مقایسه شبکه‌های عصبی نوع GMDHچند هدفی و شبکه خودباوری بیزین در پیش‌بینی کدورت آب تصفیه شده مطالعه موردی: تصفیه خانه بزرگ آب گیلان

نوع مقاله: مقاله پژوهشی

نویسندگان

1 استادیار، گروه مهندسی شیمی، دانشکده فنی و مهندسی، دانشگاه گیلان، رشت

2 دانشجوی کارشناسی ارشد مهندسی شیمی دانشگاه گیلان، رشت

3 مسئول واحد بهره برداری تصفیه خانه بزرگ آب گیلان

چکیده

آب کافی و با کیفیت مطلوب برای ادامه حیات بشر ضروری است. تصفیه‌خانه‌ها، آب شرب را با کیفیت بالا در کوتاه‌ترین زمان ممکن با حداقل هزینه فراهم می‌کنند. در این مقاله ابتدا متغیرهای تأثیر‌گذار بر فرآیند حذف کدورت آب، با استفاده از روش‌شناسی سطح پاسخ‌ شناسایی گردیده است. در ادامه شبکه‌‌های عصبی نوع GMDH و شبکه خودباوری بیزین برای مدل-سازی و پیش‌بینی کدورت آب تصفیه شده، با استفاده از مجموعه داده‌های ورودی- خروجی مورد مطالعه قرار گرفته است. برای ارزیابی مدل پیشنهادی، تصفیه‌خانه بزرگ آب گیلان به صورت موردی بررسی و داده‌های مورد نیاز شامل 700 سری داده به دست آمده است. به منظور مدل‌سازی داده‌های برگرفته از واحد بهره‌برداری به دو دسته (70% برای آموزش و30% برای آزمایش) تقسیم شده‌اند. نتایج حاصل از مدل‌سازی با داده‌های تجربی مقایسه گردید که ضریب تعیین مقادیرآزمایشی برای دو الگوریتم شبکه خودباوری بیژین شامل EM و GD و برای مدل GMDH به ترتیب 9388/0 ، 9196/0 و 97095/0 بوده است که بر این اساس مدل GMDH نسبت به مدل BBN کارایی بهتری برای پیش‌بینی میزان کدورت آب تصفیه شده دارد.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Comparison of Multi Objective GMDH-type Neural Network and Bayesian Belief Network in the Prediction of Treated Water Turbidity . Case Study: Great Water Treatment Plant in Guilan Province

نویسندگان [English]

  • Allahyar Daghbandan 1
  • Fereshteh Alitaleshi 2
  • Mehran Yaghoobi 3
1 َAss. Prof. of Chemical Engineering, Faculty of Engineering, University of Guilan, Rasht
2 MSc Student of Chemical Engineering,University of Guilan, Rasht
3 Management of Operation Unit of Guilan Water Treatment Plant, RAsht
چکیده [English]

Enough water with proper quality is necessary for life. Drinking Water Treatment Plants (WTPs) have to provide high quality drinking water in the shortest possible time with minimal costs. In this paper, Factors affecting the process for removal of water turbidity using the Response Surface Methodology (RSM) were firstly identified and then GMDH-type Neural Networks and Bayesian Belief Network (BBN) have been used for modeling and prediction of treated water turbidity; using input-output data set. To validate the proposed model, a case study was carried out based on the data consisted of 700 sets obtained from Guilan‌WTP. For modeling, the experimental data obtained from the operation unit were divided into train and test sections (70% for training and 30% for testing). The predicted values were compared with those of experimental values. The determination coefficient of the predicted values for the two BBN algorithms consist of EM and GD, and GMDH model were 0.9388, 0.9196 and 0.97095, respectively. The GMDH model performed better than the BBN model in predicting treated water turbidity dosage.

کلیدواژه‌ها [English]

  • Water Treatment
  • Turbidity
  • Modeling
  • GMDH-NN
  • BBN
1. Chalkosh Amiri, M. (2010). Principes of water treatment, Arkan Danesh Publications, Isfahan. (In Persian)

2. Davis, M. L. (2010). Water and wastewater engineering, design principles and practice, The Mc Graw-Hill  Companies. Inc.,Michigan State University, USA.

3. Water, C.O.D. (2012). Turbidity in drinking water, Federal, Provincial-Territorial Committee, Canada.

4. Gagnon, C., Grandjean, B., and Thibault, J. (1997). “Modelling of coagulant dosage in a water treatment plant.” Artificial Intelligence in Engineering, 11 (4), 401-404.

5. Montgomery, J. M. (1985). Water treatment: Principles and design, Published by John Wiley and Sons Ltd.,New York, USA.

6. Reckhow, K. H. (1999). “Water quality prediction and probability network models.” Canadian Journal of Fisheries and Aquatic Sciences, 56 (7), 1150-1158.

7. Joo, D.-S., Choi, D.-J., and Park, H. (2000). “The effects of data preprocessing in the determination of coagulant dosing rate.” Water Research, 34 (13), 3295-3302.

8. Pike, W. A. (2004). “Modeling drinking water quality violations with bayesian networks.” Journal of the American Water Resources Association(JAWRA), 40 (6), 1563-1578.

9. Benardos, P., and Vosniakos, G.-C. (2007). “Optimizing feedforward artificial neural network architecture.” Engineering Applications of Artificial Intelligence, 20 (3), 365-382.

10. Wu, G. D., and Lo, S. L. (2008). “Predicting real-time coagulant dosage in water treatment by artificial neural networks and adaptive network-based fuzzy inference system.” Engineering Applications of Artificial Intelligence, 21 (8), 1189-1195.

11. Olyaie, E., Banejad, H., Samadi, M. T., Rahmani, A., and Saghi, M. H. (2010). “Performance evaluation of artificial neural networks for predicting rivers water quality indices (BOD and DO) in Hamadan Morad Beik River.” Water and Soil Science,  20 (3), 199-210. (In Persian)

12. Juntunen, P., Liukkonen, M., Pelo, M., Lehtola, M. J., and Hiltunen, Y. (2012). “Modelling of water quality: An application to a water treatment process.” Applied Computational Intelligence and Soft Computing, 2012, (4), doi : 10.1155/2012/846321.

13. Nam, S. W., Jo, B. I., Kim, M.-K., Kim, W.-K., and Zoh, K.-D. (2013). “Streaming current titration for coagulation of high turbidity water.” Colloids and Surfaces A: Physicochemical and Engineering Aspects, 419, 133-139.

14. Daghbandan, A., Akbarizadeh, M., and Yaghoobi, M. (2013). “Modeling and optimization of poly electrolyte dosage in water treatment process by GMDH Type-NN and MOGA.” International Journal of Chemoinformatics and Chemical Engineering (IJCCE), 3 (2), 94-106.

15. Daghbandan, A., Ali Taleshi, F., and Akbari Zadeh, M. (2014). “Modeling of coagulant dosage in water treatment process by artificial neural network.” The 8th International Chemical Engineering Congress and Exhibition (IChEC 2014), Kish, Iran. (In Persian)

 

16. Box, G. E., and Wilson, K. (1951). “On the experimental attainment of optimum conditions.” J. of the Royal Statistical Society Series B (Methodological), 13 (1), 1-45.

17. Khayet, M., Zahrim, A., and Hilal, N. (2011). “Modelling  and optimization of coagulation of highly concentrated industrial grade leather dye by response surface methodology.” Chemical Engineering Journal, 167 (1), 77-83.

18. Ghorbani, F., Younesi, H., Ghasempouri, S. M., Zinatizadeh, A. A., Amini, M., and Daneshi, A. (2008). “Application of response surface methodology for optimization of cadmium biosorption in an aqueous solution by Saccharomyces cerevisiae.” Chemical Engineering Journal, 145 (2), 267-275.

19. Ivakhnenko, A.G. (1971). “Polynomial theory of complex systems.” Systems, Man and Cybernetics, IEEE Transactions on, SMC-1, 4, 364-378.

20. Darvizeh, A., Nariman-Zadeh, N., and Gharababaei, H. (2003). “GMDH-type neural network modelling of explosive cutting process of plates using singular value decomposition.” Systems Analysis Modelling Simulation, 43 (10), 1383-1397.

21. Nariman-Zadeh, N., and Jamali, A. (2007). “Pareto design of GMDH-type neural networks for nonlinear systems.” Proceedings of the International Workshop on Inductive Modelling, Czech Technical University, Prague, Czech Republic, 96-103.

22. Dolenko, S., Orlov, Y. V., and Persiantsev, I.G. (1996). Practical implementation and use of Group Method of data Handling (GMDH): Prospects and problems.” Proceedings of ACEDC, 96, PEDC, University of Plymouth, England.

23. Baran, E., and Jantunen, T. (2004). “Stakeholder consultation for bayesian decision support systems in eEnvironmental management.” Regional Conference on Ecological and Enviromental Modeling(ECOMOD 2004), Penang, Malaysia, 27 (35.6), 31-37.

24. Uusitalo, L.(2007). “Advantages and challenges of bayesian networks in environmental modelling.” Ecological Modelling, 203 (3), 312-318.

25. Jensen, F. V., and Kjarulff, U. (2005). “Bayesian networks and decision graphs.” A 3-week Course at Reykjavik University, Group of Machine Intelligence, Department of Computer Science, Aalborg University.

26. Pearl, J. (2000). Models, reasoning and inference, Cambridge University Press Cambridge, UK.

27. Grossman, D., and Domingos, P. (2004). “Learning bayesian network classifiers by Maximizing Conditional Likelihood. Proc., Proceedings of the twenty-first international conference on Machine learning, ACM, New York, USA. 46.

28. Khanteymoori, A., and Sameni, M. (2011). “Precipitation modeling using bayesian networks.” The Fifth Iran Data Mining Conference / IDMC 3122, Amirkabir University of Technology Tehran, Iran. (In Persian)