Atıksulardan Zn Gideriminin Yapay Sinir Ağı (YSA) ile Modellenmesi

Year 2021, Issue: 24, 335 - 342, 15.04.2021

Fatma Erdem

https://doi.org/10.31590/ejosat.899692

Abstract

Yapılan bu çalışmada Ankara Sanayi Odası 2. ve 3. Organize Sanayi Bölgesi Atık Su arıtma tesisi için Zn giderim tahmini YSA ile gerçekleştirilmiştir. Toksik olup ağır metal kirliliği kapsamında atıksularda oldukça sık karşılaşılan çinkonun arıtım sonrası belirlenen limite indirgenmesi oldukça önemlidir. YSA ile modelleme çalışmalarında giriş parametresi olarak giriş pH, Zn ve Fe konsantrasyonu, AKM ( Askıda Katı Madde) ve TKM (Toplam Katı Madde) seçilirken çıkış parametresi olarak Zn çıkış konsantrasyonu seçilmiştir. Verilerin eğitimi Levenberg–Marquardt ileri besleme algoritması ile yapılmış olup deneysel veriler %75 eğitim, %15 validasyon ve %15 test olarak ayrılmıştır. Çalışmada giriş parametreleri için farklı kombinasyonların oluşturduğu senaryolar denenmiş ve sisteme ait maksimum devir (epoch) değeri, eğitim, validasyon ve tüm biyosorpsiyon sistemi için R ve MSE değeri belirlenerek elde edilen sonuçlar karşılaştırılmıştır. Aktivasyon fonksiyonunun sonuçlar üzerine etkisini görebilmek için tansig, pürelin ve logsis transfer fonksiyonları kullanılmıştır. Çalışma sonucunda deneysel ve model tahmini çıkış akımındaki Zn konsantrasyon değerleri karşılaştırıldığında, YSA ile sistemin iyi bir şekilde modellendiği ve modelin iyi bir tahmin yeteneğine sahip olduğu görülmüştür.

Keywords

atık su, modelleme, çinko, yapay sinir ağı

Thanks

Ankara Sanayi Odası 2. ve 3. Organize Sanayi Bölgesi Atık Su Arıtma Tesisi, Çevre Yönetim ve Arıtma Müdürü, Çevre Mühendisi Enise Dilek ESEN’e veri paylaşımı için teşekkürlerimi sunarım.

Modeling of Zn Removal from Wastewater with Artificial Neural Network (ANN)

Abstract

In this study, Zn removal estimation for the Ankara Chamber of Industry 2nd and 3rd Organized Industrial Zone wastewater treatment plant was performed by Artificial Neural Network (ANN). It is very important to reduce the zinc, which is toxic and frequently encountered in wastewater within the scope of heavy metal pollution, to the limit determined after treatment. In the modeling studies, pH, Zn and Fe concentration, SS (Suspended Solids) and TSS (Total Suspended Solids) were selected as input parameters, while Zn output concentration was chosen as the output parameter. The training of the data was done with the Levenberg-Marquardt feed forward algorithm and the experimental data were divided into 75% training, 15% validation and 15% test. In the study, scenarios created by different combinations for input parameters were tried and the results obtained by determining the maximum cycle (epoch) value of the system, training, validation and R and MSE values for the whole biosorption system were compared. In order to see the effect of activation function on the results, tansig, purelin and logsis transfer functions were used. As a result of the study, when the Zn concentration values in the experimental and the model estimated output current were compared, it was seen that the system was well modeled with ANN and the model has a good prediction ability.

Keywords

Wastewater, Modeling, Zinc, Artificial Neural Network

References

• Agoro, M.A., Adeniji, A.O., Adefisoye, M.A., Okoh, O.O. (2020). Heavy Metals in Wastewater and Sewage Sludge from Selected Municipal Treatment Plants in Eastern Cape Province, South Africa. Water, 12,2746.
• Pugazhenthiran, N., Anandan, S., Ashokkumar M. (2016) Removal of Heavy Metal from Wastewater. Handbook of Ultrasonics and Sonochemistry, Springer.
• Prathisksha, P. Balakrishna, P. (2018) A Review on Removal of Heavy Metal Ions from Waste Water using Natural/ Modified Bentonite, J. MATEC Web of Conferences.
• John, M., Heuss-Aßbichler, S., Ullrich, A. (2016) Recovery of Zn from wastewater of zinc plating industry by precipitation of doped ZnO nanoparticles. Int. J. Environ. Sci. Technol. 13, 2127–2134.
• Gakwisiri, C., Raut, N., Al-Saadi, A., Al-Aisri, S., Al-Ajmi, A. (2012). A Critical Review of Removal of Zinc from Wastewater. In Proceedings of the World Congress on Engineering, London, UK.
• Mishra, V. (2014). Biosorption of zinc ion: a deep comprehension. Appl Water Sci, 4, 311–332.
• Kulkarni, S.J. (2015). Removal of Zinc from Effluent: A Review. International Journal of Advanced Research in Science, Engineering and Technology, 2(1), 338-340.
• Yamagata, H., Yoshizawa, M. & Minamiyama, M. (2010). Assessment of current status of zinc in wastewater treatment plants to set effluent standards for protecting aquatic organisms in Japan. Environ Monit Assess., 169, 67–73.
• Çınar, Ö., Yılmaz, A.S. (2005). Yapay Sinir Ağlarının Atıksu Arıtma Tesisi İşletimine Uygulanması: Bir Örnek Çalışma. KSÜ. Fen ve Mühendislik Dergisi, 8(2), 48-52.
• Philips, N., Heyvaerts, S., Lammens, K., Van Impe, JF. (2005). Mathematical modelling of small wastewater treatment plants: power and limitations. Water Sci Technol., 51(10):47-54.
• Boger, Z. (1992). Application of neural networks to water and wastewater treatment plant operation. ISA Transactions, 31(1), 25-33.
• Kırım, G. (2015). Atıksu Arıtma Tesislerinin Model Desteği İle İyileştirilmesi Ve Optimizasyonu. Yüksek Lisans Tezi, İstanbul Teknik Üniversitesi, Fen Bilimleri Enstitüsü.
• Buaisha, M., Balku, Ş., Yaman Özalp, Ş. (2019). ANN-assisted forecasting of adsorption efficiency to remove heavy metals. Turkish Journal of Chemistry, 43(5), 1407-1424.
• Yildiz, S. (2018) Artificial neural network approach for modeling of Ni(II) adsorption from aqueous solution by peanut shell. Ecol Chem Eng S., 25,581–604.
• Nemeček, P., Kružlicová, D. Remenárová, L. (2014). Application of Ann for Prediction of Co2+, Cd2+ and Zn2+ Ions Uptake by R. Squarrosus Biomass in Single and Binary Mixtures, Nova Biotechnologica et Chimica., 13(1), 73-84.
• Alizamir, M., Sobhanardakani, S. (2016). Forecasting of heavy metals concentration in groundwater resources of Asadabad plain using artificial neural network approach. Journal of Advances in Environmental Health Research, 4(2), 68-77.
• Javan, S., Gholamalizadeh Ahangar, A., Hassani, A.H, Soltani, J. (2019). Estimation of Zn Bonds Using Multi-Layer Perceptron (MLP) Artificial Neural Network Method in Chahnimeh, Zabol. 7(2), 87-95.
• Bayatzadeh Fard, Z., Ghadimi, F., Fattahi, H. (2017). Use of artificial intelligence techniques to predict distribution of heavy metals in groundwater of Lakan lead-zinc mine in Iran. Journal of Mining and Environment, 8(1), 35-48.
• Ağyar, Z. (2015).Yapay Sinir Ağlarının Kullanım Alanları ve Bir Uygulama. Mühendis ve Makine, 56(662), 22-23.
• Yazıcı, A.C., Öğüş, E., Ankaralı, S., Canan, S., Ankaralı, H., Akkuş, Z. (2007) Yapay Sinir Ağlarına Genel Bakış. Türkiye Klinikleri Tıp Bilimleri Dergisi, 27(1), 65-71.
• Eren, B., ve Eyüpoğlu, V. (2011). Yapay sinir ağları ile Ni(II)iyonu geri kazanım veriminin modellenmesi, 6th International Advanced Technologies Symposium, Elazığ.
• Panchal, F.S., & Panchal, M. (2014). Review on Methods of Selecting Number of Hidden Nodes in Artificial Neural Network. Computer Science, International Journal of Computer Science and Mobile Computing, 3(11), 455-464.
• Arifin, F., Robbani, H., Annisa, T., Ma’arof, N N M I 2. (2019). Variations in the Number of Layers and the Number of Neurons in Artificial Neural Networks: Case Study of Pattern Recognition. Journal of Physics: Conference Series, 1413.
• Gupta, T.K., Raza, K. (2020). Optimizing Deep Feedforward Neural Network Architecture: A Tabu Search Based Approach. Neural Process Lett., 51, 2855–2870.
• Wu, W., May, R., Dandy, G.C, and Maier, H.R. (2012). A method for comparing data splitting approaches for developing hydrological ANN models. International Congress on Environmental Modelling and Software, 394.
• Akıllı, A., Atıl, H. (2020). Evaluation of Normalization Techniques on Neural Networks for the Prediction of 305-Day Milk Yield. Turkish Journal of Agricultural Engineering Research, 1, 354-367.
• Aksu, G., Güzeller, C., Eser, M. (2019). The Effect of the Normalization Method Used in Different Sample Sizes on the Success of Artificial Neural Network Model. International Journal of Assessment Tools in Education, 6(2), 170-192 .
• Lake, H.R., Akbarzadeh A., Mehrjardi T. (2009). Development of pedotransfer functions (PTFs) to predict soil physico-chemical and hydrological characteristics in southern coastal zones of the Caspian Sea. Journal of Ecology and the Natural Environment., 1(7): 160-172.
• Amini, M., Abbaspour K.C., Khademi H., Fathianpour, N., Afyuni, M., Schulin R. (2005). Neural network models to predict cation exchange capacity in arid regions of Iran. Eur. J. Soil Sci., 53: 748-757.
• Keshavarzi, A., Sarmadian F. (2011).Comparison of Artificial Neural Network and Multivariate Regression Methods in Prediction of Soil Cation Exchange Capacity. International Journal of Environmental and Earth Sciences, 20111(1), 25-30.