Predicting Performance of a District Heat Powered Adsorption Chiller by Means of an Artificial Neural Network

Halon, Tomasz; Pelińska-Olko, E.; Szyc, Malgorzata; Zajączkowski, Bartosz

doi:10.3390/en12173328

Cited by 12 publications

(13 citation statements)

References 26 publications

(32 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Its key objective is not, therefore, to find the most accurate forecasting tool, as all we need is a reliable and accurate prediction. As the MLP has been proven to be one of the best tools for providing reliable and accurate forecasts [23,26,36,37], it will be the only one used in this research.…”

Section: Resultsmentioning

confidence: 99%

Applying Artificial Neural Networks to Forecast European Union Allowance Prices: The Effect of Information from Pollutant-Related Sectors

Jaramillo-Morán

García-García

2019

Energies

View full text Add to dashboard Cite

In this paper, we forecast the price of CO2 emission allowances using an artificial intelligence tool: neural networks. We were able to provide confident predictions of several future prices by processing a set of past data. Different model structures were tested. The influence of subjective economic and political decisions on price evolution leads to complex behavior that is hard to forecast. We analyzed correlations with different economic variables related to the price of CO2 emission allowances and found the behavior of two to be similar: electricity prices and iron and steel prices. They, along with CO2 emission allowance prices, were included in the forecasting model in order to verify whether or not this improved forecasting accuracy. Only slight improvements were observed, which proved to be more significant when their respective time series trends or fluctuations were used instead of the original time series. These results show that there is some sort of link between the three variables, suggesting that the price of CO2 emission allowances is closely related to the time evolution of the price of electricity and that of iron and steel, which are very pollutant industrial sectors. This can be regarded as evidence that the CO2 market is working properly.

show abstract

Section: Resultsmentioning

confidence: 99%

Applying Artificial Neural Networks to Forecast European Union Allowance Prices: The Effect of Information from Pollutant-Related Sectors

Jaramillo-Morán

García-García

2019

Energies

View full text Add to dashboard Cite

show abstract

“…Another direction that can be taken to improve the performance of the adsorption chiller is by modifying the control system and the software, that is, optimization of the switching time [39], cycle allocation [26,27,29,40], application of heat [30,[41][42][43][44] and mass recovery [30,40,41,[44][45][46]. Another method is the application of genetic algorithms and neural networks in order to optimize chiller performance [47,48].…”

Section: Process Managementmentioning

confidence: 99%

Experimental Study of Performance Improvement of 3-Bed and 2-Evaporator Adsorption Chiller by Control Optimization

et al. 2019

View full text Add to dashboard Cite

The main challenge facing adsorption cooling technology is low Coefficient of Performance (COP), which becomes a key factor of the commercialization of this technology. This paper presents the results of modifications, aiming to increase COP, applied to the control software of a prototype three-bed two-evaporator adsorption chiller. Changes were mainly related to the sequence of the switching valves and had no influence on the hardware of the chiller. The sequence changes enabled the introduction of heat recovery and mass regeneration. Moreover, the precooling process was improved. The applied modifications not only resulted in significant improvement of the chiller's COP, but also improved the cooperation adsorption unit heating source, which is of great importance in case of district heating supply. The improvement was also observed concerning such operational aspects as noise and vibrations. In the authors' opinion, the presented modifications can be introduced to most exploited adsorption chillers and could potentially lead to similar improvements in performance.Energies 2019, 12, 3943 2 of 17 Methods of Improving COP of Adsorption ChillerThe issue of COP improvement of adsorption chillers is the subject of much research, which focuses on two main fields of study: Improvements via hardware modification and via software modification. Hardware modifications mainly consist of the proper selection of working pairs, the optimization of the adsorption beds [8], and the general system design. Software modifications reported in the literature optimize the switching time and cycle allocation. Some of the optimization methods, like the application of heat or mass recovery, usually require both hardware and software modifications. Working PairsThe appropriate selection of the working pair was reported in [9,10] as a crucial factor influencing the COP of adsorption chillers. Therefore, much reported research is related to adsorption working pairs and their properties [10]. The most popular pairs are microporous silica gel and water, zeolite and water (including alumino-silicate zeolites) [11,12], and Y-type zeolite with methanol or ethanol combinations [9,13]. Moreover, some novel adsorption working pairs are investigated, that is (silico) aluminophosphate-water, consolidated adsorbents such as LiBr-silica-ethanol or water, CaCl 2 -silica and water, and activated carbon with ethanol, methanol or water [9].Each adsorption working pair has unique properties that make it possible to obtain good performance in the conditions considered. For example, water-based pairs cannot be applied to achieve temperatures lower than 0 • C (due to water's freezing point). Some of the adsorbates, like methanol, are harmful, and its application would probably require additional safety procedures. An overview of working pairs was presented by [14]. Other important factors which must be considered are the expense and availability of the selected adsorption working pair.

show abstract

“…The COP of adsorption chiller of 0.65 is obtainable only for high desorption temperatures, high cooled water temperatures, and low cooling temperatures. For the heating temperatures as low as 60 • C, it is drastically lower (down to 0.17-0.34) [17]. These systems have some special features due to the periodic adsorption and desorption of the sorbents.…”

Section: Introductionmentioning

confidence: 99%

Potential Study of Solar Thermal Cooling in Sub-Mediterranean Climate

et al. 2020

View full text Add to dashboard Cite

Air conditioning is becoming increasingly important in the energy supply of buildings worldwide. There has been a dramatic increase in energy requirements for cooling buildings in the Middle East and North Africa (MENA) region. This is before taking the effects of climate change into account, which will also entail a sharp increase in cooling requirements. This paper presents the potential of using a solar thermal absorption cooling system in Sub-Mediterranean Climate. Four sites in Jordan are now equipped with water-lithium bromide (H₂O-LiBr) absorption chillers with a total nominal capacity of 530 kW. The focus of the paper was on the pilot system at the German Jordanian University (GJU) campus with a cooling capacity of 160 kW. The system was designed and integrated in order to support two existing conventional compression chillers with a nominal cooling capacity of 700 kW. The system was economically evaluated based on the observed cooling capacity results with a Coefficient of Performance (COP) equals 0.32, and compared with the values observed for a COP of 0.79 which is claimed by the manufacturer. Several techniques were implemented to evaluate the overall economic viability in-depth such as present worth value, internal rate of return, payback period, and levelized cost of electricity. The aforementioned economic studies showed that the absorption cooling system is deemed not feasible for the observed COP of 0.32 over a lifespan of 25 years. The net present value was equal to −137,684 JD and a payback period of 44 years which exceeds the expected lifespan of the project. Even for an optimal operation of COP = 0.79, the discounted payback period was equal to 23 years and the Levelized Cost of Electricity (LCOE) was equal to 0.65 JD/kWh. The survey shows that there are several weaknesses for applying solar thermal cooling in developing countries such as the high cost of these systems and, more significantly, the lack of experience for such systems.

show abstract

Predicting Performance of a District Heat Powered Adsorption Chiller by Means of an Artificial Neural Network

Cited by 12 publications

References 26 publications

Applying Artificial Neural Networks to Forecast European Union Allowance Prices: The Effect of Information from Pollutant-Related Sectors

Applying Artificial Neural Networks to Forecast European Union Allowance Prices: The Effect of Information from Pollutant-Related Sectors

Experimental Study of Performance Improvement of 3-Bed and 2-Evaporator Adsorption Chiller by Control Optimization

Potential Study of Solar Thermal Cooling in Sub-Mediterranean Climate

Contact Info

Product

Resources

About