پیش بینی پسماند تولیدی شهر تهران با استفاده از سامانه استنتاج تطبیقی فازی-عصبی و شبکه‌های عصبی مصنوعی

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشجوی کارشناسی ارشد

2 استاد، دانشکده مهندسی و فناوری کشاورزی پردیس کشاورزی و منابع طبیعی دانشگاه تهران

3 استادیار، دانشکده مهندسی و فناوری کشاورزی پردیس کشاورزی و منابع طبیعی دانشگاه تهران

4 استادیار، دانشکده مدیریت دانشگاه تهران

چکیده

پیش بینی کمیت تولید، نقش به سزایی در بهینه سازی و برنامه ریزی سامانه­ مدیریت پسماند­های جامد شهری دارد، اما به علت دینامیک بودن سامانه های مدیریت پسماند، پیچیدگی روابط بین متغیر ورودی و خروجی، در دسترس نبودن و یا ناکافی بودن اطلاعات و همچنین تاثیر عوامل متغیر و غیرقابل کنترل همواره کار مشکلی بوده است. امروزه استفاده از سامانه های هوشمند به عنوان راهکاری نوین در تحلیل مسائل زیست محیطی، گسترش یافته است. در این پژوهش توانایی دو مدل هوشمند شبکه عصبی با تابع آموزش لونبرگ مارکوارت و همچنین سامانه استنتاج تطبیقی فازی-عصبی برای تخمین میزان تولید پسماندهای ماهانه شهر تهران مقایسه گردید. برای این منظور از داده های مربوط به جمعیت، الگوهای فصلی، کل بارندگی ماهانه، میانگین دمای ماهانه، ارتفاع از سطح دریا، میانگین رطوبت ماهانه و کل پسماند تولیدی (TSW) این شهر در فاصله زمانی 1389 تا 1394 که به صورت ماهانه مرتب شده بودند، استفاده شد. بعد از آموزش و آزمون مدل­های شبکه عصبی و سامانه استنتاج تطبیقی فازی­-عصبی نتایج این مدل­ها مورد مقایسه قرار گرفت. نتایج به دست آمده از این پژوهش نشان داد که مدل فازی-عصبی با ضریب تعیین 963/0، جذر میانگین مربعات خطا 096/0و درصد میانگین مطلق خطا 05/1 نسبت به مدل شبکه عصبی با ضریب تعیین 852/0، جذر میانگین مربعات خطا 132/0و درصد میانگین مطلق خطا 19/1 دارای عملکرد بهتری می­باشد. همچنین نتایج بررسی دو مدل نشان داد که در هر دو مدل با داده­های ورودی الگوهای فصلی، کل بارندگی ماهانه، میانگین دمای ماهانه، میانگین رطوبت ماهانه و کل پسماند تولیدی (TSW) می­توان به پیش­بینی دقیق­تری دست یافت.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Prediction of Tehran solid waste production by using of neural network and adaptive neuro-fuzzy inference system

نویسندگان [English]

  • Sajjad Nasrollahi 1
  • Reza Alimardani 2
  • Mohammad Sharifi 3
  • Mohammad reza Taghizadeh Yazdi 4
1
2
3
4
چکیده [English]

In this study two intelligent systems, based on adaptive neuro-fuzzy inference systems (ANFIS) and artificial neural networks (ANNs) of forecasting municipal solid wastes (MSW) generation has been proposed. ANFIS and ANNs as an intelligent tool compared with together was used to monthly prediction of MSW generated in Tehran. Monthly amount of solid wastes (SW), total monthly precipitation, monthly mean temperature, monthly average humidity and the rank of months per year in the period of 2009 -2014 was used as input data for model learning. The best ANN model had a 5-14-1 structure, it consisted of an input layer with five input variables, one hidden layers with 14 neurons and MSW production as output. The best ANFIS model was designed using one ANFIS architecture with the six-time run out which were developed at three stages. Correlation coefficient (R2), root mean square error (RMSE) and mean absolute percentage error (MAPE) for the best ANN model were computed as 0.825, 0.132 and 1.19, respectively. The corresponding R2, RMSE and MAPE values for the best ANFIS topology were 0.963, 0.096 and 1.05 respectively. The results of this study showed that, multi-layer ANFIS model due to employing fuzzy rules, better performance than the ANN model.

کلیدواژه‌ها [English]

  • waste
  • municipal solid wastes
  • intelligent systems
  • ANFIS
  • ANN
Abbasi, M., Abduli, M., Omidvar, B., and Baghvand, A. (2012). Forecasting municipal solid waste generation by hybrid support vector machine and partial least square model. International Journal of Environmental Research,  7, 27-38.
Abdoli, MA., Noori, R., Jalili, M., and Salehian, A. (2007). Forecasting of Tehran waste production using artificial neural networks and multivariate statistical methods. In: Proceedings of 3th National Congress on Waste Management, 21-22 Oct.,  Environmental Protection Agency, Tehran, Iran , pp. 61-72. (In Farsi)
Akkaya, E., and Demir, A. (2010). Predicting the heating value of municipal solid waste-based materials: An artificial neural network model. Energy Sources, Part A: Recovery, Utilization, and Environmental Effects,  32, 1777-1783.
Cay, Y., Cicek, A., Kara, F., and Sağiroğlu, S. (2012). Prediction of engine performance for an alternative fuel using artificial neural network. Applied Thermal Engineering, 37, 217-225.
Çay, Y., Korkmaz, I., Çiçek, A., and Kara, F. (2013). Prediction of engine performance and exhaust emissions for gasoline and methanol using artificial neural network. Energy,  50, 177-186.
Damghani, AM., Savarypour, G., Zand, E., and Deihimfard, R. (2008). Municipal solid waste management in Tehran: Current practices, opportunities and challenges. Waste management,  28, 929-934.
Dyson, B., and Chang, NB. (2005). Forecasting municipal solid waste generation in a fast-growing urban region with system dynamics modeling. Waste management, 25, 669-679.
Hyun Il, P., Borinara, P., and Hong, K. (2011). Geotechnical considerations for end-use of old municipal solid waste landfills. International Journal of Environmental Research  5, 573-584.
Jalili Ghazi Zade, M., and Noori, R. (2007). Prediction of municipal solid waste generation by use of artificial neural network: A case study of Mashhad. International Journal of Environmental Research, 2, 13-22.
Karaca, F., and Özkaya, B. (2006). NN-LEAP: A neural network-based model for controlling leachate flow-rate in a municipal solid waste landfill site. Environmental Modelling & Software,  21, 1190-1197.
Khoshnevisan, B., Rafiee, S., Omid, M., and Mousazadeh, H. (2014a). Development of an intelligent system based on ANFIS for predicting wheat grain yield on the basis of energy inputs. Information processing in agriculture,  1, 14-22.
Khoshnevisan, B., Rafiee, S., Omid, M., and Mousazadeh, H. (2014b). Prediction of potato yield based on energy inputs using multi-layer adaptive neuro-fuzzy inference system. Measurement  47, 521-530.
Khoshnevisan, B., Rafiee, S., and Mousazadeh, H. (2014c). Application of multi-layer adaptive neuro-fuzzy inference system for estimation of greenhouse strawberry yield. Measurement,  47, 903-910.
 Khoshnevisan, B., Rafiee, S., Iqbald, J., Shamshirbande, S., Omid, M., Anuarf, N., and Abdul Wahabg, A. (2015). A Comparative Study between Artificial Neural Networks and Adaptive Neuro-fuzzy Inference Systems for Modeling Energy Consumption in Greenhouse Tomato Production-A Case Study in Isfahan Province. Journal of Agricultural Science and Technology,  17, 49-62.
Naderloo, L., Alimardani, R., Omid, M., Sarmadian, F., Javadikia, P., Torabi, MY., and Alimardani, F. (2012). Applicationof ANFIS to predict crop yield based on different energy inputs. Measurement, 45, 1406-1413.
Najafi, G., Ghobadian, B., Tavakoli, T., Buttsworth, D., Yusaf, T., and Faizollahnejad, M. (2009). Performance and exhaust emissions of a gasoline engine with ethanol blended gasoline fuels using artificial neural network. Applied Energy, 86, 630-639.
Noori. R., Abdoli, MA., Farokhnia, A., and Ghaemi, A. (2009a). Prediction of weekly solid waste by using of neural network and hybrid of wavelet. Journal ofEnvironmental Studies,35(49), 25-30. (In Farsi)
Noori, R., Abdoli, MA., Farokhnia, A., and Abbasi, M. (2009b). Results uncertainty of solid waste generation forecasting by hybrid of wavelet transform-ANFIS and wavelet transform-neural network. Expert Systems with Applications, 36, 9991-9999.
Noori, R., Karbassi, A., and Sabahi, MS. (2010a). Evaluation of PCA and Gamma test techniques on ANN operation for weekly solid waste prediction. Journal of Environmental Management,  91, 767-771.
Noori, R., Hoshyaripour, G., Ashrafi, K., and Araabi, BN. (2010b). Uncertainty analysis of developed ANN and ANFIS models in prediction of carbon monoxide daily concentration. Atmospheric Environment,  44, 476-482.
Pahlavan, R., Omid, M., and Akram, A. (2012). Energy input–output analysis and application of artificial neural networks for predicting greenhouse basil production. Energy, 37, 171-176.
Sahoo, G., Ray, C., and De, Carlo E. (2006). Use of neural network to predict flash flood and attendant water qualities of a mountainous stream on Oahu, Hawaii. Journal of Hydrology, 327, 525-538.
Shojaeefard, M., Etghani, M., Tahani, M., and Akbari, M. (2012). Artificial Neural Network Based Multi-Objective Evolutionary Optimization of a Heavy-Duty Diesel Engine. International Journal of Automotive Engineering, 2(4), 206-215 (In Farsi)
Singh, R., Kainthola, A., and Singh, T. (2012). Estimation of elastic constant of rocks using an ANFIS approach. Applied Soft Computing, 12, 40-45.
Tehran Waste Management Organization. (2014). Statistics report on 2014. Tehran  Municipality, Iran.  Retrieved January 12, 2014, from http://pasmand.tehran.ir/Default.aspx?alias=pasmand.tehran.ir/en.
Tiwari, MK., Bajpai, S., and Dewangan, U. (2012). Prediction of industrial solid waste with ANFIS model and its comparison with ANN model-A case study of Durg-Bhilai twin city India. International Journal of Engineering and Innovative Technology (IJEIT), 6, 192-201.
Wahab, SA., and Alawi, SM. (2008). Prediction of sulfur dioxide (so2) concentration levels from the mina al-fahal refinery in oman using artificial neural networks. American Journal of Environmental Sciences, 4, 473.
Yesilnacar, MI., Sahinkaya, E., Naz, M., and Ozkaya, B. (2008). Neural network prediction of nitrate in groundwater of Harran Plain, Turkey. Environmental Geology, 56, 19-25.
Zare, M., and Khaki, JV. (2012). Prediction of mechanical properties of a warm compacted molybdenum prealloy using artificial neural network and adaptive neuro-fuzzy models. Materials & Design, 38, 26-31.