The use of artificial neural networks for the assessment of the operation of settling tanks

Domurat, Katarzyna; Ochowiak, Marek; Krupińska, Andżelika; Włodarczak, Sylwia; Ochowiak, Oskar; Tomikowska, Róża; Tomikowski, Rafał; Matuszak, Magdalena

doi:10.2478/pjct-2025-0001

Abstract

The aim of the research was to develop and evaluate the usefulness of artificial neural network models for predicting the key operating parameters of centrifugal settlers. Various settler structures were analyzed, taking into account such elements as internal partitions and also inlet and outlet nozzles. Neural network modeling was continued until the highest possible quality was achieved in terms of training, testing and validation, with the occurrence of errors also being minimized. This process involved multiple iterations and adjustments of the network’s parameters to achieve optimal results. It was shown that artificial neural networks are characterized by having high accuracy in predicting the efficiency and damming values of centrifungal sedimentation tanks with regards to their design and hydraulic load. The designed network is able to determine both efficiency and liquid level with satisfactory accuracy.

References

Markowska, M. (2021). The analysis of separation process of solid-liquid and liquid-liquid in modified swirl settling tanks. PhD Thesis, Poznan University of Technology, Poznan (in Polish).
Search in Google Scholar Back to article
Southard, M.Z., Green, D.W. (2018). Perry’s Chemical Engineers’ Handbook, 9th Edition, McGraw-Hill Education, New York.
Search in Google Scholar Back to article
Królikowska, J. (2011). Influence of wastewater treatment technology on particle size distribution in the effluent. Inż. Ekol. 26, 156–170.
Search in Google Scholar Back to article
Czernek, K., Ochowiak, M., Janecki, D., Zawilski, T., Dudek, L., Witczak, S., Krupińska, A., Matu-szak, M., Włodarczak, S., Hyrycz, M., Pavlenko, I. (2021). Sedimentation tanks for treating rainwater: CFD simulations and PIV experiments. Energies, 14(23), 7852. DOI: 10.3390/en14237852.
Search in Google Scholar Back to article
Ochowiak, M., Matuszak, M., Włodarczak, S., Ancukiewicz, M., Gościniak, A. (2016). Study on ef-ficiency of rainwater stream purification in a swirl sedimentation tank. Inż. Ap. Chem. 5, 199–200.
Search in Google Scholar Back to article
Ochowiak, M., Matuszak, M., Włodarczak, S., Ancukiewicz, M., Krupińska, A. (2017). Evaluation of the work of modified swirl sedimentation tank for purification of rainwater stream contaminated by light fraction. Inż. Ap. Chem. 4, 132–133.
Search in Google Scholar Back to article
Ochowiak, M., Markowska, M., Matuszak, M., Włodarczak, S. (2018). Analysis of work of a modified swirl separation tank. Inż. Ap. Chem. 1, 12–13.
Search in Google Scholar Back to article
Aglodiya, A. (2017). Application of Artificial Neural Network (ANN) in chemical engineering: A review. Korean J. Chem. Eng. 17(4), 373–392. DOI: 16.0415/IJARIIE-5013.
Search in Google Scholar Back to article
Din, M., Smith, D., Gamal, A. (2004). Application of artificial neural networks in wastewater treat-ment. J. Environ. Eng. Sci. 3, S1. DOI: 10.1139/s03-067.
Search in Google Scholar Back to article
Yanbo, H. (2009). Advances in Artificial Neural Networks – methodological development and ap-plication. Algorithms. 2(3), 973–1007. DOI: 10.3390/algor2030973.
Search in Google Scholar Back to article
Guiné, R., Dets, C. (2019). The use of Artificial Neural Networks (ANN) in food process engineering. ETP Int. J. Food Eng. 5(1), 15–21. DOI: 10.18178/ijfe.5.1.15-21.
Search in Google Scholar Back to article
Saharawat, D., Kashyap, P., Kisi, O. (2018). Simulation of suspended sediment based on gamma test, heuristic, and regression-based techniques. Environ. Earth Sci. 77, 1–14. DOI: 10.1007/s12665-018-7892-6.
Search in Google Scholar Back to article
Taloba, A.I. (2022). An Artificial Neural Network mechanism for optimizing the water treatment process and desalination process. Alexandria Eng. J. 61, 9287–9295. DOI: 10.1016/j.aej.2022.03.029.
Search in Google Scholar Back to article
Gamal El-Din, A., Smith, D. (2002). Modeling a full-scale primary sedimentation tank. Environ. Tech. 23(5), 479–496. DOI: 10.1080/09593332308618384.
Search in Google Scholar Back to article
Szaleniec, M. (2008). Neural networks and multiple regression: How to tackle complexity in scientific research?, Kraków, www.statsoft.pl, (in Polish).
Search in Google Scholar Back to article
Yang, Y., Rosenbaum, M. (2001). Artificial Neural Networks linked to GIS for determining sedi-mentology in harbours. J. Petroleum Sci. Eng. 29(3), 213–220. DOI: 10.1016/s0920-4105(01)00091-2.
Search in Google Scholar Back to article
Haykin, S. (1999). Neural networks: A comprehensive foundation, Second Edition, Prentice-Hall, Englewood Cliffs, Corpus ID: 60577818.
Search in Google Scholar Back to article
Rummelhart, D., Hinton, G., Williams, R. (1986). Learning representations by back-propagating errors, Nature. DOI: 10.1038/323533a0.
Search in Google Scholar Back to article
Meireles, M., Almeida, P., Simoes, M. (2003). A comprehensive review for industrial applicability of Artificial Neural Networks. IEEE Trans. Ind. Elect. 50(3), 585–601. DOI: 10.1109/TIE.2003.812470.
Search in Google Scholar Back to article
Han, J., Kamber, M., Pei, J. (2011). Data mining: concepts and techniques, Morgan Kaufmann Pulisers In. DOI: 10.1016/C2009-0-61819-5.
Search in Google Scholar Back to article
Goodfellow, I., Bengio, Y., Courville, A. (2016). Deep learning, MIT Press, 19: 305–307. DOI: 10.1007/s10710-017-9314-z.
Search in Google Scholar Back to article
Bichri, H., Chergui, A., Mustapha, H. (2024). Investigating the impact of train/test split ratio on the performance of pre-trained models with custom datasets. Int. J. Adv. Comp. Sci. Appl. 15. DOI: 10.14569/IJACSA.2024.0150235.
Search in Google Scholar Back to article
Domurat, K. (2024). The application of artificial neural networks for evaluating the performance of settling tanks, MSc Thesis, Poznan University of Technology, Poznan.
Search in Google Scholar Back to article

The use of artificial neural networks for the assessment of the operation of settling tanks

Abstract

Paradigm

My account