Investigation of the dehydration of ulexite ore with different parameters and modeling with artificial neural network (ANN) method

KOCADAGISTAN, MUSTAFA ENGIN

doi:10.55730/1300-0527.3531

Investigation of the dehydration of ulexite ore with different parameters and modeling with artificial neural network (ANN) method

MUSTAFA ENGIN KOCADAGISTAN (Atatürk Üniversitesi, Mühendislik Fakültesi, Metalurji ve Malzeme Mühendisliği Bölümü, Erzurum, Türkiye)

Turkish Journal of Chemistry

3 0

Yıl: 2023 Cilt: 47 Sayı: 1 Sayfa Aralığı: 218 - 231 Metin Dili: İngilizce DOI: 10.55730/1300-0527.3531 İndeks Tarihi: 13-03-2023

Investigation of the dehydration of ulexite ore with different parameters and modeling with artificial neural network (ANN) method

Öz:

Study experiments were conducted considering the temperature, time, and sample weight parameters in order to model the dehydration by applying dehydration processes to ulexite ores. Data obtained from the dehydration processes of ulexite ore were compared with TG analyzes. It was observed as the result of the heat treatment that the fastest water removal was provided in the temperature range of 150–250 °C and it was very low in the range of 400–750 °C. In order to design the ANN method, 4 different models were proposed with the same parameters in the dehydration experiments and the network structure was determined. The performance of the ANN model was assessed by means of error measurements i.e. absolute error (AE), absolute relative error (ARE) and coefficient of determination $(R^2)$. The mean value of $R^2$ was 99%. It was found that the independent variables explained the dependent variable efficiently and the models were very successful. It was shown that the new models can be created using genetic algorithms or hybrid methods in the future studies requiring fewer experiments by following the same process in the present study.

Anahtar Kelime: Ulexite dehydration ANN modeling heat treatment

Belge Türü: Makale Makale Türü: Araştırma Makalesi Erişim Türü: Erişime Açık

1. Helvacı C. Bor yataklarının mineral ve kimyası yönünden genel değerlendirilmesi ve gelecek öngörüsü. Madencilik ve Yer Bilimleri Dergisi 1 Haziran 2015; 6 (47). www.madencilik-turkiye.com (in Turkish with an abstract in English).
2. Helvacı C. Borate deposits: An overview and future forecast with regard to mineral deposits. Bor Dergisi (Journal of Boron) 2017; Boron 2 (2): 59 – 70.
3. Çelik MS, Uzunoğlu HA, Arslan F. Decrepitation properties of some boron minerals. Powder Technology 1994; 79: 167-172. https://doi. org/10.1016/0032-5910(94)02811-7
4. Tunç M, Erşahan H, Yapıcı S, Çolak S. Dehydration kinetics of ulexite from thermogravimetric data. Journal of Thermal Analysis and Calorimetry 1997; 48: 403-411.
5. Şener S, Özbayoğlu G, Demirci Ş. Changes in the structure of ulexite on heating. Thermochimica Acta 2000; 362: 107-112. https://doi. org/10.1016/S0040-6031(00)00584-0
6. Çelik H. Üleksit cevherinin perklorik asit çözeltilerindeki çözünürleştirme kinetiği, kalsinasyonu ve optimizasyonu. Yüzüncüyıl Üniversitesi, Fen Bilimleri Enstitüsü 2007; (in Turkish with an abstract in English).
7. Buluttekin MB. Bor madeni ekonomisi, Türkiye’nin dünya bor piyasasındaki yeri. 2. Ulusal İktisat Kongresi; DEÜ İİBF İktisat Bölümü, İzmir, Türkiye; 20-22 Şubat 2008 (in Turkish).
8. Kayandan İ, Pehlevan V, Çağlayan B, Türedi S. Düşük tenörlü kolemanit cevherinin kalsinasyon yöntemi ile zenginleştirilmesi. Uluslararası Bor Sempozyumu, Eskişehir, Türkiye; 23-25 Eylül 2004 (in Turkish with an abstract in English).
9. Allen RD. DTA’s of selected borate minerals. U.S. Geol. Survey. Bull. 1957; 1038-K.
10. Griswold WT. Method of calcining and classifying of borates. U.S. Patent 1970; 3.309.170.
11. Davies TW, Çolak S, Hooper RM. Boric acid production by the calcination and leaching of powdered colemanite. Powder Technology 1991; 65: 433-440. https://doi.org/10.1016/0032-5910(91)80204-V
12. Erşahan H, Tunç M, Ekmekyapar A, Yapıcı S. Flash dehydration of ulexite and investigation of dehydration kinetics from thermogravimetric data. Thermochimica Acta. 1995; 250: 125. https://doi.org/10.1016/0040-6031(94)01978-P
13. Özbayoğlu G. Üleksit ve kolemanit tozlarının, kalsinasyon ürünlerinin ve boraks pentahidratın biriketlenmesi. TUBİTAK Yer-Deniz- Atmosfer Bilimleri ve Çevre Araştırma Grubu YDABÇAĞ-138 No’lu Proje, Ankara Kasım-1997 (in Turkish).
14. Şener S, Özbayoğlu G. Üleksitin kalsinasyon özelliklerinin tespiti ve üleksit-kolemanit ayrılmasında kalsinasyonun kullanımı, Bor Mineralleri Zenginleştirme Semineri Bildirileri, Bornova, 22 Nisan 1994; 47-57 (in Turkish).
15. Şener S, Özbayoğlu G. Separation of ulexite from colemanite by calcination. Minerals Engineering 1995; 8 (6): 697-704.
16. Hoskan S. The calcination behavior of fine-sized colemanite and ulexite ore under conventional heat treatment. IJSEC 2019; 9 (7) http:// ijesc.org/.
17. Gülensoy H, Teberdar HT. Studies on tunellite (strontium borate) mineral. Bulletin of the Mineral Research and Exploration Institute of Turkey 1972; 79: 30.
18. Gülensoy H, Savcı H. Solubilities of some calcium minerals and prepared calcium compounds in EDTA (Ethylene Diamine, Tetraacetic Acid) solutions. Bulletin of the Mineral Research and Exploration Institute of Turkey 1976; 86: 75. https://dergipark.org.tr/en/pub/ bulletinofmre/issue/3912/52138
19. Yanen C, Dağ M, Aydoğmuş E. Investigation of thermophysical properties of colemanite, ulexite, and tincal reinforced polyester composites. European Journal of Science and Technology Special Issue 2022; 36: 155-159. https://doi.org/10.31590/ejosat.1008386
20. Erdoğan Y, Zeybek A, Şahin A, Demirbaş A. Dehydration kinetics of howlite, ulexite, and tunellite using thermogravimetric data. Thermochimica Acta 1999; 326: 99-103. https://doi.org/10.1016/S0040-6031(98)00591-7
21. Ochoa-Martinez CI, Ramaswamy HS, Ayala-Aponte AA. Artificial Neural Network modeling of osmotic dehydration mass transfer kinetics of fruits. Drying Technology 2007; 25: 85–95. https://doi.org/10.1080/07373930601160882
22. Kang HT, Yoon CJ. Neural network approaches to aid simple truss design problems. Microcomputers in Civil Engineering 1994; 9: 211- 218. https://doi.org/10.1111/j.1467-8667.1994.tb00374.x
23. Gonzalez PA, Zamarreno JM. Prediction of hourly energy consumption in buildings based on a feed-back Artificial Neural Network. Energy and Buildings 2005; 37: 595-601. https://doi.org/10.1016/j.enbuild.2004.09.006
24. Kalogirou S, Bojic M. Artificial Neural Networks for the prediction of the energy consumption of a passive solar building. Energy 2000; 25 (5): 479-491. https://doi.org/10.1016/S0360-5442 (99)00086-9
25. Codur MY, Ünal A. An estimation of transport energy demand in Turkey via Artificial Neural Networks. Swarm Intelligence in Transportation Engineering Preliminary Communication Submitted: 22 July 2018, Accepted; 5 Feb. 2019. https://doi.org/10.7307/ptt. v31i2.3041
26. Codur MY, Tortum A. An Artificial Neural Network model for highway accident prediction: A case study of Erzurum, Turkey. Promet – Traffic&Transportation 2015; 27 (3): 217-225. https://doi.org/10.7307/ptt.v27i3.1551
27. Sönmez M, Akgüngör AP, Bektaş S. Estimating transportation energy demand in Turkey using the artificial bee colony algorithm. Energy 2017; 122: 301-310. https://doi.org/10.1016/j.energy.2017.01.074
28. Silva Ribeiro T, Grossi CD, Merma AG, Ferreira dos Santos B, Torem ML. Removal of boron from mining wastewaters by electrocoagulation method: Modelling experimental data using Artificial Neural Networks. Minerals Engineering 2019; 131 (15): 8-13. https://doi. org/10.1016/j.mineng.2018.10.016
29. Elçiçek H, Akdoğan E, Karagöz S. The use of Artificial Neural Network for prediction of dissolution kinetics. Hindawi Publishing Corporation the Scientific World Journal 2014; Article ID 194874, 9 pages. http://dx.doi.org/10.1155/2014/194874
30. Aydoğmuş E, Arslanoğlu H, Dağ M. Production of waste polyethylene terephthalate reinforced biocomposite with RSM design and evaluation of thermophysical properties by ANN. Journal of Building Engineering 2021; 44. https://doi.org/10.1016/j.jobe.2021.103337
31. Wendlandt WM. Thermal methods of analysis, Editors: Elving, P.J., Kolthoff, I.M., Jhon Wiley and Sons, USA (Toronto) 1974.
32. Ewin GW. Instrumental Methods of Chemical Analysis, Fourth Edition, Mc-Graw Hill Book Company, USA (Toronto): 1975.
33. Mackenzie RC. Differantial Thermal Analysis. Academic Press, New York, Vol.1 1970.
34. Ağyar Z. Mühendis ve Makina Dergisi: Mart 2015; 662 (in Turkish). https://www.mmo.org.tr/muhendismakina
35. Codur MY, Tortum A. Erzurum-Pasinler yolu trafik kaza tahmin modeli, Ordu Uni. J. Sci. Tech. 2013; 3 (2): 39-49. https://dergipark.Org. tr/tr/pub/ordubtd/issue/11066/132171 (in Turkish with an abstract in English).
36. Narendra KS, Parthasarathy K. Identification and control of dynamical systems using neural networks. IEEE Transactions on Neural Networks 1990; 1 (1): 4-27. https://doi.org/10.1109/72.80202
37. Fırat M, Güngör M. Askı madde konsantrasyonu ve miktarının yapay sinir ağları ile Belirlenmesi. İMO Teknik Dergi 2004; 3267-3282: Yazı 219 (in Turkish).
38. Liu Y, Shi P, Chao Q, Jiang M. Efficient acid leaching of high-magnesium boron tailings and the low cost recovery of siliceous residues with good adsorption capacity. Hydrometallurgy 2022; 209, 105827. https://doi.org/10.1016/j.hydromet.2022.105827
39. Darvishvand L, Kamkari B, Kowsary F. Optimal design approach for heating irregular-shaped objects in three-dimensional radiant furnaces using a hybrid genetic algorithm–artificial neural network method. Engineering Optimization 2017; 50 (3): 452-470. https://doi. org/10.1080/0305215X.2017.1323889
40. Karahan İH, Özdemir R, Erkayman B. A comparison of genetic programming and neural networks; new formulations for electrical resistivity of Zn-Fe alloys. Applied Physics A 2013; 113: 459-476. doi: 10.1007/s00339-013-7544-3

APA	KOCADAGISTAN M (2023). Investigation of the dehydration of ulexite ore with different parameters and modeling with artificial neural network (ANN) method. , 218 - 231. 10.55730/1300-0527.3531
Chicago	KOCADAGISTAN MUSTAFA ENGIN Investigation of the dehydration of ulexite ore with different parameters and modeling with artificial neural network (ANN) method. (2023): 218 - 231. 10.55730/1300-0527.3531
MLA	KOCADAGISTAN MUSTAFA ENGIN Investigation of the dehydration of ulexite ore with different parameters and modeling with artificial neural network (ANN) method. , 2023, ss.218 - 231. 10.55730/1300-0527.3531
AMA	KOCADAGISTAN M Investigation of the dehydration of ulexite ore with different parameters and modeling with artificial neural network (ANN) method. . 2023; 218 - 231. 10.55730/1300-0527.3531
Vancouver	KOCADAGISTAN M Investigation of the dehydration of ulexite ore with different parameters and modeling with artificial neural network (ANN) method. . 2023; 218 - 231. 10.55730/1300-0527.3531
IEEE	KOCADAGISTAN M "Investigation of the dehydration of ulexite ore with different parameters and modeling with artificial neural network (ANN) method." , ss.218 - 231, 2023. 10.55730/1300-0527.3531
ISNAD	KOCADAGISTAN, MUSTAFA ENGIN. "Investigation of the dehydration of ulexite ore with different parameters and modeling with artificial neural network (ANN) method". (2023), 218-231. https://doi.org/10.55730/1300-0527.3531

APA	KOCADAGISTAN M (2023). Investigation of the dehydration of ulexite ore with different parameters and modeling with artificial neural network (ANN) method. Turkish Journal of Chemistry, 47(1), 218 - 231. 10.55730/1300-0527.3531
Chicago	KOCADAGISTAN MUSTAFA ENGIN Investigation of the dehydration of ulexite ore with different parameters and modeling with artificial neural network (ANN) method. Turkish Journal of Chemistry 47, no.1 (2023): 218 - 231. 10.55730/1300-0527.3531
MLA	KOCADAGISTAN MUSTAFA ENGIN Investigation of the dehydration of ulexite ore with different parameters and modeling with artificial neural network (ANN) method. Turkish Journal of Chemistry, vol.47, no.1, 2023, ss.218 - 231. 10.55730/1300-0527.3531
AMA	KOCADAGISTAN M Investigation of the dehydration of ulexite ore with different parameters and modeling with artificial neural network (ANN) method. Turkish Journal of Chemistry. 2023; 47(1): 218 - 231. 10.55730/1300-0527.3531
Vancouver	KOCADAGISTAN M Investigation of the dehydration of ulexite ore with different parameters and modeling with artificial neural network (ANN) method. Turkish Journal of Chemistry. 2023; 47(1): 218 - 231. 10.55730/1300-0527.3531
IEEE	KOCADAGISTAN M "Investigation of the dehydration of ulexite ore with different parameters and modeling with artificial neural network (ANN) method." Turkish Journal of Chemistry, 47, ss.218 - 231, 2023. 10.55730/1300-0527.3531
ISNAD	KOCADAGISTAN, MUSTAFA ENGIN. "Investigation of the dehydration of ulexite ore with different parameters and modeling with artificial neural network (ANN) method". Turkish Journal of Chemistry 47/1 (2023), 218-231. https://doi.org/10.55730/1300-0527.3531