استفاده از شبکه عصبی مصنوعی به منظور مدلسازی فرایند بیولیچینگ فلزات با ارزش از خاکستر سوخت نفت کوره با استفاده از باکتری اسیدی تیوباسیلوس فرواکسیدانس

نوع مقاله : علمی - پژوهشی

نویسندگان

گروه مهندسی شیمی، دانشکده مهندسی، دانشگاه کردستان، سنندج، ایران

چکیده

در این مطالعه مدلسازی بیولیچینگ فلزات باارزش وانادیوم، نیکل و مس موجود در خاکسترهای سوخت نفت‌کوره با استفاده شبکه‌های عصبی مصنوعی بررسی می‌شود. در مدل‌های به‌دست‌آمده، درصد استخراج فلزات به‌عنوان تابعی از فاکتورهای pH (در بازه 1- 5/2)، غلظت اولیه یون Fe2+ (در بازه 0- 9 گرم بر لیتر)، درصد تلقیح باکتری (در بازه 1- 10 %) و زمان (در بازه 0- 15 روز) فرایند مورد بررسی قرارگرفته است. سه مدل شبکه عصبی برای تخمین درصد استخراج هریک از فلزات ارائه شد. از روش پس انتشار خطا و الگوریتم لونبرگ-مارکورت برای آموزش شبکه استفاده شد. یک‌چهارم داده‌ها در فرایند آموزش شبکه عصبی استفاده نشد و برای ارزیابی مدل مورد استفاده قرار گرفت. متوسط خطای نسبی (MRE) برای وانادیوم، نیکل و مس به ترتیب برابر با % 35/5، % 07/3 و % 82/2 به دست آمد. همچنین مقدار بزرگ‌تر از 99/0 از کسر مطلق واریانس (R2) بیانگر تائید اعتبار مدل‌های به دست آمده از شبکه عصبی می‌باشد.

کلیدواژه‌ها


عنوان مقاله [English]

Using Artificial Neural Network to modeling of valuable metals bioleaching from fuel oil fly ash using Acidithiobacillus ferrooxidans

نویسندگان [English]

  • Seyed Omid Rastegar
  • Reza Beigzadeh
Chemical engineering group, University of Kurdistan
چکیده [English]

In this study, the modeling of vanadium, nickel and copper bioleaching from fuel oil ash ash using artificial neural networks was investigated. In the obtained models, the extraction percentage of metals was investigated as a function of factors such as initial pH (from 1-2.5), initial Fe2+ concentration (from 0 – 9 g/l), initial bacterial inoculation (from 1 – 10%) and process time (from 0-15 day). Three neural network models were presented to estimate the extraction percentage of metals. The propagation error method and Levenberg–Marquardt algorithm were used for training. Furthermore, trial and error method was used to determine the optimal number of neurons. One quarter of the data were used to evaluate the model and were not used for training process. The Mean Relative Errors (MRE) were obtained 5.35%, 3.07% and 2.82% for V, Ni and Cu, respectively. Also the higher 0.99 of R2 indicates the validity of the obtained models.

کلیدواژه‌ها [English]

  • Modeling
  • Bioleaching
  • Artificial Neural Networks
  • fuel oil ash
منابع [1] J. C. Lee, B. D. Pandey (2012) “Bio-processing of solid wastes and secondary resources for metal extraction–a review”, Waste management, 32(1), 3-18## [2]‌ M. V. Tsygankova, V. I. Bukin, E. I. Lysakova, A. G. Smirnova, A. M.Reznik (2011) “The recovery of vanadium from ash obtained during the combustion of fuel oil at thermal power stations”, Russian Journal of Non-Ferrous Metals, 52(1), 19-23## [3] M. Vijayakumar, , L. Li, , G. Graff, , J. Liu, , H. Zhang, , Z. Yang, , J. Z. Hu, (2011) “Towards understanding the poor thermal stability of V5+ electrolyte solution in vanadium redox flow batteries”, Journal of Power Sources, 196(7), 3669-3672## [4] Y. M. Zhang, S. X. Bao, T. Liu, T. J. Chen, J. Huang (2011) “The technology of extracting vanadium from stone coal in China: History, current status and future prospects:, Hydrometallurgy, 109(1-2), 116-124## [5] T. Gu, S. O. Rastegar, S. M. Mousavi, M. Li, M. Zhou (2018), “Advances in bioleaching for recovery of metals and bioremediation of fuel ash and sewage sludge, Bioresource technology, 261, 428-440.## [6] M. Ijadi Bajestani, , S. M. Mousavi, S. A. Shojaosadati (2014) “Bioleaching of heavy metals from spent household batteries using Acidithiobacillus ferrooxidans: statistical evaluation and optimization”, Separation and Purification Technology, 132, 309-316.## [7] S. Ilyas, J. C. Lee, B. S. Kim (2014), “Bioremoval of heavy metals from recycling industry electronic waste by a consortium of moderate thermophiles: process development and optimization”, Journal of Cleaner Production, 70, 194-202.## [8] P. Rasoulnia, S. M. Mousavi, S. O. Rastegar, H. Azargoshasb (2016) “Fungal leaching of valuable metals from a power plant residual ash using Penicillium simplicissimum: Evaluation of thermal pretreatment and different bioleaching methods”, Waste management, 52, 309-317.## [9] S. O. Rastegar, S. M. Mousavi, S. A. Shojaosadati, T. Gu (2016), “Bioleaching of fuel-oil ash using Acidithiobacillus thiooxidans in shake flasks and a slurry bubble column bioreactor”, RSC Advances, 6(26), 21756-21764## [10] B. E. Taştan (2017), “Clean up fly ash from coal burning plants by new isolated fungi Fusarium oxysporum and Penicillium glabrum”, Journal of environmental management, 200, 46-52## [11] H. Abdollahi, M. Noaparast, S.Z. Shafaei, A. Akcil, S. Panda, M. Hazrati Kashi, P. Karimi (2019), “Prediction and optimization studies for bioleaching of molybdenite concentrate using artificial neural networks and genetic algorithm”, Minerals Engineering, 130, 24-35. ## [12] S. O. Rastegar, S. M. Mousavi, S. A. Shojaosadati, R. S. Mamoory (2015), “Bioleaching of V, Ni, and Cu from residual produced in oil fired furnaces using Acidithiobacillus ferrooxidans”, Hydrometallurgy, 157, 50-59## [13] M. T. Hagan, H. B. Demuth, M. H. Beale, O. De Jesús (1996) “Neural network design” , Vol. 20, Boston: Pws Pub., USA. ## [14] M. A. Hussain (1999) “Review of the applications of neural networks in chemical process control—simulation and online implementation”, Artificial intelligence in engineering, 13(1), 55-68## [15] G. Cybenko (1989) “Approximation by superpositions of a sigmoidal function”, Mathematics of control, signals and systems, 2(4), 303-314.## [16] M. T. Hagan, M. B. Menhaj (1994), “Training feedforward networks with the Marquardt algorithm”, IEEE transactions on Neural Networks, 5(6), 989-993## [17] R. Eslamloueyan, M. H. Khademi (2010) “A neural network-based method for estimation of binary gas diffusivity”, Chemometrics and Intelligent Laboratory Systems, 104(2), 195-204.## [18] M. Izadi, M. Rahimi, R. Beigzadeh (2019), “Evaluation of micromixing in helically coiled microreactors using artificial intelligence approaches”, Chemical Engineering Journal, 356, 570-579.## [19] R. Beigzadeh, S.O. Rastegar (2020), Assessment of Cr (VI) biosorption from aqueous solution by artificial intelligence”, Chemical Methodologis, 4, 181-190.##