Efficiency Consideration of Wastewater Treatment Plant of Tabriz using Artificial Intelligence Models

Document Type : Research Paper


1 Graduate Student, Faculty of Natural Sciences, University of Tabriz

2 Assistant professor, Faculty of Natural Sciences, University of Tabriz

3 professor, Faculty of Natural Sciences, University of Tabriz


According to the shortage of water resources in the world, it seems necessary the use of refined water, particularly in arid and semi-arid areas such as Iran. The correct treatment, management and the control of refining process needs to investigate effective parameters in this process precisely. Therefore, because of the uncertainty and complexity in refining qualitative parameters and their relationship, artificial intelligence such as a fuzzy model (FL) and artificial neural networks (ANNs) were used in this study for modeling the behavior of Tabriz plant wastewater treatment.
Tabriz city as the capital of the East Azarbaijan province is the most industrialized and urbanized cities of North West of Iran (Figure 1).The sewage of Tabriz city, including industrial and domestic wastewaters, collected gravitationally and enter into the wastewater treatment plant in Tabriz city. It is located in Qaramalek District, four kilometers away in west of downtown on the south side of the Ajichay river and on the lowest part of the city at 1334 (amsl) level. The wastewater treatment plant is designed in three stages. The first phase of Tabriz wastewater treatment plant with a capacity of 612 thousand people has been established in July of (2001). Currently, due to the being incomplete of sewerage network in Tabriz city, only the first phase of this plant is exploited with around 30% of total capacity. The second and third phases are under study. Tabriz wastewater refinery with an annual average rate 1.5 cubic meters per second and peak flow in the rainy and non-rainy days are 3.8 and 2.5 cubic meters per second, respectively. Refinery process including both primary and secondary treatment stages, the physical refining is done in first step then biological treatment and finally disinfection.
Figure 1. Location of wastewater treatment plant of Tabriz city in Tabriz plain.
Material and method
The data used in this study to develop an artificial neural network and two fuzzy logic model (Sugeno and Mamdani FL models for evaluating the performance of wastewater treatment plant of Tabriz city is influent and effluent of refinery system. In this study, the system influent applied as input model to estimate the qualitative factors of effluent. To quality assessment in wastewater and sewage treatment plant, the parameters that are usually measured and recorded are the Temperature (T), Biochemical Oxygen Demand (BOD), Chemical Oxygen Demand (COD), Total Suspended Solids (TSS) and pH compared in the input and Output of wastewater treatment. In this regard, the monthly values of BOD, COD, TSS, T, and pH of effluent raw wastewater and effluent treated water of treatment plant were analyzed for the 11 years 2002 to 2012
At first the data set that contains 660 data from Tabriz refinery, were divided into two parts include testing (130 data) and training (530 data). A FL method consists of three main parts, fuzzification, inference engine (fuzzy rule base), and defuzzification. In the fuzzification step, the four crisp inputs change to fuzzy set for constructing the inference engine. The inference engine consists of rules. Each rule, in turn, is formed from multiple inputs and a single output. When the antecedents of fuzzy rules include more than one rule, then fuzzy operators are used to connect them. The most common fuzzy operators are AND which supported min (minimum) and prod (product), OR (maximum) and NOT. The consequences of a fuzzy rule assign an entire fuzzy set to the output through the process which is called implication. The input to the implication process is a single number given by the antecedent, and the output is a fuzzy set. Since decisions are based on the testing of all of the rules in an FIS, the rules must be combined via aggregation processes in order to make a decision. The process of transforming the aggregation result into a crisp output is termed defuzzification. The most common defuzzification methods are centroid, bisector, middle of maximum (the average of the maximum value of the output set), largest of maximum, and smallest of maximum.
Discussion of Results
The Sugeno fuzzy logic model is constructed by subtractive clustering method. The optimal cluster radius is assigned based on the minimum Root Mean Square Errors (RMSE) and MAPE are 2.71 and 8.08. Based on the optimal clustering radius, five clusters and five If-Then rules were determined using Gaussian membership functions. The average correlation coefficient of this model is 0.82.
Also, for constructing Mamdani fuzzy model, FCM clustering method is applied. By using minimum RMSE and MAPE that are 2.83 and 8.88 respectively, the optimal numbers of input and output clusters are assign 17. The Membership functions are Gaussian membership functions and average correlation coefficient of this model is 0.8.
  The perceptron network, three layers artificial neural network, includes input, hidden and output layers. Data division in train and test steps is the same as the FL models. Input layer have 5 nodes include BOD, COD, TSS, T and pH that is used as input data for predicting 3 output parameters (i.e., BOD, COD and TSS). To select the appropriate number of neurons in the hidden layer has been proposed the various methods such as trial and error and also mathematical rules. In this study, the number of neurons in the hidden layer determined 3 neurons by the trial and error method. At the first step, the network must be trained. The purpose of the learning network is achieving Minimum Absolute Percentage Errors and optimal weights of the network. Due to the high R² and lowest RMSE in the optimal structure is 5-3-3. The obtained results for test step (average RMSE= 3.63) confirm of high ability of artificial neural network in estimating parameters of wastewater treatment plant.
Finally, to evaluate the output of wastewater treatment plant and the results of artificial intelligence models in removing and reducing studying parameters, percentage of removal efficiency was used according to equation 1.
This index shows indicates the isolation of each of the quality parameters of the wastewater after treatment. In this equation, REX is the index of removal efficiency percent of x,  amount of input mass of parameters x to treatment plant and artificial intelligence,  amount of output mass of the parameters x from the treatment plant which was estimated by artificial intelligence and n is the number of data for each pollutant. This equation was performed in two cases, one based on the measured data in the input and output of treatment plant and the other based on the measured data in the input and the estimates of the artificial intelligence. At the end calculated and compared the efficiency of reducing emissions separately for each pollutant for both cases.
   The removal efficiency of each three contaminant is close together and the TSS pollutant has maximum removal efficiency (93.74%) for three artificial intelligence models. The results represent a good performance of applied models. Consequently, the neural network and Mamdani and Sugeno fuzzy models have good accuracy in evaluating the performance of treatment.
Although three artificial intelligence models have acceptable results, but based on the correlation coefficient and RMSE for each of the parameters in the models, the Sugeno fuzzy model is more superior than other models. The superiority of the Sugeno fuzzy model over an artificial neural network is due to high uncertainty of wastewater treatment plant parameters. Also, calculate the percentage of contaminant removal efficiency was determined in the output treatment. The maximum removal efficiency was related to TSS pollutant that is equal to 93%. TSS values were also very close to other pollutants. Similarly, the removal efficiency of pollutants from the estimated values by fuzzy model and neural network is the same and close to the observed value due to the good performance of used models.  


Main Subjects

اصغری‌مقدم، الف.، ندیری، ع.، فیجانی، الف. 1388. استفاده از مدل‌های شبکه‌های عصبی مصنوعی و زمین‌آمار برای پیش‌بینی مکانی غلظت فلوئورید، مجلة دانش آب- خاک، سال دوم، شمارۀ 1/19، صص 129- 145.
بینا، ب.، موحدیان، ح.، پورزمانی، ح . ر. 1384. بررسی تأثیر نسبت COD/N ورودی بر سرعت نیتریفیکاسیون در تصفیۀ فاضلاب با استفاده از یک راکتور پایلوت در مقیاس آزمایشگاه، مجلۀ آب و فاضلاب، سال شانزدهم، شمارۀ 1، صص30- 36.
ترابیان، ع.، مطلبی، م. 1382. طرح مدیریتی استفادۀ مجدد از پساب تصفیه‌شده (مطالعۀ موردی: شهرک اکباتان)، مجلۀ محیط‌شناسی، سال بیست و نهم، شمارۀ 32، صص57- 62.
توکلی، م.، جهانی بهنمیری، ا.، محمودی، ش. 1390. برنامه‌ریزی و مدیریت طرح‌های استفادۀ مجدد از فاضلاب‌های تصفیه‌شده، چاپ اول، چاپ شرکت مدیریت منابع آب ایران.
خلیلی، ن.، خداشناس، س.، داوری، ک.، و موسوی بایگی. م. 1385. پیش‌بینی بارش ماهانه با استفاده از شبکه‌های عصبی مصنوعی، علوم و صنایع کشاورزی، سال بیست و دوم، شمارۀ 1، صص 89- 100.
ذوقی، م. ج.، ذوقی، ت.، سعیدی، م. 1389. پیش‌بینی غلظت آمونیوم و مواد آلی فاضلاب دفنگاه زباله با استفاده از شبکۀ عصبی مصنوعی، مجلۀ آب و فاضلاب، شمارۀ 74، دورۀ 21، صص ۵۲- 60.
رجبی، م.، بهلولی، ب.، محمدی‌نیا، م.، و غلامپور آهنگر، الف. 1390. پیش‌بینی سرعت موج برشی از نگارهای تخلخل به وسیلۀ روش‌های منطق فازی و عصبی- فازی در یکی از مخازن کربناتی جنوب ایران، مجلۀ علوم زمین، سال بیستم، شمارۀ 80، صص 63- 70.
رجبی، م.، بهلولی، ب.، موسوی، س. ج. 1388. تخمین سرعت موج استونلی از نگارهای پتروفیزیکی با استفاده از ماشین مشاورۀ هوشمند در سازند سروک، دشت آبادان، مجلۀ علوم دانشگاه تهران، جلد سی و پنجم، شمارۀ 2، صص 1- 10.
رفعت‌متولی، ف.، دانش، ش.، رجبی‌مشهدی، ح. 1391. بررسی امکان کاربری مدل شبکۀ عصبی مصنوعی در پیش‌بینی کیفیت پساب خروجی تصفیه‌خانه‌های فاضلاب نیمه‌مکانیکال، همایش ملی سنجش و مدل‌سازی محیط، دانشگاه تهران.
رنگ‌زن، ن.، پاینده، خ.، لندی، ا. 1385. بررسی کیفیت پساب بر انباشت عناصر سنگین در دو گیاه سورگوم و شبدر، نهمین کنگرۀ علوم خاک ایران، تهران.
روستایی، س.، شکرانه، ف.، رحیم‌پور بناب، ح. و کدخدایی ایلخچی، ع. 1388. تخمین تراوایی توسط تکنیک منطق فازی و روش‌های آماری در میدان گاز پارس جنوبی، مجلۀ اکتشاف و تولید، شمارۀ 59، صص 42- 45.
زارع‌ابیانه، ح.، بیات ورکشی، م.، بیات‌ورکشی، ج. 1391. کاربرد شبکۀ عصبی مصنوعی در ارزیابی تصفیه‌خانۀ فاضلاب اکباتان، مجلۀ محیط‌شناسی، سال سی و هشتم، شمارۀ 3، صص 85- 98.
صفوی، ح. ر. 1389. پیش‌بینی کیفی رودخانه‌ها با استفاده از سیستم استنتاج فازی- عصبی تطبیقی، محیط‌شناسی، جلد 1، شمارۀ 53، صص 1- 10.
طاهریون، م. 1385. شبکه‌های عصبی مصنوعی و کاربرد آن در مهندسی محیط‌زیست، اولین همایش تخصصی مهندسی محیط‌زیست، دانشگاه تهران.
فلاح‌قالهری، غ.، موسوی‌بایگی، س. م.، حبیبی‌نوخندان، م. 1388. مقایسۀ نتایج به‌دست‌آمده از کاربرد سیستم استنباط فازی ممدانی و شبکه‌های عصبی مصنوعی در پیش‌بینی بارش فصلی، مطالعۀ موردی: منطقۀ خراسان، مجلۀ تحقیقات منابع آب ایران، سال پنجم، شمارۀ 2، صص 40- 52.
محوی، ا. ح.، رجبی‌زاده، ا.، احمدیان، م.، و فاتحی‌زاده.، ع. 1388. بررسی وضعیت تصفیۀ فاضلاب و کیفیت پساب خروجی بیمارستان‌های استان کرمان در سال‌های 84- 86، دوازدهمین همایش بهداشت محیط ایران دانشگاه علوم پزشکی شهید بهشتی دانشکدة بهداشت.
مرادمند، م.، بیگی‌هرچگانی، ح. 1388. اثر آبیاری با پساب تصفیه‌شده بر توزیع سرب و نیکل در اندام فلفل سبز و خاک، مجلۀ پژوهش آب ایران، دورۀ سوم، شمارۀ 5، صص 63- 70.
مشاور یکم، مهندسین مشاور. 1391. مطالعات آب زیرزمینی دشت تبریز، سازمان آب منطقه‌ای استان آذربایجان شرقی.
مشاور یکم، مهندسین مشاور. 1384. مطالعات زیست‌محیطی استفادۀ مجدد از پساب تصفیه‌خانۀ فاضلاب تبریز، جلد دوم، مطالعات زیست‌محیطی، امور محیط‌زیست.
میران‌زاده، م. ب.، بابامیر، ش. 1382. بررسی کارایی تصفیه‌خانۀ فاضلاب شهرک اکباتان تهران طی سال‌های 79- 80، فصلنامۀ علمی- پژوهشی فیض، شمارۀ 25، صص 40- 47.
ندیری، ع.، اصغری‌مقدم، الف.، عبقری، ه.، فیجانی،. الف. 1392. توسعۀ مدل‌های هوش مصنوعی مرکب در برآورد قابلیت انتقال آبخوان، مطالعۀ موردی: دشت تسوج، تحقیقات منابع آب ایران، سال نهم، شمارۀ 1، صص 1- 14.
ندیری، ع.، اصغری‌مقدم، الف.، عبقری، ه. 1393. مدل منطق فازی مرکب نظارت‌شده در تخمین قابلیت انتقال آبخوان‌ها، مطالعۀ موردی: دشت تسوج، شمارۀ 1، صص 219- 233.
ASCE Task Committee and Govindaraju, R. S. 2000. Artificial neural network in hydrology (part II). Hydrologic Applications, Journal of Hydrologic Engineering, Vol. 5(2),pp: 124- 137.
Chan, C.W. and Huang, G.H. 2003. Artificial intelligence for management and control of pollution minimization and mitigation processes, Journal of Engineering Applications of Artificial Intelligence, Vol. 16(2), pp:75 –90.
Chan, C.W., Chang, N.B. and Shieh, W.K. 2001.Advanced hybrid fuzzy- neural controller for industrial wastewater treatment, Journal of Environmental Engineering,Vol. 127(11), pp:1048–1050.
Choi, D. and Park, H. 2001. A hybrid artificial neural network as a software sensor for optimal control of a wastewater treatment process, Journal of Water Research. Vol. 35(16), pp:3959–3967.
Dogan, E. Ates, A. Yilmaz, E.C. and Eren, B. 2008. Application of Artificial Neural Networks to Estimate Wastewater Treatment Plant Inlet Biochemical Oxygen Demand, Journal of Environmental Progress, Vol. 27(4), pp:439-446.
Erdirencelebi, D. and Yalpir, S. 2011. Adaptive network fuzzy inference system modeling for the input selection and prediction of anaerobic digestion effluent quality, Journal of Applied Mathematical Modelling, Vol. 35(8), pp:3821- 3832.
Esra, Y. and sukran, Y. 2011. Prediction of primary treatment effluent parameters by Fuzzy Inference System (FIS) approach, Journal of Procedia Computer Science, Vol. 3, pp:659–665.
Fijani, E., Nadiri, A.A., Asghari Moghaddam, A., Tsai, F.T.C. and Dixon, B. 2013. Optimization of DRASTIC method by supervised committee machine artificial intelligence to assess groundwater vulnerability for Maragheh–Bonab plain aquifer, Iran. Journal of Hydrology, 503(0): 89-100.
Grande, J. A., Manuel Andujar, J., Beltran, R., de la Torre, M.L., Ceron, J. C. and Gomez, T.2010. Fuzzy modeling of the spatial evolution of the chemistry in the Tinto River (SW Spain), Journal of Water Resources Management, Vol. 24(12), pp:3219-3235.
Hamed, M., Khalafallah, M.G. and Hassanein, E.A. 2004. Prediction of wastewater treatment plant performance using artificial neural network, Journal of Environmental Modeling and Software, Vol. 19 (10), pp:919–928.
Hong, Y. T., Rosen M.R. and Bhamidimarri R. 2003. Analysis of a municipal wastewater treatment plant using a neural network-based pattern analysis, Journal of Water Research, Vol. 37 (7), pp:1608–1618.
Hopfield, J.J. 1982. Neural network and physical systems with emergent collective computational abilities, Proc. Nat. Academy of scientists of the United States of America (PNAS), Vol. 79(8), pp:2554-2558.
Jalili-Ghazizade, M. and Noori, R. 2008. Prediction of municipal solid waste generation by use of artificial neural network: a case study of Mashhad, International Journal of Environmental Research, Vol. 2(1), pp:13-22.
Kadkhodaie-Ilkhchi, A. andAmini, A. 2009. A fuzzy logic approach to estimating hydraulic flow units from well log data: A case study from the Ahwaz oilfield, South Iran, Journal of Petroleum Geology, Vol. 32(1), pp:67-78.
Mamdani, E.H., 1976. Advances in the linguistic synthesis of fuzzy controllers. International Journal of Man-Machine Studies, Vol.8, pp: 669–678.
Mamdani, E.H., 1977. Applications of fuzzy logic to approximate reasoning using linguistic synthesis. IEEE Transactions on Computers, Vol. 26, pp:1182–1191.
Mamdani, E.H., Assilian, S., 1975. An experimental in linguistic synthesis with a fuzzy logic control. International Journal of Man-Machine Studies, Vol. 7: pp:1–13.
Mingzhi, H., Ma, Y., Jinquan, W. and Yan, W. 2009. Simulation of a paper mill wastewater treatment using a fuzzy neural network, Journal of Expert Systems with Applications, Vol. 36(3), pp:5064-5070.
Mjalli, F. S., Al-Asheh, S. and Alfadala, H.E. 2007. Use of artificial neural network black-box modeling for the prediction of wastewater treatment plants performance, Journal of Environmental Management, Vol. 83(3), pp:329–338.
Murnleitner, E., Becker, T.M. and Delgado, A. 2002. State detection and control of overloads in the anaerobic wastewater treatment using fuzzy logic, Journal of Water Research, Vol. 36(1), pp:201–211.
Nadiri, A., Chitsazan, N., Tsai, F. and Moghaddam, A.A. 2014, Bayesian Artificial Intelligence Model Averaging for Hydraulic Conductivity Estimation. Journal of Hydrologic Engineering, Vol. 19(3), pp:520–532.
Nadiri, A., Moghaddam, A., Tsai, F-C., Fijani, E.  2013b. Hydrogeochemical analysis for Tasuj plain aquifer, Iran. J Earth Syst Sci. Vol. 122(4):1091-105.
Nadiri, A.A., Fijani, E., Tsai, F. T. C. and Moghaddam, A.A. 2013a. Supervised Committee Machine with Artificial Intelligence for Prediction of Fluoride Concentration, Journal of Hydroinformatics. Vol. 15(4), p:1474-1490.
Oliveira-Esquerre, K.P., Mori, M. and Bruns, R.E. 2002. Simulation of an industrial wastewater treatment plant using artificial neural networks and principal components analysis, Journal of Brazilian Journal of Chemical Engineering, Vol. 19(4), pp:365-370.
Ozkaya, B., Demir, A. and Bilgili, M.S. 2007. Neural network prediction model for the methane fraction in biogas from field scale landfill bioreactors, Journal of Environmental Modelling & Software, Vol. 22(6), pp:815 -822.
Pai, T.Y., Tsai, Y.P., Lo, H.M., Tsai, C.H. and Lin, C.Y. 2007. Grey and neural network prediction of suspended solids and chemical oxygen demand in hospital wastewater treatment plant effluent, Journal of Computers and Chemical Engineering, Vol. 31(10), pp:1272 – 1281.
Pai, T.Y., Wan, T.J., Hsu, S.T., Chang, T.C. and Tsai, Y.P. 2009. Using fuzzy inference system to improve neural network for predicting hospital wastewater treatment plant effluent, Journal of computers and Chemical Engineering, Vol. 33(7), pp:1272–1278.
Perendeci, A., Arslan, S., Tanyolac, A. and Celebi, S. 2009. Effects of phase vector and history extension on prediction power of adaptive-network based fuzzy inference system (ANFIS) model for a real scale anaerobic wastewater treatment plant operating under unsteady state, Journal of Bioresource Technology, Vol. 100(20), pp:4579–4587.
Sahoo, G.B., Ray, C. and Wade, H.F. 2005. Pesticide prediction in ground water in North Carolina domestic wells using artificial neural networks, Journal of  Ecological Modelling, Vol. 183(1), pp: 29- 46.
Singh, K.P., Basant, A., Malik, A. and Jain, G. 2009. Artificial neural network modeling of the river water quality-A case study, Journal of Ecological Modeling, Vol. 220(6), pp:888–895.
Sugeno, M. 1985. Industrial Application of Fuzzy Control. North-Holland, New York, 269.
Wan, J., Huang, M., Ma, Y., Gue, W., Wang, Y., Zhang, H., Li, W. and Sun, X. 2011. Prediction of effluent quality of a paper mill wastewater treatment using an adaptive network-based fuzzy inference system, Journal of Applied Soft Computing, Vol. 11(3), pp:3238–3246.
Wen, C.H. and Vassiliadis, C.A. 1998. Applying hybrid artificial intelligence techniques in wastewater treatment, Journal of Engineering Applications of Artificial Intelligence, Vol. 11(6), pp:685-705.
Yel, E., Yalpir, S., 2011. Prediction of primary treatment effluent parameters by Fuzzy Inference System (FIS) approach. Procedia Computer Science, Vol. 3: pp: 659-665.
Zadeh, L. A. 1965. Fuzzy sets as a basic for theory of possibility, Fuzzy Sets and Systems, Vol.1, pp:3-29.