Abstract
Membrane fouling is one of the major problems in desalination processes as it can cause a severe drop in the quality and quantity of the permeate water. This paper presents a data-driven approach for long-term forecasting of fouling behavior in membrane-based desalination processes. The proposed Long-term forecastIng ModEl (LIME) consists of two intertwined machine learning models trained separately by historical operating conditions of ultrafiltration for pretreatment of reverse osmosis seawater where transmembrane pressure is used as a fouling indicator. The first model predicts the increase in fouling due to filtration. This output is fed to the second model to predict the fouling reduction due to membrane cleaning. In turn, this output is used as the initial fouling condition for predicting the next filtration cycle. The forecasted fouling is used to estimate the membrane’s remaining useful life (RUL), which ends when cleaning no longer reduces the fouling below a safety threshold. Evaluation results show that the model can predict the membrane fouling for 1400 cycles with an R-squared score of 0.8. Moreover, the RUL is estimated for various thresholds with an average percentage error of 7%.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Barandas, M., et al.: TSFEL: time series feature extraction library. SoftwareX 11, 100456 (2020)
Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)
Cai, G., Li, C.: Application of improved wavelet neural network in MBR flux prediction. In: Proceedings of the 16th IEEE/ACIS International Conference on Computer and Information Science, ICIS 2017, pp. 359–363. Institute of Electrical and Electronics Engineers Inc. (2017)
Choi, Y., Lee, Y., Shin, K., Park, Y., Lee, S.: Analysis of long-term performance of full-scale reverse osmosis desalination plant using artificial neural network and tree model. J. Environ. Eng. 25(5), 763–770 (2020)
Cohen, Y., Zhou, Y., Khan, B., Gu, H.: Dryad Data - UF pre-treatment of seawater RO feedwater - performance data (2021)
Fane, T.: Irreversible fouling. In: Drioli, E., Giorno, L. (eds.) Encyclopedia of Membranes, pp. 1–2. Springer, Heidelberg (2015). https://doi.org/10.1007/978-3-642-40872-4_328-1
Gao, L.X., Rahardianto, A., Gu, H., Christofides, P.D., Cohen, Y.: Novel design and operational control of integrated ultrafiltration - reverse osmosis system with RO concentrate backwash. Desalination 382, 43–52 (2016)
Jawad, J., Hawari, A.H., Javaid Zaidi, S.: Artificial neural network modeling of wastewater treatment and desalination using membrane processes: a review. Chem. Eng. J. 419, 129540 (2021)
Klambauer, G., Unterthiner, T., Mayr, A., Hochreiter, S.: Self-normalizing neural networks. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 972–981 (2017)
Nectoux, P., et al.: PRONOSTIA: an experimental platform for bearings accelerated degradation tests. In: IEEE International Conference on Prognostics and Health Management, PHM 2012, Colorado, USA, pp. 1–8 (2012)
Oishi, H., Kaneko, H., Funatsu, K.: Adaptive model and model selection for long-term transmembrane pressure prediction in membrane bioreactors. J. Memb. Sci. 494, 86–91 (2015)
Schmitt, F., Banu, R., Yeom, I.T., Do, K.U.: Development of artificial neural networks to predict membrane fouling in an anoxic-aerobic membrane bioreactor treating domestic wastewater. Biochem. Eng. J. 133, 47–58 (2018)
Zhang, B., et al.: Backwash sequence optimization of a pilot-scale ultrafiltration membrane system using data-driven modeling for parameter forecasting. J. Memb. Sci. 612, 118464 (2020)
Zhang, W., Liang, W., Huang, G., Wei, J., Ding, L., Jaffrin, M.Y.: Studies of membrane fouling mechanisms involved in the micellar-enhanced ultrafiltration using blocking models. RSC Adv. 5(60), 48484–48491 (2015)
Zhao, Z., Wu, J., Li, T., Sun, C., Yan, R., Chen, X.: Challenges and opportunities of AI-enabled monitoring, diagnosis & prognosis: a review. Chin. J. Mech. Eng. 34(1), 1–29 (2021)
Zheng, Y., Zhang, W., Tang, B., Ding, J., Zheng, Y., Zhang, Z.: Membrane fouling mechanism of biofilm-membrane bioreactor (BF-MBR): pore blocking model and membrane cleaning. Bioresour. Technol. 250, 398–405 (2018)
Zhou, Y., Khan, B., Gu, H., Christofides, P.D., Cohen, Y.: Modeling UF fouling and backwash in seawater RO feedwater treatment using neural networks with evolutionary algorithm and Bayesian binary classification. Desalination 513, 115129 (2021)
Acknowledgment
This publication was made possible by Qatar University High Impact grant [QUHI-CENG-21/22-2] from Qatar University. The statements made herein are solely the responsibility of the authors.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Eltanbouly, S., Erradi, A., Tantawy, A., Said, A.B., Shaban, K., Qiblawey, H. (2023). LIME: Long-Term Forecasting Model for Desalination Membrane Fouling to Estimate the Remaining Useful Life of Membrane. In: Fujita, H., Wang, Y., Xiao, Y., Moonis, A. (eds) Advances and Trends in Artificial Intelligence. Theory and Applications. IEA/AIE 2023. Lecture Notes in Computer Science(), vol 13926. Springer, Cham. https://doi.org/10.1007/978-3-031-36822-6_1
Download citation
DOI: https://doi.org/10.1007/978-3-031-36822-6_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-36821-9
Online ISBN: 978-3-031-36822-6
eBook Packages: Computer ScienceComputer Science (R0)