Development of a dynamic artificial neural network model of an absorption chiller and its experimental validation

Lazrak, Amine; Boudéhenn, François; Bonnot, Sylvain; Fraisse, Gilles; Leconte, Antoine; Papillon, Philippe; Souyri, Bernard

doi:10.1016/j.renene.2015.09.023

Cited by 35 publications

(12 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of sorption chillers in the building sector is increasing because of their ability to use low‐grade heat for cold production. However, their operating conditions are highly dependent on the climate and building characteristics making their control difficult . Krzywanski et al built a neural network based model to predict the cooling capacity of a three‐bed adsorption chiller based on the operating conditions.…”

Section: Neural Network Applications Over a Building's Lifementioning

confidence: 99%

“…However, their operating conditions are highly dependent on the climate and building characteristics making their control difficult. 31 Krzywanski et al 57 built a neural network based model to predict the cooling capacity of a three-bed adsorption chiller based on the operating conditions. Their method, easy to apply, constitutes a valuable alternative compare with other methods involving numerical analysis and/or experiments that are time consuming and expensive.…”

Section: Production and Distribution Systems Controlmentioning

confidence: 99%

See 1 more Smart Citation

Overview of the use of artificial neural networks for energy‐related applications in the building sector

et al. 2019

View full text Add to dashboard Cite

Summary The incessant growing of the world's energy consumption and associated greenhouse gases emissions have created tremendous problems to be solved by today's and future generations. As the building sector is one of the biggest energy consumers, reducing its energy consumption is now mandatory. Being able to conceive and built efficient buildings, to effectively manage and operate them, and to rapidly renovate the existing building stock is a challenging task. Neural networks models open new possibilities to address this problem. This paper offers a comprehensive review of the studies that use neural networks for energy‐related applications in the building sector focusing on their application and on the technical characteristics of the network (ie, learning algorithm, number of layers, number of neurons, inputs and output variables, and performance criteria). On the basis of this review, limitations concerning the use of neural networks in the building sector along with existing research gaps and future research directions are identified.

show abstract

Section: Neural Network Applications Over a Building's Lifementioning

confidence: 99%

Section: Production and Distribution Systems Controlmentioning

confidence: 99%

Overview of the use of artificial neural networks for energy‐related applications in the building sector

et al. 2019

View full text Add to dashboard Cite

show abstract

“…The results showed that the required cooling load could be achieved with an error of less than 0.05%. Lazrak et al [19] implemented an ANN to predict outlet temperature and the transferred energy of the driving loop, heat rejection loop, and chilled water loop of a single-effect water-lithium bromide absorption chiller. The absolute relative errors of the transferred energy prediction were 0.1-6.6%.…”

Section: Introductionmentioning

confidence: 99%

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

Halon

Pelińska-Olko

Szyc³

et al. 2019

Energies

View full text Add to dashboard Cite

In this paper, the feasibility of a multi-layer artificial neural network to predict both the cooling capacity and the COP of an adsorption chiller working in a real pilot plant is presented. The ANN was trained to accurately predict the performance of the device using data acquired over several years of operation. The number of neurons used by the ANN should be selected individually depending on the size of the training base. The optimal number of datasets in a training base is suggested to be 35. The predicted cooling capacity curves for a given adsorption chiller driven by the district heating are presented. Predictions of the artificial neural network used show good correlation with experimental results, with the mean relative deviation as low as 1.36%. The character of the cooling capacity curve is physically accurate, and during normal operation for cooling capacities ≥8 kW, the errors rarely exceed 1%.

show abstract

“…This style of falling-film absorber is used in most absorption machines because it has several advantages, such as the high heat transfer coefficient, relatively low pressure drop, and sufficient absorption process compared to other tube arrangements. The absorption efficiency depends on many parameters, such as solution flow rate, tube geometry, and surface wetting, which governs flow around and between the tubes (Lazrak et al 2016;Li, Liu, and Liu 2016;Shirazi, Taylor, White, and Morrison 2016;Thangavelu, Myat, and Khambadkone 2017). Although the absorption chiller can use waste heat as an extra energy resource (Barrera et al 2012;Gomri 2010), the general adoption is still constrained by its relatively low coefficient of performance (COP).…”

Section: Introductionmentioning

confidence: 99%

Experimental study on the active enhancement mechanisms of heat and mass transfer in an absorption chiller (RP-1462)

Wang

Yoon

et al. 2018

Science and Technology for the Built Environment

View full text Add to dashboard Cite

Based on the introduction of periodic vibration equipment in a sorption fluids system, the effect of an active mechanism on the heat and mass transfer enhancement in an absorber and the coefficient of performance (COP) enhancement in an absorption chiller was investigated. Different combinations of frequency (15-30 Hz), amplitude (0.1-0.4 mm), and flow rate (0.1-0.5 m 3 /h), with and without additive (2EH), were compared quantitatively. The results indicated the heat and mass transfer coefficients of the absorber and the COP of the absorption chiller significantly improved-by about 50% under certain conditions. There was a critical value for the amplitude (0.2 mm) and an optimal frequency (25 Hz) in the current study. The additive and solution flow rate also affected performance, but no exclusive conclusion was obtained from our experiment. A properly controlled and applied active mechanism would be of great value not only for the absorption chiller, but also for other chemical engineering applications. The results also begin to fill the knowledge gap between the analysis of mechanical motion and absorption chiller technology. The next phase of work is to find the active mechanism of heat and mass transfer enhancement from the microflow perspective.

show abstract

Development of a dynamic artificial neural network model of an absorption chiller and its experimental validation

Cited by 35 publications

References 29 publications

Overview of the use of artificial neural networks for energy‐related applications in the building sector

Overview of the use of artificial neural networks for energy‐related applications in the building sector

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

Experimental study on the active enhancement mechanisms of heat and mass transfer in an absorption chiller (RP-1462)

Contact Info

Product

Resources

About