مدل‌سازی استخراج فنل از فاضلاب با استفاده از روش‌های هوشمند

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشجوی کارشناسی ارشد مهندسی شیمی، دانشگاه علم و صنعت ایران، تهران، ایران

2 استادیار، دانشکده مهندسی شیمی، دانشگاه علم وصنعت ایران، تهران، ایران

3 دانشیار، دانشکده مهندسی شیمی، دانشگاه علم وصنعت ایران، تهران، ایران

چکیده

در این پژوهش فرایند استخراج فنل از فاضلاب با استفاده از روشهای هوشمند مدل‌سازی شد. از روش‌های هوشمند شامل شبکه پرسپترون چندلایه، شبکه بر پایه توابع شعاعی و ماشین بردار رگرسیونی برای مدل‌سازی استفاده‌ شد. طراحی ساختار بهینه شبکه‌ها از 184 مجموعه داده تجربی انجام شد. ورودی‌های شبکه شامل حجمی آلی به آبی، سرعت روتور، دما، pH و زمان و خروجی شبکه‌ بازده استخراج فنل بود. برای ارزیابی عملکرد و توقف شبکه‌ها از ضریب تعیین و میانگین مربع خطا برای هر سه مدل استفاده ‌شد. مقایسه نتایج کلیه مدل‌ها نشان داد که مدل ماشین بردار رگرسیونی با میانگین مربع خطا برابر 684/0 و ضریب بهترین مدل است. پارامترهای بهینه فرایند شامل نسبت حجمی آلی به آبی 22/0، سرعت روتور 350 دور در دقیقه، دما 86/22 درجه سلسیوس،pH  برابر 7/5، زمان 86/15 دقیقه و بازده استخراج متناظر 35/96 به دست آمد.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Modeling of Phenol Extraction from Wastewater Using Intelligent Techniques

نویسندگان [English]

  • Mohsen Keshavarz Tork 1
  • Ahad Ghaemi 2
  • Mansour Shirvani 3
1 MSc Student of Chemical Engineering, Iran University of Science and Technology (IUST), Tehran, Iran
2 Ass. Prof. of Chemical Engineering Iran University of Science and Technology (IUST)
3 Assoc. Prof. of Chemical Engineering, Iran University of Science and Technology (IUST), Tehran, Iran
چکیده [English]

In this study, the extraction of phenol from wastewater was simulated using intelligent methods which include multi-layer perceptron, radial basis functions network, and support vector regression. To design the network structure and to train and test it, 184 experimental data sets were used. Inputs to the network consisted of organic–aqueous volume ratio, rotor speed, temperature, pH, and time while extraction efficiency was the output. Root mean square error and correlation coefficient were used in all the three models as network performance and network stop criteria. Comparison of the results obtained from the three models revealed that the support vector regression was the best model with a correlation coefficient of 0.684 and a root mean square error of 0.99. Moreover, model results showed good agreement with experimental data. Optimal process operational parameters included an organic to aqueous volume ratio of 0.22, a rotor speed of 350 rpm, a temperature of 22.86 °C, a pH equal to 7.5, and an agitation time of 15.86 minutes; the corresponding extraction efficiency was obtained to be 96.35.

کلیدواژه‌ها [English]

  • Modeling Phenol Removal
  • Multilayer perceptron network
  • Radial Basis Function Network
  • Support vector regression
1. Khosravi, R., Fazlzadeh, R., Samadi, Z., Mostafavi, H.,Taghizadeh, A.A., and Dorri, H. (2013). “Investigation of phenol absorption from aqueous solution by carbonized service bark and modified-carbonized service bark by ZnO.” Health Magazine, 4 (1), 21-30.
2. Asgari, G., Sidmohammadi, A., Ebrahimi, A., Gholami, Z., and Hosseinzadeh, E. (2010). “Study on phenol removing by using modified zolite (Clinoptilolite) with FeCl3 from aqueous solutions.” Journal of Health System Research, 89, 848-857.
3. Jiang, H., Fang, Y., Fu, Y., and Guo, Q.X. (2003).“Studies on the extraction of phenol in wastewater.” Journal of Hazardous Materials, 101(2), 179-190.
4. Shen, S., Chang, Z., and Liu, H. (2006). “Three-liquid-phase extraction systems for separation of phenol and p-nitrophenol from wastewater.” Separation and Purification Technology, 49(3), 217-222.
5. Daraei, H., Manshouri, M., and Yazdanbakhsh, A.R. (2010). “Removal of phenol from aqueous solution using ostrich feathers ash.” Journal of Mazandaran University Medical Sciences, 20(79), 81-87. (In Persian)
6. Diyanati, R., Yousefi, Z., Yazdani Cherati, J., and Balarak, D. (2013).“Investigating phenol absorption from aqueous solution by dried Azolla.” Journal of Mazandaran University Medical Sciences, 22(2), 13-20. (In Persian)
7. Ghaneian, M.T., and Ghanizadeh, G. (2009). “Application of enzymatic polymerization process for the removal of phenol from synthetic wastewater.” Iranian Journal of Health and Environment, 2(1), 46-55.
8. Senturk, H.B., Ozdes, D., Gundogdu, A., Duran, C., and Soylak, M. (2009). “Removal of phenol from aqueous solutions by adsorption onto organomodified Tirebolu bentonite: Equilibrium, kinetic and thermodynamic study.” Journal of Hazardous Materials, 172(1), 353-362.
9. Piuleac, C.G., Rodrigo, M.A., and Can, P. (2010). “Ten steps modeling of electrolysis processes by using neural networks.” Environmental Modelling and Software, 25, 74-81.
10. Zidi, C., Tayeb, R., Ali, M. B. S., and Dhahbi, M. (2010). “Liquid–liquid extraction and transport across supported liquid membrane of phenol using tributyl phosphate.” Journal of Membrane Science, 360(2), 334-340.
11. Xu, J.Q., Duan, W.H., Zhou, X.Z., and Zhou, J.Z. (2006). “Extraction of phenol in wastewater with annular centrifugal contactors.” Journal of Hazardous Materials, 131(1-3), 98-102.
12. Messikh, N., Samar, M. H., and Messikh, L. (2007). “Liquid–liquid extraction of phenol from wastewater using TBP solvent.” Desalination, 208(1-3), 42-48.
13. Du, K.L., and Swamy, M. N. S. (2006). Neural networks in a softcomputing framework, 2nd Ed., Springer.
14. Hassoun, M. H. (1996). “Fundamentals of artificial neural networks.” Proceedings of the IEEE, New York.
15. Engelbrecht, A. P. (2007). Computational intelligence: An introduction, John Wiley and Sons, New York.
16. Hagan, M.T., and Menhaj, M.B. (1994). “Training feedforward networks with the Marquardt algorithm.” Neural Networks, IEEE Transactions, 5(6), 989-993.
17. MahmoodzadehVaziri, B., and Shahsavand, A. (2013). “Analysis of supersonic separators geometry using generalized radial basis function (GRBF) artificial neural networks.” Journal of Natural Gas Science and Engineering, 13, 30-41.
18. Heydari, M., and Ahmadvand, H. (2009). “Building heating energy estimation radial using neural networks.” National Conf. on Fuel, Energy and the Environmental, Tehran, Iran. (In Persian)
19. Eskandari, A., Noori, R. A., and Kiaghadi, A. (2009). “Development model based on artificial neural network and support vector machine for predicting biochemical oxygen demand during 5 days.” Journal of Ecology, 61, 34-46.
20. Liu, Y., Hu, N., Wang, H., and Li, P. (2009). “Soft chemical analyzer development using adaptive least-squares support vector regression with selective pruning and variable moving window size.” Industrial and Engineering Chemistry Research, 48(12), 5731-5741.
21. Zaidi, S. (2012). “Development of support vector regression (SVR)-based model for prediction of circulation rate in a vertical tube reboiler.” Chemical Engineering Science, 69(1), 514-521.
22. Gandhi, A. B., and Joshi, J. B. (2010). “Estimation of heat transfer coefficient in bubble column reactors using support vector regression.” Chemical Engineering Journal, 160(1), 302-310.
23. Alves, J. C. L., Henriques, C. B., and Poppi, R. J. (2012). “Determination of diesel quality parameters using support vector regression and near infrared spectroscopy for an in-line blending optimizer system.” Fuel, 97, 710-717.
24. Treybal, R. E. (1968). Mass-transfer operations, 2nd Ed., McGraw-Hill, New York.
25. Lashkarbolooki, M., Shafipour, Z. S., and Hezave, A. Z. (2013). “Trainable cascade-forward back-propagation network modeling of spearmint oil extraction in a packed bed using SC-CO2.” The Journal of Supercritical Fluids, 73, 108-115.
26. Khajeh, M., and Barkhordar, A. (2013). “Modelling of solid-phase tea waste extraction for the removal of manganese from food samples by using artificial neural network approach.” Food Chemistry, 141(2), 712-718.