction model.     

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.     

太阳能辅助地源热泵联合供暖(制冷)运行模式分析

太阳能和地源热泵联合供暖系统以其良好的节能和环保特性,近年来得到国内外众多学者和研究机构的广泛关注。总结了国内外地源热泵和太阳能集热器联合供暖（制冷）技术的发展现状和最新研究动态,介绍了太阳能辅助地源热泵联合供暖（制冷）的技术和特点,指出太阳能辅助地源热泵供暖（制冷）技术具有较好的发展前景。     

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.     

太阳能辅助二氧化碳热泵热水系统实验研究

利用实验的方法,研究了太阳辐照度、外界气温和风速、初始水温、蒸发器出口温度和压力等对太阳能辅助二氧化碳热泵热水系统运行状况和COP的影响。实验结果表明,系统COP随初始水温的升高而增大;太阳辐照度、外界温度和风速对热泵系统性能的影响主要体现在对系统循环水温的影响;在一定范围内,蒸发压力和蒸发温度越高,热泵系统的COP越大。     

Analysis of a direct expansion solar assisted heat pump using different refrigerants

The thermal performance of a direct expansion solar assisted heat pump (DX-SAHP) is analyzed for several refrigerants using two collector configurations, namely a bare collector and a one cover collector. The REFPROP computer program, developed by the National Institute of Science and Technology, is employed to predict the refrigerant properties involved in the energy balance across the collector. The thermal performance, as characterized by the coefficient of performance (COP), is determined for a variety of pure refrigerants as well as refrigerant mixtures. The performance degradation due to switching from R-12 to pure hydrofluorocarbon (HFC) refrigerants as well as refrigerant blends is investigated. A graphical procedure is developed and illustrated for several refrigerants for sizing the solar collector area and the heat pump compressor displacement capacity for the two collector configurations considered in this study.     

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.