مطالعه‌ معماری‌های مختلف شبکه‌ عصبی مصنوعی در مدل‌سازی لخته‌سازی سویه‌ Chlorella sp. توسط کلرید آهن (III)

نوع مقاله : مقاله پژوهشی

نویسندگان

1 گروه صنایع شیمیایی دانشگاه ملی مهارت ، تهران، ایران

2 دانشکده مهندسی شیمی، دانشگاه صنعتی امیرکبیر

چکیده

 هدف:  ریزجلبک‌ها به عنوان منابع زیستی فوتوسنتزکننده، پتانسیل بالایی برای تولید سوخت‌های زیستی از جمله بیودیزل دارند. با این حال، جداسازی زیست‌توده از محیط کشت، یکی از مراحل پرهزینه و چالش‌برانگیز در فرآیند بهره‌برداری صنعتی محسوب می‌شود. در میان روش‌های موجود، لخته‌سازی به عنوان یک روش کارآمد، سریع و مقرون به صرفه برای برداشت زیست‌توده مطرح است. هدف این پژوهش، بررسی فرآیند لخته‌سازی گونه‌ی Chlorella sp. با استفاده از کلرید آهن (III) و مدلسازی آن با بهره‌گیری از شبکه‌های عصبی مصنوعی برای پیش‌بینی دقیق بازده فرآیند است.
مواد و روش ها:   در این مطالعه، لخته‌سازی گونه‌ی Chlorella sp. در شرایط مختلف شامل تغییرات pH، غلظت سلولی (OD) و میزان ماده‌ی لخته‌کننده (FeCl₃) انجام شد. داده‌های تجربی حاصل با سه معماری متفاوت شبکه‌ی عصبی شامل پرسپترون چندلایه (MLP)، تابع پایه‌ی شعاعی (RBF) و مدل ترکیبی (Ensemble MLP) مدل‌سازی گردید. داده‌ها به دو بخش آموزش (۷۰٪) و آزمون (۳۰٪) تقسیم شده و عملکرد مدل‌ها بر اساس شاخص‌های آماری ضریب تعیین (R²) و میانگین مربعات خطا (MSE) مورد ارزیابی قرار گرفت.
نتایج: مدل‌های MLP و RBF به‌صورت مستقل قادر به پیش‌بینی دقیق رفتار فرآیــند نبودند، در حالی که مدل ترکیبی (Ensemble MLP) بالاتــرین دقت پیـش‌بینی را با R² = ‎96.37%‎ و MSE = ‎0.0035‎ به دست آورد. مقادیر R² برای مدل‌های MLP در بازه‌ی 92.5 تا 94.5 درصد و برای مدل RBF برابر 79.8 درصد بود. مدل ترکیبی با کاهش قابل توجه خطا و افزایش قابلیت تعمیم، توانست تغییرات غیرخطی و پیچیده‌ی فرآیند لخته‌سازی را با دقت بالا بازتولید کند.
نتیجه‌گیری:  استفاده از شبکه‌های عصبی ترکیبی، دقت و قابلیت تعمیم بالاتری نسبت به مدل‌های منفرد در پیش‌بینی فرآیندهای زیستی پیچیده نظیر لخته‌سازی میکروجلبک‌ها دارد. نتایج این مطالعه نشان می‌دهد که معماری Ensemble MLP می‌تواند به عنوان یک ابزار هوشمند در طراحی، کنترل و بهینه‌سازی فرآیندهای جداسازی زیست‌توده و تولید سوخت‌های زیستی مورد استفاده قرار گیرد.

کلیدواژه‌ها


 
1)  C.E. Richards, R.C. Lupton, J.M. Allwood, Re-framing the threat of global warming: an empirical causal loop diagram of climate change, food insecurity and societal collapse, Climatic Change 164 (3) (2021) 49. https://doi.org/10.1007/s10584-021-02957-w.
 
2) S.A. Montzka, E.J. Dlugokencky, J.H. Butler, Non-CO2 greenhouse gases and climate change, Nature 476(7358) (2011) 43-50. https://doi.org/10.1038/nature10322.
 
3) W. Zhou, Concept and Framework of the East Asian Low-Carbon Community, in: W. Zhou, X. Qian, K.i. Nakagami (Eds.), East Asian Low-Carbon Community: Realizing a Sustainable Decarbonized Society from Technology and Social Systems, Springer Singapore, Singapore, 2021, pp. 61-81. https://doi.org/10.1007/978-981-33-4339-9_3.
 
4) R.E.H. Sims, H.-H. Rogner, K. Gregory, Carbon emission and mitigation cost comparisons between fossil fuel, nuclear and renewable energy resources for electricity generation, Energy Policy 31(13) (2003) 1315-1326. https://doi.org/10.1016/S0301-4215(02)00192-1.
 
5) H. Cheng, Y. Liu, Z. Deng, C. Yang, X. Xie, H. Baloch, W. Xu, H. Zhang, J. Gao, Z. Qin, A. Jaleel, M. Ren, The potential microalgae-based strategy for attaining carbon neutrality and mitigating climate change: a critical review, Frontiers in Marine Science Volume 12 - 2025 (2025). https://doi.org/10.3389/fmars.2025.1644390.
 
6) H. Wang, J. Liu, K. Phyu, Y.a. Cao, X. Xu, J. Liang, C.-C. Chang, K. Zhang, S. Zhi, Microalgae create a highway for carbon sequestration in livestock wastewater: Carbon sequestration capacity, sequestration mechanisms, influencing factors, and prospects, Science of The Total Environment 956 (2024) 177282. https://doi.org/10.1016/j.scitotenv.2024.177282.
 
7) M. Gharabaghi, H. Delavai Amrei, A. Moosavi Zenooz, J. Shahrivar Guzullo, F. Zokaee Ashtiani, Biofuels: Bioethanol, Biodiesel, Biogas, Biohydrogen from Plants and Microalgae, in: E. Lichtfouse, J. Schwarzbauer, D. Robert (Eds.), CO2 Sequestration, Biofuels and Depollution, Springer International Publishing, Cham, 2015, pp. 233-274. https://doi.org/10.1007/978-3-319-11906-9_6.
 
8) F. Kanwal, A. Aslam, A.A.J. Torriero, Microalgae-based biodiesel: integrating AI, CRISPR and nanotechnology for sustainable biofuel development, Emerging Topics in Life Sciences 131-143(2025) (3) 8. https://doi.org/10.1042/etls20240004.
 
9) R.H. Wijffels, M.J. Barbosa, An outlook on microalgal biofuels, Science 329(5993) (2010) 796-9.
 
10) B. Barati, K. Zeng, J. Baeyens, S. Wang, M. Addy, S.-Y. Gan, A. El-Fatah Abomohra, Recent progress in genetically modified microalgae for enhanced carbon dioxide sequestration, Biomass and Bioenergy 145 (2021) 105927. https://doi.org/10.1016/j.biombioe.2020.105927.
 
11) D.P. Krishna Samal, L.B. Sukla, Unveiling the dual potential of microalgae and seaweed biomass for sustainable biofuel production: a review, RSC Advances 15(41) (2025) 34160-34175. https://doi.org/10.1039/D5RA04845A.
 
12) P.P. Borthakur, P. Sarmah, Emerging Catalysts and Techniques in Microalgae-Based Biodiesel Production, Chemistry Proceedings 17(1) (2025) 9.
 
13) A.I. Adetunji, S.f.T. Gumbi, M. Erasmus, Harnessing the potential of microalgae in sequestration of CO2 emissions: Removal mechanisms, optimization strategies, and bioenergy production, Journal of Hazardous Materials Advances 18 (2025) 100722. https://doi.org/10.1016/j.hazadv.2025.100722.
 
14) G. Torzillo, A. Vonshak, Handbook of Microalgal Culture: Applied Phycology and Biotechnology, Second Edition, 2013, pp. 90-113. https://doi.org/10,1002/9781118567166.ch6.
 
15) A.S. Japar, M.S. Takriff, N.H. Mohd Yasin, Microalgae acclimatization in industrial wastewater and its effect on growth and primary metabolite composition, Algal Research 53 (2021) 102163. https://doi.org/10. 1016/j.algal.2020.102163.
 
[6) A. Moosavi Zenooz, F. Zokaee Ashtiani, R. Ranjbar, N. Javadi, Synechococcus sp. (PTCC 6021) cultivation under different light irradiances-Modeling of growth rate-light response, Prep Biochem Biotechnol 46(6) (2016) 567-74.
 
17) M.I. Khan, J.H. Shin, J.D. Kim, The promising future of microalgae: current status, challenges, and optimization of a sustainable and renewable industry for biofuels, feed, and other products, Microbial Cell Factories 17(1) (2018) 36. https://doi.org/10,1186/s12934-018-0879-x.
 
18) K. Heeley, R.L. Orozco, L.E. Macaskie, J. Love, B. Al-Duri, Supercritical water gasification of microalgal biomass for hydrogen production-A review, International Journal of Hydrogen Energy 49 (2024) 310-336. https://doi.org/10.1016/j.ijhydene.2023.08.081.
 
19) G. Muhammad, M.A. Alam, M. Mofijur, M.I. Jahirul, Y. Lv, W. Xiong, H.C. Ong, J. Xu, Modern developmental aspects in the field of economical harvesting and biodiesel production from microalgae biomass, Renewable and Sustainable Energy Reviews 135 (2021) 110209. https://doi.org/10.1016/j.rser.2020.110209.
 
20)chloride coupled with polysilicate aluminum ferrite, Environ Technol 39(1) (2018) 83-90.
 
21) X. Álvarez, A. Jiménez, Á. Cancela, E. Valero, Á. Sánchez, Harvesting freshwater algae with tannins from the bark of forest species: Comparison of methods and pelletization of the biomass obtained, Chemosphere 268 (2021) 129313. https://doi.org/10.1016/j.chemosphere.2020.129313.
 
22) D. Vandamme, I. Foubert, K. Muylaert, Flocculation as a low-cost method for harvesting microalgae for bulk biomass production, Trends in Biotechnology 31(4) (2013) 233-239. https://doi.org/10.1016/j.tibtech.2012.12.005.
 
23) S. Malik, F. Khan, Z. Atta, N. Habib, M. Haider, N. Wang, M.A. Alam, E. Jambi, M. Gull, M. Mehmood, H. Zhu, Microalgal flocculation: Global research progress and prospects for algal biorefinery, Biotechnology and Applied Biochemistry 67 (2019). https://doi.org/10.1002/bab.1828.
 
24) C.N. Ogbonna, E.G. Nwoba, Bio-based flocculants for sustainable harvesting of microalgae for biofuel production. A review, Renewable and Sustainable Energy Reviews 139 (2021) 110690. https://doi.org/10.1016/j.rser.2020.110690.
 
25) Z. Gojkovic, A. Skrobonja, V. Radojicic, B. Mattei, The Use of Flocculation as a Preconcentration Step in the Microalgae Harvesting Process, Physiologia Plantarum 177 (4) (2025) e70366. https://doi.org/10.1111/ppl.70366.
 
26) I. Rodriguez-Garcia, J.L. Guil-Guerrero, Evaluation of the antioxidant activity of three microalgal species for use as dietary supplements and in the preservation of foods, Food Chemistry 108(3) (2008) 1023-1026. https://doi.org/10.1016/j.foodchem.2007.11.059.
 
27) H. Delavari Amrei, R. Ranjbar, S. Rastegar, B. Nasernejad, A. Nejadebrahim, Using fluorescent material for enhancing microalgae growth rate in photobioreactors, Journal of Applied Phycology 27(1) (2015) 67-74. https://doi.org/10.1007/s10811-014-0305-7.
 
28) G. Mujtaba, W. Choi, C.-G. Lee, K. Lee, Lipid production by Chlorella vulgaris after a shift from nutrient-rich to nitrogen starvation conditions, Bioresource Technology 123 (2012) 279-283. https://doi.org/10.1016/j.biortech.2012.07.057.
 
29) R. Eldridge, D. Hill, B. Gladman, A comparative study of the coagulation behaviour of marine microalgae, Journal of Applied Phycology 24 (2012). https://doi.org/10.1007/s10811-012-9830-4.
 
30) R.K. Henderson, S.A. Parsons, B. Jefferson, Successful Removal of Algae through the Control of Zeta Potential, Separation Science and Technology 43(7) (2008) 1653-1666. https://doi.org/10.1080/01496390801973771.
 
31) Y. Shen, Y. Cui, W. Yuan, Flocculation optimization of microalga Nannochloropsis oculata, Appl Biochem Biotechnol 169(7) (2013) 2049-63.
 
32) F. Mohseni, A. Moosavi Zenooz, Flocculation of Chlorella vulgaris with alum and pH adjustment, Biotechnology and Applied Biochemistry n/a(n/a) (2021). https://doi.org/10.1002/bab.2182.
 
33) M. Trovão, A. Barros, A. Machado, A. Reis, H. Pedroso, G. Espírito Santo, N. Correia, M. Costa, S. Ferreira, H. Cardoso, J. Varela, J. Silva, H. Pereira, F. Freitas, Heterotrophic cultivation of Chlorella vulgaris yellow mutant on sidestreams: Medium formulation and process scale-up, Journal of Environmental Chemical Engineering 13(2) (2025) 115361. https://doi.org/10.1016/j.jece.2025.115361.
 
34) S.H. CHO, S.-C. JI, S.B. HUR, J. BAE, I.-S. PARK, Y.-C. SONG, Optimum temperature and salinity conditions for growth of green algae Chlorella ellipsoidea and Nannochloris oculata, Fisheries Science 73(5) (2007) 1050-1056- https://doi.org/10.1111/j.1444-2906.2007.01435.x.
 
35) A. Converti, A.A. Casazza, E.Y. Ortiz, P. Perego, M. Del Borghi, Effect of temperature and nitrogen concentration on the growth and lipid content of Nannochloropsis oculata and Chlorella vulgaris for biodiesel production, Chemical Engineering and Processing: Process Intensification 48(6) (2009) 1146-1151. https://doi.org/10.1016/j.cep.2009.03.006.
 
36) R.L. Taylor, J.D. Rand, G.S. Caldwell, Treatment with Algae Extracts Promotes Flocculation, and Enhances Growth and Neutral Lipid Content in Nannochloropsis oculata—a Candidate for Biofuel Production, Marine Biotechnology 14(6) (2012) 774-781. https://doi.org/10.1007/s10126-012-9441-8.
 
37) Y. Jiang, T. Yoshida, A. Quigg, Photosynthetic performance, lipid production and biomass composition in response to nitrogen limitation in marine microalgae, Plant Physiology and Biochemistry 54 (2012) 70-77. https://doi.org/10.1016/j.plaphy.2012.02.012.
 
38) Standard Practice for Coagulation-Flocculation Jar Test of Water, ASTM D-2035, 1999, pp. 1-4.
 
39) A.M. Zenooz, F.Z. Ashtiani, R. Ranjbar, F. Nikbakht, O. Bolouri, Comparison of different artificial neural network architectures in modeling of Chlorella sp. flocculation, Preparative Biochemistry & Biotechnology 47(6) (2017) 570-577. https://doi.org/10.1080/10826068.2016.1275013.
 
40) W. Brostow, H. Hagg Lobland, R. Singh, Polymeric flocculants for wastewater and industrial effluent treatment, Journal of Materials Education Pal and Singh Journal of Materials Education 31 (2009) 3-4.
41) Z.-H. Zhou, J. Wu, W. Tang, Ensembling neural networks: Many could be better than all, Artificial Intelligence 137(1) (2002) 239-263. https://doi.org/10.1016/S0004-3702(02)00190-X.
 
42) S. Hashem, Optimal Linear Combinations of Neural Networks, Neural Networks 10(4) (1997) 599-614. https://doi.org/10.1016/S0893-6080(96)00098-6.
 
43) T.G. Dietterich, Ensemble Methods in Machine Learning, Multiple Classifier Systems, Springer Berlin Heidelberg, Berlin, Heidelberg, 2000, pp. 1-15.
 
44) J.S. Jaganathan, S.R.S. Abdullah, S.N.A. Sanusi, N.N. Ramli, J. Alias, S.V. Subramaniam, N.M. Daud, F.A. Buslima, N.S.M. Said, J. Buhari, S.S.N. Sharuddin, S.B. Kurniawan, Machine learning and explainable artificial intelligence in coagulation–flocculation: A contemporary review, Journal of Environmental Chemical Engineering 13(6) (2025) 119664. https://doi.org/10.1016/j.jece.2025.119664.
 
45) A.O. Bankole, R. Moruzzi, R.G. Negri, J. Bridgeman, S. Sharifi, Image-based machine learning applications for flocculation modelling in water treatment: Prospects towards automation, Journal of Hazardous Materials Advances 19 (2025) 100870. https://doi.org/10.1016/j.hazadv.2025.100870.
 
46) T. Syed, F. Krujatz, Y. Ihadjadene, G. Mühlstädt, H. Hamedi, J. Mädler, L. Urbas, A review on machine learning approaches for microalgae cultivation systems, Computers in Biology and Medicine 172 (2024),108248. https://doi.org/10.1016/j.compbiomed.2024.108248.
 
47) M.D. Lind, Crystal Structure of Ferric Chloride Hexahydrate, Journal of Chemical Physics 47 (1967) 990-993.
 
48) S. Hashem, B. Schmeiser, Improving Model Accuracy using Optimal Linear Combinations of Trained Neural Networks, Neural Networks, IEEE Transactions on 6 (1995) 792-794. https://doi.org/10.1109/72.377990.