Predicting Performance of a District Heat Powered Adsorption Chiller by Means of an Artificial Neural Network
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 yea...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-08-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/12/17/3328 |
| _version_ | 1797999807410733056 |
|---|---|
| author | Tomasz Halon Ewa Pelinska-Olko Malgorzata Szyc Bartosz Zajaczkowski |
| author_facet | Tomasz Halon Ewa Pelinska-Olko Malgorzata Szyc Bartosz Zajaczkowski |
| author_sort | Tomasz Halon |
| collection | DOAJ |
| description | 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%. |
| first_indexed | 2024-04-11T11:10:39Z |
| format | Article |
| id | doaj.art-60bff23538a9402c9cbaa1b21be187a5 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-04-11T11:10:39Z |
| publishDate | 2019-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-60bff23538a9402c9cbaa1b21be187a52022-12-22T04:27:30ZengMDPI AGEnergies1996-10732019-08-011217332810.3390/en12173328en12173328Predicting Performance of a District Heat Powered Adsorption Chiller by Means of an Artificial Neural NetworkTomasz Halon0Ewa Pelinska-Olko1Malgorzata Szyc2Bartosz Zajaczkowski3Faculty of Mechanical and Power Engineering, Wroclaw University of Science and Technology, Wyb. Wyspianskiego 27, 50-370 Wroclaw, PolandFaculty of Mechanical and Power Engineering, Wroclaw University of Science and Technology, Wyb. Wyspianskiego 27, 50-370 Wroclaw, PolandFortum Power and Heat Polska, ul. Antoniego Slonimskiego 1A, 50-304 Wroclaw, PolandFaculty of Mechanical and Power Engineering, Wroclaw University of Science and Technology, Wyb. Wyspianskiego 27, 50-370 Wroclaw, PolandIn 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%.https://www.mdpi.com/1996-1073/12/17/3328adsorption refrigerationdistrict heatartificial neural networks |
| spellingShingle | Tomasz Halon Ewa Pelinska-Olko Malgorzata Szyc Bartosz Zajaczkowski Predicting Performance of a District Heat Powered Adsorption Chiller by Means of an Artificial Neural Network Energies adsorption refrigeration district heat artificial neural networks |
| title | Predicting Performance of a District Heat Powered Adsorption Chiller by Means of an Artificial Neural Network |
| title_full | Predicting Performance of a District Heat Powered Adsorption Chiller by Means of an Artificial Neural Network |
| title_fullStr | Predicting Performance of a District Heat Powered Adsorption Chiller by Means of an Artificial Neural Network |
| title_full_unstemmed | Predicting Performance of a District Heat Powered Adsorption Chiller by Means of an Artificial Neural Network |
| title_short | Predicting Performance of a District Heat Powered Adsorption Chiller by Means of an Artificial Neural Network |
| title_sort | predicting performance of a district heat powered adsorption chiller by means of an artificial neural network |
| topic | adsorption refrigeration district heat artificial neural networks |
| url | https://www.mdpi.com/1996-1073/12/17/3328 |
| work_keys_str_mv | AT tomaszhalon predictingperformanceofadistrictheatpoweredadsorptionchillerbymeansofanartificialneuralnetwork AT ewapelinskaolko predictingperformanceofadistrictheatpoweredadsorptionchillerbymeansofanartificialneuralnetwork AT malgorzataszyc predictingperformanceofadistrictheatpoweredadsorptionchillerbymeansofanartificialneuralnetwork AT bartoszzajaczkowski predictingperformanceofadistrictheatpoweredadsorptionchillerbymeansofanartificialneuralnetwork |