Drying of Nettle Using Concentrated Air Collector and Concentrated Photovoltaic Thermal Supported Drying System and Modeling with Machine Learning

Mehmet Onur Karaagac

doi:10.29130/dubited.1460576

EN TR

Drying of Nettle Using Concentrated Air Collector and Concentrated Photovoltaic Thermal Supported Drying System and Modeling with Machine Learning

Abstract

This study examines the performance of a solar assisted drying system in the nettle drying process. The drying process works by using thermal energy obtained from solar air collectors and PV modules. The experimental were carried out in October 2022, and the room temperature, total efficiency and moisture content parameters were investigated. The data obtained from the drying system were modelled using machine learning algorithms such as artificial neural networks (ANN), support vector machines (SVM), and gradient boosting decision trees (GBDT). The average thermal energy transferred to the drying cabin was calculated as 154 W, with 77% of this energy was obtained from the air collector and the remaining 23% from the PV module. The stinging nettle was dried from an initial moisture content of 11.18 g water/g dry matter to a final moisture content of 1.18 g water/g dry matter. The average total efficiency of the drying system was found to be 16.8%. Additionally, the results show that the SVM algorithm exhibits the best performance in estimating important parameters such as chamber temperature, moisture content, and total efficiency. Especially in total efficiency prediction. The SVM algorithm has a significant advantage over other algorithms. As a result, it was concluded that the SVM algorithm can be used effectively utilized in solar energy-supported drying systems and can be a precious choice for the optimization of the drying process.

Keywords

Solar energy-supported drying systems, Machine learning algorithms, Drying process optimization

Yoğunlaştırılmış Havalı Kolektör ve Yoğunlaştırılmış Fotovoltaik Termal Destekli Bir Kurutma Sistemi ile Isırgan Otunun Kurutulması ve Sistem Verilerinin Makine Öğrenmesi ile Modellenmesi

Abstract

Bu çalışma, ısırgan otu kurutma sürecinde güneş enerjisi destekli bir kurutma sisteminin performansını incelemektedir. Kurutma işlemi, havalı güneş kolektöründen ve PV modüllerden elde edilen termal enerjiyi kullanarak çalışmaktadır. Deneyler, 2022 yılı ekim ayında gerçekleştirilmiş ve oda sıcaklığı, toplam verimlilik ve nem içeriği parametrelerin değişimi incelenmiştir. Kurutma sürecinde elde edilen veriler, yapay sinir ağı (YSA), destek vektör makinesi (SVM) ve gradyan artırıcı karar ağacı (GBDT) gibi makine öğrenmesi algoritmaları kullanılarak modellenmiştir. Isırgan otu başlangıçta 11,18 gr su / gr kuru madde nem içerirken, 1,18 gr su /gr kuru madde miktarına kadar kurutulmuştur. Kurutma kabinine aktarılan ortalama termal enerji 154 W olarak hesaplanmıştır. Bu enerjinin %77 kolektörden geri kalan %23 kısımda FV modelden elde edilmiştir. Kurutma sisteminin ortalama toplam verimi %16,8 olarak hesaplanmıştır. Isırgan otu başlangıçta 11,18 gr su / gr kuru madde nem içeriğinden 1,18 gr su /gr kuru madde miktarına kadar kurutulmuştur. Ayrıca elde edilen sonuçlar, kabinsıcaklığı, nem içeriği ve toplam verim gibi önemli parametrelerin tahmin edilmesinde SVM algoritmasının en iyi performansı sergilediğini göstermektedir. Özellikle toplam verim tahmininde SVM algoritması, diğer algoritmalara göre önemli bir üstünlük sağlamıştır. Sonuç olarak, güneş enerjisi destekli kurutma sistemlerinde SVM algoritmasının etkili bir şekilde kullanılabileceği ve kurutma sürecinin optimize edilmesinde değerli bir araç olabileceği sonucuna varılmıştır.

Keywords

Güneş enerjisi destekli kurutma sistemleri, Makine öğrenme algoritmaları, Kurutma prosesi optimizasyonu

References

[1] M. Aktaş, A. Khanlari, A. Amini, and S. Şevik, ‘Performance analysis of heat pump and infrared–heat pump drying of grated carrot using energy-exergy methodology’, Energy Conversion and Management, vol. 132, pp. 327–338, Jan. 2017.
[2] M. S. Buker and S. B. Riffat, ‘Solar assisted heat pump systems for low temperature water heating applications: A systematic review’, Renewable and Sustainable Energy Reviews, vol. 55, pp. 399–413, Mar. 2016.
[3] M. O. Karaağaç, A. Ergün, A. Etem Gürel, İ. Ceylan, and G. Yıldız, ‘Assessment of a novel defrost method for PV/T system assisted sustainable refrigeration system’, Energy Conversion and Management, vol. 267, p. 115943, Sep. 2022.
[4] İ. Arslan, ‘Tekirdağ koşullarında polikristal ve monokristal tip pv güneş panellerinin verimlilik karşılaştırılması’, Monocyrstal and polycrystal solar panels under tekirdag conditions investigation of efficiency, 2018, Accessed: Feb. 23, 2021.
[5] M. O. Karaagac, H. Oğul, and F. Bulut, ‘Sinop İli Koşullarında Monokristal ve Polikristal Fotovoltaik Panellerin Değerlendirilmesi’, Türk Doğa ve Fen Dergisi, vol. 10, no. 1, Art. no. 1, Jun. 2021.
[6] M. Abdelgaied, A. S. Abdullah, A. E. Kabeel, and H. F. Abosheiasha, ‘Assessment of an innovative hybrid system of PVT-driven RO desalination unit integrated with solar dish concentrator as preheating unit’, Energy Conversion and Management, vol. 258, p. 115558, Apr. 2022.
[7] M. Abderrahman, B. Abdelaziz, and O. Abdelkader, ‘Thermal performances and kinetics analyses of greenhouse hybrid drying of two-phase olive pomace: Effect of thin layer thickness’, Renewable Energy, vol. 199, pp. 407–418, Nov. 2022.
[8] F. Durmaz, R. C. Akdeni̇z, and F. Kömekçi̇, ‘Fotovoltaik Enerji ile Tarımsal İşletmelerin Enerji Gereksiniminin Karşılanabilirliği: Manisa - Turgutlu Örneği’, TMBD, vol. 13, no. 3, Art. no. 3, Dec. 2017.
[9] E. K. Akpinar, ‘Drying of mint leaves in a solar dryer and under open sun: Modelling, performance analyses’, Energy Conversion and Management, vol. 51, no. 12, pp. 2407–2418, Dec. 2010.
[10] M. Aktaş, İ. Ceylan, A. Ergün, A. E. Gürel, and M. Atar, ‘Assessment of a solar-assisted infrared timber drying system’, Environmental Progress & Sustainable Energy, vol. 36, no. 6, pp. 1875–1881, 2017.

[11] I. Ceylan and A. Ergun, ‘Psychrometric analysis of a timber dryer’, Case Studies in Thermal Engineering, vol. 2, pp. 29–35, Mar. 2014.
[12] Ö. Demi̇r, ‘Kızılötesi Kurutucuda Nane Bitkisinin Optimum Kurutma Sıcaklığının Belirlenmesi’, Bitlis Eren Üniversitesi Fen Bilimleri Dergisi, vol. 8, no. 3, Art. no. 3, Sep. 2019.
[13] M. O. Karaağaç, A. Ergün, Ü. Ağbulut, A. E. Gürel, and İ. Ceylan, ‘Experimental analysis of CPV/T solar dryer with nano-enhanced PCM and prediction of drying parameters using ANN and SVM algorithms’, Solar Energy, vol. 218, pp. 57–67, Apr. 2021.
[14] İ. Ceylan, M. Aktaş, and H. Doğan, ‘Güneş Enerjili Kurutma Fırınında Elma Kurutulması’, Politeknik Dergisi, vol. 9, no. 4, Art. no. 4, Dec. 2006.
[15] A. Uçar and A. Oral, ‘Havalı Güneş Kollektörlü Bir Isıtma Sisteminin Deneysel Olarak İncelenmesi’, International Journal of Pure and Applied Sciences, vol. 9, no. 2, Art. no. 2, Dec. 2023.
[16] E. Kaya, H. Dumrul, and S. Yilmaz, ‘Isı Borulu Güneş Kollektörlü Kurutma Sisteminin Tasarımı ve Deneysel Analizi’, Politeknik Dergisi, vol. 26, no. 2, Art. no. 2, Jul. 2023.
[17] S. M. Mousavifard, M. M. Attar, A. Ghanbari, and M. Dadgar, ‘Application of artificial neural network and adaptive neuro-fuzzy inference system to investigate corrosion rate of zirconium-based nano-ceramic layer on galvanized steel in 3.5% NaCl solution’, Journal of Alloys and Compounds, vol. 639, pp. 315–324, Aug. 2015.
[18] A. K. Yıldız, H. Polatcı, and U. Harun, ‘Farklı Kurutma Şartlarında Muz (Musa cavendishii) Meyvesinin Kurutulması ve Kurutma Kinetiğinin Yapay Sinir Ağları ile Modellenmesi’, Tarım Makinaları Bilimi Dergisi, vol. 11, no. 2, pp. 173–178, 2015.
[19] G. V. S. Bhagya Raj and K. K. Dash, ‘Microwave vacuum drying of dragon fruit slice: Artificial neural network modelling, genetic algorithm optimization, and kinetics study’, Computers and Electronics in Agriculture, vol. 178, p. 105814, Nov. 2020.
[20] H. N. Bulus, A. Moralar, and S. Celen, ‘Modeling the Moisture Content and Drying Rate of Zucchini (Cucurbita pepo L.) in a Solar Hybrid Dryer Using ANN and ANFIS Methods’, The Philippine Agricultural Scientist, vol. 106, no. 3, Sep. 2023.
[21] D. B. Saydam, K. N. Çerçi̇, and E. Hürdoğan, ‘V Tipi Havali Bir Güneş Kolektörünün Isil Performansinin Deneysel Olarak İncelenmesi Ve Yapay Sinir Ağlari İle Modellenmesi’, MBTD, vol. 9, no. 4, Art. no. 4, Dec. 2021.
[22] T. Menlik, M. B. Özdemir, and V. Kirmaci, ‘Determination of freeze-drying behaviors of apples by artificial neural network’, Expert Systems with Applications, vol. 37, no. 12, pp. 7669–7677, Dec. 2010.
[23] D. B. Saydam, K. N. Çerçi̇, and E. Hürdoğan, ‘Güneş Enerjili Yeni Tip Bir Kurutucuda Granny Smith Elmanın Kuruma Davranışının İncelenmesi’, Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi, vol. 21, no. 4, Art. no. 4, Aug. 2021.
[24] Ş. Seyfi; Aktaş, ‘Güneş destekli ısı pompalı bir kurutucuda mantarın kuruma davranışlarının yapay sinir ağı kullanılarak modellenmesi’, Tarım Bilimleri Dergisi, vol. 20, no. 2, pp. 187–202, 2014.
[25] A. Ergün, İ. Ceylan, B. Acar, and H. Erkaymaz, ‘Energy–exergy–ANN analyses of solar-assisted fluidized bed dryer’, Drying Technology, vol. 35, no. 14, pp. 1711–1720, Oct. 2017.
[26] B. E. Boser, I. M. Guyon, and V. N. Vapnik, ‘A training algorithm for optimal margin classifiers’, presented at the Proceedings of the fifth annual workshop on Computational learning theory, 1992, pp. 144–152.
[27] G.-Q. Lin, L.-L. Li, M.-L. Tseng, H.-M. Liu, D.-D. Yuan, and R. R. Tan, ‘An improved moth-flame optimization algorithm for support vector machine prediction of photovoltaic power generation’, Journal of Cleaner Production, vol. 253, p. 119966, Apr. 2020.
[28] T. Zhang, Y. Huang, H. Liao, and Y. Liang, ‘A hybrid electric vehicle load classification and forecasting approach based on GBDT algorithm and temporal convolutional network’, Applied Energy, vol. 351, p. 121768, Dec. 2023.
[29] S. G. Gouda, Z. Hussein, S. Luo, and Q. Yuan, ‘Model selection for accurate daily global solar radiation prediction in China’, Journal of Cleaner Production, vol. 221, pp. 132–144, Jun. 2019.
[30] D. S. K. Karunasingha, ‘Root mean square error or mean absolute error? Use their ratio as well’, Information Sciences, vol. 585, pp. 609–629, Mar. 2022.
[31] M. O. Karaağaç, A. Kabul, and H. Oğul, ‘First- and second-law thermodynamic analyses of a combined natural gas cycle power plant: Sankey and Grossman diagrams’, Turk J Phys, vol. 43, no. 1, pp. 93–108, Feb. 2019.

Details

Primary Language

English

Subjects

Solar Energy Systems

Journal Section

Research Article

Authors

Mehmet Onur Karaagac ^*
0000-0003-1783-9702
Türkiye

Publication Date

October 23, 2024

Submission Date

March 28, 2024

Acceptance Date

May 23, 2024

Published in Issue

Year 2024 Volume: 12 Number: 4

DOI

https://doi.org/10.29130/dubited.1460576

IZ

https://izlik.org/JA76HW54LS

APA

Karaagac, M. O. (2024). Drying of Nettle Using Concentrated Air Collector and Concentrated Photovoltaic Thermal Supported Drying System and Modeling with Machine Learning. Duzce University Journal of Science and Technology, 12(4), 1913-1929. https://doi.org/10.29130/dubited.1460576

AMA

1.Karaagac MO. Drying of Nettle Using Concentrated Air Collector and Concentrated Photovoltaic Thermal Supported Drying System and Modeling with Machine Learning. DUBİTED. 2024;12(4):1913-1929. doi:10.29130/dubited.1460576

Chicago

Karaagac, Mehmet Onur. 2024. “Drying of Nettle Using Concentrated Air Collector and Concentrated Photovoltaic Thermal Supported Drying System and Modeling With Machine Learning”. Duzce University Journal of Science and Technology 12 (4): 1913-29. https://doi.org/10.29130/dubited.1460576.

EndNote

Karaagac MO (October 1, 2024) Drying of Nettle Using Concentrated Air Collector and Concentrated Photovoltaic Thermal Supported Drying System and Modeling with Machine Learning. Duzce University Journal of Science and Technology 12 4 1913–1929.

IEEE

[1]M. O. Karaagac, “Drying of Nettle Using Concentrated Air Collector and Concentrated Photovoltaic Thermal Supported Drying System and Modeling with Machine Learning”, DUBİTED, vol. 12, no. 4, pp. 1913–1929, Oct. 2024, doi: 10.29130/dubited.1460576.

ISNAD

Karaagac, Mehmet Onur. “Drying of Nettle Using Concentrated Air Collector and Concentrated Photovoltaic Thermal Supported Drying System and Modeling With Machine Learning”. Duzce University Journal of Science and Technology 12/4 (October 1, 2024): 1913-1929. https://doi.org/10.29130/dubited.1460576.

JAMA

1.Karaagac MO. Drying of Nettle Using Concentrated Air Collector and Concentrated Photovoltaic Thermal Supported Drying System and Modeling with Machine Learning. DUBİTED. 2024;12:1913–1929.

MLA

Karaagac, Mehmet Onur. “Drying of Nettle Using Concentrated Air Collector and Concentrated Photovoltaic Thermal Supported Drying System and Modeling With Machine Learning”. Duzce University Journal of Science and Technology, vol. 12, no. 4, Oct. 2024, pp. 1913-29, doi:10.29130/dubited.1460576.

Vancouver

1.Mehmet Onur Karaagac. Drying of Nettle Using Concentrated Air Collector and Concentrated Photovoltaic Thermal Supported Drying System and Modeling with Machine Learning. DUBİTED. 2024 Oct. 1;12(4):1913-29. doi:10.29130/dubited.1460576

Drying of Nettle Using Concentrated Air Collector and Concentrated Photovoltaic Thermal Supported Drying System and Modeling with Machine Learning

Abstract

Keywords

Yoğunlaştırılmış Havalı Kolektör ve Yoğunlaştırılmış Fotovoltaik Termal Destekli Bir Kurutma Sistemi ile Isırgan Otunun Kurutulması ve Sistem Verilerinin Makine Öğrenmesi ile Modellenmesi

Abstract

Keywords

References

Details

Primary Language

Subjects

Journal Section

Authors

Publication Date

Submission Date

Acceptance Date

Published in Issue

DOI

IZ

Cite