Abstract
Membrane bioreactor (MBR) is one of the most popular sewage treatment technologies. However, membrane fouling, a complicated process, has a negative effect on the membrane service life and effluent quality. A model with high accuracy, stability, generalization ability was needed to overcome this problem. Artificial neural network (ANN) stands out from numerous machine learning modeling methods with self-learning and sufficient capacity to capture the nonlinear complexity processes. In this paper, back-propagation neural network models (BPNN) with different hyper parameters were proposed using back-propagation algorithm. To improve the efficiency of learning process, batch module was introduced into training dataset. 4000 samples experimental data have been collected with the MBR pilot plant, 60% was used for training, 20% was used for validation, the rest for testing. With the simulation result, in theory a three-layer ANN have the ability to fit any mapping problem was proved with an average of 98% for R2 performance. However, with the comparison of models with different hyper parameters, two hidden layer models have a better performance with appropriate neurons, within an acceptable computational load. Over-fitting phenomenon occurs when the number of nodes is too large, resulting in larger MAE.
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
Similar content being viewed by others
References
Zheng, Y., et al.: Membrane fouling mechanism of biofilm-membrane bioreactor (BF-MBR): Pore blocking model and membrane cleaning. Biores. Technol. 250, 398–405 (2018)
Krzeminski, P., et al.: Membrane bioreactors – a review on recent developments in energy reduction, fouling control, novel configurations, LCA and market prospects. J. Membr. Sci. V527, 207–227 (2017)
Wu, M., et al.: Membrane fouling caused by biological foams in a submerged membrane bioreactor: mechanism insights. Water Res. 181, 115932 (2020)
Du, X., et al.: A review on the mechanism, impacts and control methods of membrane fouling in MBR system. Membranes 10, 10020024 (2020)
Abdul Wahab, N., et al.: Permeate flux control in SMBR system by using neural network internal model control. Processes 8, 1672 (2020)
Zaghloul, M.S., et al.: Performance prediction of an aerobic granular SBR using modular multilayer artificial neural networks. Sci. Total Environ. 645, 449–459 (2018)
Zaghloul, M.S., et al.: Comparison of adaptive neuro-fuzzy inference systems (ANFIS) and support vector regression (SVR) for data-driven modelling of aerobic granular sludge reactors. J. Environ. Chem. Eng. 8, 103742 (2020)
Zhao, B.: Cleaning decision model of MBR membrane based on Bandelet neural network optimized by improved Bat algorithm. Appl. Soft Comput. J. 91, 106211 (2020)
Yusuf, Z., Wahab, N.A., et al.: Soft computing techniques in modelling of membrane filtration system: a review. Desalin. Water Treat. 161, 144–155 (2019)
Ren, N., Chen, Z., Wang, X., Hu, D., Wang, A.: Optimized operational parameters of a pilot scale membrane bioreactor for high-strength organic wastewater treatment. Int. Biodeterior. Biodegrad. 56, 216–223 (2005)
Wei, A.L., Zeng, G.M., Huang, G.H., Liang, J., Li, X.D.: Modeling of a permeate flux of cross-flow membrane filtration of colloidal suspensions: a wavelet network approach. Int. J. Environ. Sci. Tchnol. 6, 395–406 (2009)
Lee, Y.G., et al.: Artificial neural network model for optimizing operation of a seawater reverse osmosis desalination plant. Desalination 247, 180–189 (2009)
Yusuf, Z., Wahab, N.A., Sahlan, S.: Modeling of filtration process using PSO-neural network. J. Telecommun. Electron. Comput. Eng. 9, 15–19 (2017)
Schmidt-Hieber, J.: The Kolmogorov-Arnold representation theorem revisited. Neural Netw. 137, 119–126 (2021)
Zhang, Z.: Research on Modeling and Predictive Control of Heavy Duty Gas Turbine Based on Neural Network. D Beijing China, pp. 10–15 (2020)
Xu, H., Jagannathan, S.: Stochastic optimal controller design for uncertain nonlinear networked control system via neuro dynamic programming. IEEE Trans. Neural Netw. Lean. Syst. 24(5), 471–484 (2013)
Barello, M., Manca, D., Patel, R., Mujtaba, I.M.: Neural network based correlation for estimating water permeability constant in RO desalination process under fouling. Desalination 345, 101–111 (2014)
More, J.J.: The Levenberg-Marquardt Algorithm: Implementation and Theory (1978). https://doi.org/10.1007/bfb0067700
Madaeni, S.S., Shiri, M., Kurdian, A.R.: Modeling, optimization, and control of reverse osmosis water treatment in kazeroon power plant using neural network. Chem. Eng. Commun. 202, 6–14 (2015)
Acknowledgement
We are grateful to acknowledge the Ministry of Higher Education Malaysia (MOHE) and Universiti Technologi Malaysia (UTM) for the financial support under the University Grant under project number Q.J130000.3851.19J19.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Yin, L., Ismail, F.S., Wahab, N.A. (2022). Flux Modelling of Membrane Bioreactor Process Plant Using Optimized-BPNN. In: Fan, W., Zhang, L., Li, N., Song, X. (eds) Methods and Applications for Modeling and Simulation of Complex Systems. AsiaSim 2022. Communications in Computer and Information Science, vol 1713. Springer, Singapore. https://doi.org/10.1007/978-981-19-9195-0_1
Download citation
DOI: https://doi.org/10.1007/978-981-19-9195-0_1
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-9194-3
Online ISBN: 978-981-19-9195-0
eBook Packages: Computer ScienceComputer Science (R0)