2. Home
  3. ARCHIVE
  4. 2022
  5. VOL 44, NO 6 (2022)
  6. pp. 36-47

DEVELOPMENT OF AN INTELLIGENT COAGULANT DOSING SYSTEM FOR THE WATER PURIFICATION PROCESS BASED ON AN ARTIFICIAL NEURAL NETWORK

A.P. Safonyk, M.B. Matviichuk

Èlektron. model. 2022, 44(6):36-47

https://doi.org/10.15407/emodel.44.06.036

ABSTRACT

The article reveals the essence and features of an artificial neural network, which is used to regulate water purification processes. Features, principles and main stages of water purification are determined. The stages of learning artificial neural networks are disclosed. The approach to the use of artificial neural networks during dosing of the mixture for water purification is substantiated. The process of dosing the mixture for water purification and the related indicators, which are important for the implementation of the water purification process, are analyzed. A number of factors that directly affect the coagulation process and, as a result, the structure of the neural network include turbidity and flow speed. It is shown that determining the dose of coagulant is necessary to minimize time, implement a continuous process, stabilize variations in the operator’s observations, and improve the quality of water treatment. A coagulant dose adjustment mode is proposed, as well as a water purification process control scheme based on the developed artificial neural network with unsupervised learning, which is used to optimize the coagulant dosage in the water purification process.

KEYWORDS

neural network, automatic dosing, coagulant, water purification, intelligent information system.

REFERENCES

  1. Zorina, S.O. (2019), “Hygienic problems of drinking water supply in Ukraine and ways to solve them in the conditions of European integration”, Qualifying scientific work. Abstract of Doc. Sci. (Bio.), dissertation, 02.14.01, Kyiv, Ukraine, available at: http://www.health.gov.ua/ docs/zorina/dissertatsia_Zorina.pdf.
  2. Nidheesh, P.V., Jaimy, S., Syam Babu, D. and Suresh Kumar, M. (2021), “An overview on combined electrocoagulation-degradation processes for the effective treatment of water and wastewater”, Chemosphere, Vol. 263, no. 127907, DOI: https://doi.org/10.1016/j.chemosphere.2020.127907
  3. Guohua, Chen. (2004), “Electrochemical technologies in wastewater treatment”, Separation and Purification Technology, Vol. 38, pp. 11-41, DOI: https://doi.org/10.1016/j.seppur.2003.10.006
  4. Cao, W. and Yang, Q. (2020), “Online sequential extreme learning machine based adaptive control for wastewater treatment plant”, Neurocomputing, Vol. 408, pp.169-175, DOI:https://doi.org/10.1016/j.neucom.2019.05.109
  5. Qiao, J., Guang, H. and Hong‐gui, H. (2013), “Neural Network On-Line Modeling and Controlling Method for Multi-Variable Control of Wastewater Treatment Processes”, Asian Journal of Control, Vol. 4, pp. 1213-1223, DOI: https://doi.org/10.1002/asjc.758
  6. Rahman, M.S. and Islam, M.R. (2020), “Sustainability of Current Water Purification Technologies”, Sustainable Water Purification, pp. 59-122, DOI: https://doi.org/10.1002/9781119651123.ch3
  7. Larissa, F. da Silva, Barbosa, A.D., Heber P.M., Romualdo L.R. and Andrade L.S. (2016), “Treatment of paint manufacturing wastewater by coagulation/electrochemical methods: Proposals for disposal and/or reuse of treated water”, Water Research, Vol. 101, pp. 467-475, DOI: https://doi.org/10.1016/j.watres.2016.05.006
  8. Wang, G., Jia, Q.-S., MengChu, Z., Bi, J. and Qiao, J. (2021). “Soft-sensing of Wastewater Treatment Process via Deep Belief Network with Event-triggered Learning”, Neurocomputing, Vol. 436, pp. 103-113, DOI: https://doi.org/10.1016/j.neucom.2020.12.108
  9. Min, L., Jongho, W., Sehyun, C., Seonghwan, K. and Simon, S. (2022), “Rapid detection of ionic contents in water through sensor fusion and convolutional neural network”, Chemosphere, Vol. 294, no. 133746, DOI: https://doi.org/10.1016/j.chemosphere.2022.133746
  10. Safonyk, A., Tarhonii, I., Hrytsiuk, I., Rudyk, A. and Ilkiv, I. (2021), “Dynamic optimization of the technological water treatment process automatic control system”, 2021 11th International Conference on Advanced Computer Information Technologies (ACIT), pp. 13-18, DOI: https://doi.org/10.1109/ACIT52158.2021.9548486
  11. Safonyk, A., Mishchanchuk, M. and Hrytsiuk, I. (2020). “Spectrophotometric method for coagulant determining in a stream based on an artificial neural network”, ISDMCI 2021: Lecture Notes in Computational Intelligence and Decision Making, pp. 589–601, DOI: https://doi.org/10.1007/978-3-030-82014-5_40
  12. Safonyk, A., Mishchanchuk, M. and Lytvynenko, V. (2021). “Intelligent information system for the determination of iron in coagulants based on a neural network”, Conference Paper 11th International Conference on Advanced Computer information Technologies (ACIT2021), Deggendorf, Germany, available at: https://ceur-ws.org/Vol-2853/short13.pdf.

Full text: PDF