PREDICTIVE MODELING OF OZONE DOSING IN DRINKING WATER TREATMENT PLANT USING DEEP LEARNING COMPARATIVE STUDY BETWEEN DEEP NEURAL NETWORKS AND CONVOLUTIONAL NEURAL NETWORKS

a; HELLAL, M. DJEDDOU, I. LOUKAM, A.I. HAMEED, J. AL DALLAL, M. SHAWAQFAH

Abstract


Ozone is known to be a powerful oxidant and disinfectant in drinking water production processes. The ozone dosing process presents a particularly difficult control problem due to its nonlinear behavior.

Most water treatment plants use ozone dosing by determining the ozone concentration based on operational experience without considering temporal variations in water quantity and quality. In this case, this approach can lead to an overdosing that can increase costs or an underdosing that will influence the quality of the treated water.

Two deep learning models, namely, the DNN model and CNN model, were applied for ozone dosing predictive modeling tasks. Comparing the results obtained in the training and testing processes, we notice that the DNN model with 5 hidden layers outperforms the CNN model. These results seem very encouraging, and the methodologies seem promising.

Keywords


Ozone dosing, Drinking water treatment, Deep learning, Predictive modeling

Full Text:

PDF

References


ACHOUR S., CHABBI F. (2014). Disinfection of drinking water-constraints and optimization perspectives in Algeria, Larhyss Journal, No 19, pp. 193-212.

ACHOUR S., CHABBI F. (2017). Study of oxidation/disinfection steps of treatment plant of Ain Tinn (Mila, Eastern Algeria), Larhyss Journal, No 31, pp. 233-247. (In French)

ACHOUR S., MODJAD H., HELLAL A., KELILI H. (2019). Optimization tests of clarification and disinfection processes of water dam of Khenchela area (Eastern Algeria), Larhyss Journal, No 37, pp. 151-174. (In French)

ADAOBI C.I., IGHALO J.O, IWUOZOR K.O., OKECHUKWU DOMINIC ONUKWULI O.D., OKOYE P.U., EID AL-RAWAJFEH A. (2022). Prediction and optimisation of coagulation-flocculation process for turbidity removal from aquaculture effluent using Garcinia kola extract: Response surface and artificial neural network methods, Cleaner Chemical Engineering, Vol 4, Paper 100076,

https://doi.org/10.1016/j.clce.2022.100076.

AGATONOVIC-KUSTRIN S., BERESFORD R. (2000). Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research, Journal of Pharmaceutical and Biomedical Analysis, Vol. 22, Issue 5, pp. 717-727.

ALAM G., IHSANULLAH I., NAUSHAD M., SILLANPÄÄ M. (2022). Applications of artificial intelligence in water treatment for optimization and automation of adsorption processes: Recent advances and prospects, Chemical Engineering Journal, Vol. 427, Paper130011. https://doi.org/10.1016/j.cej.2021.130011.

AUDENAERT W.T.M., CALLEWAERT M., INGMAR NOPENS I., CROMPHOUT J., VANHOUCKE R., DUMOULIN A., DEJANS P., VAN HULLE S.W.H. (2010). Full scale modelling of an ozone reactor for drinking water treatment, Chemical Engineering Journal, Vol. 157, Issue 2-3, pp.551–557.

BAEK S.S., PYO J., CHUN J.A. (2020). Prediction of water level and water quality using a CNNLSTM combined deep learning approach, Water, Vol.12, Issue 12, Paper 3399.

CLARK R.M., SIVAGENESAN M., RICE E.W., CHEN J. (2002). Development of a Ct equation for the inactivation of Cryptosporidium oocysts with ozone, Water Research, Vol.36, Issue 12, pp.3141-3149.

DA SILVA L.F., CATTO A.C., AVANSI, JR. W., CAVALCANTE L.S., ANDRÉS J., AGUIR K., MASTELARO V.L., LONGOA E. (2014). A novel ozone gas sensor based on one-dimensional (1D) a-Ag 2 WO 4 nanostructures. Nanoscale Journal, Vol. 6, Issue 8, pp. 4058–4062. https://doi.org/10.1039/C3NR05837A

DAN N., XIAOJUN W., XISONG C., LI D., JUN Y., FUCHUN J. (2021). Optimized dosage control of the ozonation process in drinking water treatment, Measurement and Control, Vol. 54, Issues 5-6, pp. 692–700.

DE VERA G.A.D., FARRE M.J., GERNJAK W., KELLER J. (2015). Changes in inorganic nitrogen ratio ([NH4+ -N]/[NO3–N]) during ozonation of drinking water and its application for micropollutant removal prediction, Disinfection Byproducts in Drinking Water, In book: Disinfection Byproducts in Drinking Water, Edited by K Clive Thompson; Simon Gillespie; Emma Goslan, 368 pages.

DOI: https://doi.org/10.1039/9781782622710.

DJEDDOU M., HELLAL A., LOUKAM I., HOUICHI L. (2022). Predictive modeling of ozone dosing in Full-scale drinking water treatment plant using Improved Hybrid Model Based on Discrete Wavelet Decomposition and Radial Basis Function Neural Network (WRBFNN), 3rd International Conference on Disinfection and DBPs, 27 June- 01 July, Milan, Italy, 4 p.

DONGSHENG W., YONGJIE L., LEI Z. (2017). A case study on the MPC for ozone dosing process based on SVM. In: 29th Chinese control and decision conference (CCDC), IEEE, Chongqing, 28–30 May, pp.1772–1776.

ELOVITZ M.S., GUNTEN U.V., KAISER H. (2000). Hydroxyl radical ozone ratios during ozonation processes. II. The effect of temperature, pH, alkalinity, and DOM properties, Ozone: Science & Engineering, Journal of the International Ozone Association, Vol.22, Issue 2, pp. 123–150.

GOMES J., COSTA R., QUINTA-FERREIRA R.M., MARTINS R.C. (2017). Application of ozonation for pharmaceuticals and personal care products removal from water, Science of The Total Environment, Vol.586, pp. 265–283.

GOODFELLOW I., BENGIO Y., COURVILLE, A. (2016). Deep learning. MIT press., ISBN 9780262035613, 800p.

HARRAT N., ACHOUR S. (2016). Behavior of humic substances from Zit El Amba dam during coagulation-flocculation in the presence of aluminium sulphate and activated carbon, Larhyss Journal, No 26, pp. 149-165. (In French)

KAISER H.P. KÖSTER O., GRESCH M., PÉRISSET P.M.J., JÄGGI P., SALHI E., VON GUNTEN U. (2013). Process control for ozonation systems: a novel real-time approach. Ozone: Science & Engineering, Journal of the International Ozone Association, Vol.35, Issue 3, pp.168–185.

KANG J.W, OH B.S., PARK S.Y., HWANG T.M., OH H.J., CHOUNG Y.K. (2008). An advanced monitoring and control system for optimization of the ozone AOP (Advanced Oxidation Process) for the treatment of drinking water. In Kim, YJ and Platt, U (eds.) Advanced environmental monitoring, The Netherlands: Springer, pp. 271–281.

KIM K.M, AHN J.H. (2022). Machine learning predictions of chlorophyll-a in the Han river basin, Korea, Journal of Environmental Management, Vol 318, Paper 115636

https://doi.org/10.1016/j.jenvman.2022.115636.

LE X.H., HO H.V., LEE G. (2019). River streamflow prediction using a deep neural network: a case study on the Red River, Vietnam. Korean Journal of Agricultural Science, Vol 46, pp.843-856. https://doi.org/10.7744/kjoas.20190068.

LECUN Y., BENGIO Y., HINTON G. (2015). Deep learning, Nature, Vol 52, pp. 436–444. https://doi.org/10.1038/nature14539.

LEE Y., KOVALOVA L., MCARDEL l.C.S., et al. (2014). Prediction of micropollutant elimination during ozonation of a hospital wastewater effluent, Water Research, Vol.64, pp.134–148.

LOWE M., QIN R., MAO X. (2022). A Review on Machine Learning, Artificial Intelligence, and Smart Technology in Water Treatment and Monitoring, Water, Vol. 14, Issue 9, Paper 1384.

MUNIYASAMY A., SIVAPORUL G., GOPINATH A., LAKSHMANAN R., ALTAEE A., ACHARY A., VELAYUDHAPERUMAL CHELLAM P.V. (2020). Process development for the degradation of textile azo dyes (mono-, di-, poly-) by advanced oxidation process – Ozonation: experimental & partial derivative modeling approach, Journal of environmental management, Vol. 265, Paper 110397. doi: 10.1016/j.jenvman.2020.110397

NIU D, WANG X, CHEN X, DING L, YANG J, JIANG F. (2021). Optimized dosage control of the ozonation process in drinking water treatment, Measurement and Control, Vol. 54, Issues 5-6, pp. 692-700. doi:10.1177/00202940211007164

OH H.J., KIM W.J., CHOI J.S, GEE C.S,HWANG T.M, KANG J.G., KANG J.W. (2010). Optimization and control of ozonation plant using raw water characterization method.Ozone: Science & Engineering, Journal of the International Ozone Association, Vol. 25, Issue 5, pp. 383–392.

O'SHEA K., NASH R. (2015). An Introduction to Convolutional Neural Networks. arXiv preprint arXiv:1511.08458, 2015 - arxiv.org. 11p.

PALKAR S., USGAONKAR S., ANSARI S. (2022). "Wq-Net: A Deep Neural Network Model For Water Quality Prediction," OCEANS 2022 - Chennai, Chennai, India, pp. 1-6. doi: 10.1109/OCEANSChennai45887.2022.9775235.

REN T., LIU X., NIU J., LEI X., ZHANG Z. (2020). Real-time water level prediction of cascaded channels based on multilayer perception and recurrent neural network, Journal of Hydrology, Vol 585, Paper 124783.

https://doi.org/10.1016/j.jhydrol.2020.124783.

REZA A., ASHLEY R., TERRI S.H. (2021). Development of a Multilayer Deep Neural Network Model for Predicting Hourly River Water Temperature From Meteorological Data, Frontiers in Environmental Science, Vol. 9, Article 738322.

https://doi.org/10.3389/fenvs.2021.738322.

SCHMIDHUBER J. (2015). Deep learning in neural networks: An overview. Neural networks, Vol. 61, pp. 85-117.

SHIN J., HIDAYAT Z.R., LEE Y. (2016). Influence of seasonal variation of water temperature and dissolved organic matter on ozone and OH radical reaction kinetics during ozonation of a lake water, Ozone: Science & Engineering, Journal of the International Ozone Association, Vol. 38, Issue 2, pp. 100–114.

SUN B., WANG Y., XIANG Y., SHANG C. (2020). Influence of preozonation of DOM on micropollutant abatement by UV-based advanced oxidation processes, Journal of Hazardous Materials, Vol.391, Paper 12220.

VAN DER HELM A.W.C., SMEETS P.W.M., BAARS E.T., RIETVELD L.C., VAN DIJK J.C. (2007). of ozonation for dissolved ozone dosing. Ozone: Science &Engineering, Journal of the International Ozone Association, Vol. 29, Issue 5, pp.379C–389C.

VAN DER HELM A.W.C., VAN DER AA L.T.J., VAN SCHAGEN K.M. (2009). Modeling of full-scale drinking water treatment plants with embedded plant control, Water Science & Technology Water Supply, Vol.9, Issue 3, pp. 253–261.

VON GUNTEN U. (2003). Ozonation of drinking water: Part I, Oxidation kinetics and product formation, Water Research, Vol.37, Issue 7, pp.1443-146.

WANG D., LI S., YANG J., YOU Z., ZHOU X. (2014) Adaptive MPC for ozone dosing process of drinking water treatment based on RBF modeling. Transactions of the Institute of Measurement and Control, Vol. 36, Issue 1, pp. 58–67.

WOLS B.A., HOFMAN J.A.M.H., UIJTTEWAAL W.S.J., RIETVELD L.C., STELLING G.S., VANDIJK J.C. (2008). Residence time distributions in ozone contactors, Ozone: Science & Engineering, Journal of the International Ozone Association, Vol.30, Issue 1, pp. 49-57.

XIE Y., CHEN Y., LIAN Q., YIN H., PENG J., SHENG M., WANG Y. (2022). Enhancing real-time prediction of effluent water quality of wastewater treatment plant based on improved feed forward neural network coupled with optimization algorithm, Water, Vol.14, Issue 7, Paper 1053.


Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.