Artificial neural network modelling of parabolic trough types solar thermal power plant
Abstract
This study aims to determine the most appropriate design point for solar energy aided power plant system using the R-134a as a working fluid, using the Artificial neural network (ANN) method. A total of 900 different data, with varying fractions of solution and working parameters, were analysed utilising energy-exergy, power, and Net Present Value (NPV) analysis. In the training phase, 630 data were used. The remaining 270 data were reserved for testing. Levenberge Marguardt ( ), Pola- Ribiere Conjugate Gradient ( ), and Scaled Conjugate Gradient ( ), algorithms are used to find the best approximation in the network. According to the ANN results, the error rate of 0.013% was determined in an acceptable range for engineering applications. The best results were obtained in the training and testing stages in the -10 algorithm. The values of absolute change percentage , Mean Percentage Error , Coefficient of Variation and Root Mean Square Error ( ) were determined as 0.9999, 0.5100, 0.3807, and 0.0031, respectively, for the output of in training steps. When the obtained results are examined, the analysis results of the most suitable system are as follows; the energy efficiency 18.4%, exergy efficiency 23.6%, and generated power of the system 281.9 . Besides, the profitability value of the system has been determined as 1.31 million .
Full Text:
PDFReferences
D. Guler, A Mutlu, E. Guney, B. Caglar, A. Hepbaslı and M. Araz, “Design and thermodynamic analysis of a 1 MW solar thermal power plant,” 13. National Plumbing Engineering Congress, 13-27 April 2017, İzmir, pp, 345-359.
C. Yilmaz, I. Koyuncu, “Thermoeconomic modelling and artificial neural network optimisation of Afyon geothermal power plant,” Renewable Energy, vol. 163, pp. 1166-1181, 2021.
A. Zaaoumi, A. Bah, M. Ciocan, P. Sebastian, M.C. Balan, A. Mechaqrane, M. Alaoui, “Estimation of the energy production of a parabolic trough solar thermal power plant using analytical and artificial neural networks models,” Renewable Energy, vol. 170, pp. 620-638, 2021.
F. Ferrara, A. Gimelli, A. Luongo, “Small-scale concentrated solar power (CSP) plant: ORCs comparison for different organic fluids,” Energy Procedia, 45(68th), pp. 217-226, 2014.
F. A. Al-Sulaiman, “Exergy analysis of parabolic trough solar collectors integrated with combined steam and organic Rankine cycles,” Energy Conversion and Management, vol. 77, pp. 441-449, 2014.
T. E. Boukelia, M. S. Mecibah, B. N. Kumar, K. S. Reddy, “Investigation of solar parabolic trough power plants with and without integrated TES (thermal energy storage) and FBS (fuel backup system) using thermic oil and solar sal,” Energy, vol. 88, pp. 292-303, 2015.
O. Arslan, D. Kilic, “Concurrent optimisation and 4E analysis of organic Rankine cycle power plant driven by parabolic trough collector for low-solar radiation zone,” Sustainable Energy Technologies and Assessments, vol. 46, 101230, 2021.
S. Thaker, A. O. Oni, A. Kumar, “Techno-economic evaluation of solar-based thermal energy storage systems,” Energy Conversion and Management, vol.153, pp.423-434, 2017.
J. Yang, J. Li, Z. Yang, Y. Duan, “Thermodynamic analysis and optimisation of a solar organic Rankine cycle operating with stable output,” Energy Conversion and Management, vol. 187, pp. 459-471, 2019.
S. Kumar, T. Kaur, T. “Development of ANN based model for solar potential assessment using various meteorological parameters,” Energy Procedia, vol. 90, pp. 587-592, 2016.
O. Arslan, O. Yetik, “ANN-based optimisation of supercritical ORC-Binary geothermal power plant: Simav case study,” Applied Thermal Engineering, 31(17-18), pp. 3922-3928, 2011.
A. Sencan, K. A. Yakut, S. A. Kalogirou, “Thermodynamic analysis of absorption systems using artificial neural network,” Renewable Energy, 31(1), pp. 29-43, 2006.
T. E. Boukelia, O. Arslan, M. S. Mecibah, “ANN-based optimisation of a parabolic trough solar thermal power plant,” Applied Thermal Engineering, vol. 107, pp. 1210-1218, 2016.
A. Sozen, M. Ozalp, E. Arcaklioglu, E. Galip Kanit, “A study for estimating solar resources in Turkey using artificial neural networks,” Energy Sources, 26(14), pp. 1369-1378, 2004.
O. Arslan, “Power generation from medium temperature geothermal resources: ANN-based optimisation of Kalina cycle system-34,” Energy, 36(5), pp. 2528-2534, 2011.
O. Senkal, “Modeling of solar radiation using remote sensing and artificial neural network in Turkey,” Energy, 35(12), pp. 4795-4801, 2010.
T. E. Boukelia, O. Arslan, M. S. Mecibah, “Potential assessment of a parabolic trough solar thermal power plant considering hourly analysis: ANN-based approach,” Renewable Energy, vol. 105, pp. 324-333, 2017.
S. A. Kalogirou, “Optimisation of solar systems using artificial neural networks and genetic algorithms,” Applied Energy, 77(4), pp. 383-405, 2004.
D. E. Ighravwe, D. Mashao, “Development of artificial neural networks for an energy storage system generated power prediction,” Energy Reports, 6, pp. 674-679, 2020.
A. Tugcu, O. Arslan, “Optimisation of geothermal energy aided absorption refrigeration system—GAARS: A novel ANN-based approach,” Geothermics, vol. 65, pp. 210-221, 2017.
General directorate of renewable energy. https://gepa.enerji.gov.tr/MyCalculator/pages/11.aspx (date of access 10.06.2019), in Turkey.
Y. E. Yüksel, “Thermodynamic assessment of modified Organic Rankine Cycle integrated with parabolic trough collector for hydrogen production,” International Journal of Hydrogen Energy, 43(11), pp. 5832-5841, 2018.
Therminol VP1 http://twt.mpei.ac.ru/tthb/hedh/htf-vp1.pdf (date of access 10.09.2018)
M. S. Sohal, M. A. Ebner, P. Sabharwall, P. Sharpe, “Engineering Database of Liquid Salt Thermophysical and Thermochemical Properties”, No. INL/EXT-10-18297, Idaho National Laboratory, 2010.
Refprop. Reference Fluid Thermodynamic and Transport Properties. NIST Reference Database. Version 9.0. National Institute of Standards and Technology, NIST, USA, 2010.
Y. Cengel, M. Boles, Thermodynamics with Engineering Approach. (Translation: T. Derbentli). Istanbul: McGraw-Hill- Literature Publishing, 1996.
Ministry of Labor and Social Security Turkish Republic. https://www.csgb.gov.tr/media/1236/2018_onikiay.pdf (date of access 2018, January). Check
S. Agatonovic-Kustrin, R. Beresford, “Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research,” Journal of Pharmaceutical and Biomedical Analysis, 22(5), pp. 717-727, 2000.
URN: https://sloi.org/urn:sl:tjoee63178
Copyright (c) 2021 Turkish Journal of Electromechanics and Energy
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Indexed in:
