Abstract
A continuous stirred tank bioreactor (CSTB) with cell recycling combined with ceramic membrane technology and inoculated with Rhodococcus opacus PD630 was employed to treat petroleum refinery wastewater for simultaneous chemical oxygen demand (COD) removal and lipid production from the retentate obtained during wastewater treatment. In the present study, the COD removal efficiency (CODRE) (%) and lipid concentration (g/L) were predicted using two artificial intelligence models, i.e., an artificial neural network (ANN) and a neuro-fuzzy neural network (NF-NN) with a network topology of 6-25-2 being the best for NF-NN. The results revealed the superiority of NF-NN over ANN in terms of determination coefficient (R2), root mean square error (RMSE), and mean absolute percentage error (MAPE). Three learning algorithms were tested with NF-NN; among them, the Bayesian regularization backpropagation (BR-BP) outperformed others. The sensitivity analysis revealed that, if solid retention time and biomass concentrations were maintained between 35 and 75 h and 3.0 g/L and 3.5 g/L, respectively, high CODRE (93%) and lipid concentration (2.8 g/L) could be obtained consistently.
Graphical abstract
Similar content being viewed by others
Data availability
Supporting information may be found in the online version of this article.
Abbreviations
- ANFIS:
-
Adaptive neuro-fuzzy inference system
- ANN:
-
Artificial neural network
- BP-NN:
-
Back propagation neural network
- BR-BP:
-
Bayesian regularization backpropagation
- COD:
-
Chemical oxygen demand
- CODRE :
-
COD removal efficiency
- CSTB:
-
Continuous stirred tank bioreactor
- GDX:
-
Gradient descent with momentum and adaptive learning rate
- HRT:
-
Hydraulic retention time
- HTL:
-
Hydrothermal liquefaction
- LM-BP:
-
Levenberg Marquardt backpropagation
- MAPE :
-
Mean absolute percentage error
- MF:
-
Membership function
- NF-NN:
-
Neuro-fuzzy neural network
- R 2 :
-
Determination coefficient
- RMSE :
-
Root mean square error
- SRT:
-
Solid retention time
- WWTP:
-
Wastewater treatment plant
- η :
-
Learning rate
- α :
-
Momentum term
- μ :
-
Marquardt adjustment parameter
- T c :
-
Training cycle
- N H :
-
Number of neurons in the hidden layer
- W ij :
-
Weights of the input neurons
- X i :
-
Inputs to the neural network
- θ j :
-
Bias term of the input neurons
References
Arshad F, Selvaraj M, Banat F, Haija MA (2020) Removal of metal ions and organics from real refinery wastewater using double-functionalized graphene oxide in alginate beads. J Water Process Eng 38:101635
Paul T, Baskaran D, Pakshirajan K, Pugazhenthi G (2020) Valorization of refinery wastewater for lipid-rich biomass production by Rhodococcus opacus in batch system: a kinetic approach. Biomass Bioenergy 143:105867
Jain M, Majumder A, Ghosal PS, Gupta AK (2020) A review on treatment of petroleum refinery and petrochemical plant wastewater: a special emphasis on constructed wetlands. J Environ Manag 272:111057
Paul T, Baskaran D, Pakshirajan K, Pugazhenthi G (2019) Continuous bioreactor with cell recycle using tubular ceramic membrane for simultaneous wastewater treatment and bio-oil production by oleaginous Rhodococcus opacus. Chem Eng J 367:76–85
Gopikiran M, Das R, Behera SK, Pakshirajan K, Das G (2021) Modelling a rotating biological contactor treating heavy metal contaminated wastewater using artificial neural network. Water Supply 21:1895–1912
Yu L, Yang Y, Yang B, Li Z, Zhang X, Hou Y, Lei L, Zhang D (2018) Effects of solids retention time on the performance and microbial community structures in membrane bioreactors treating synthetic oil refinery wastewater. Chem Eng J 344:462–468
Moser PB, Bretas C, Paula EC, Faria C, Ricci BC, Cerqueira ACFP, Amaral MCS (2019) Comparison of hybrid ultrafiltration-osmotic membrane bioreactor and conventional membrane bioreactor for oil refinery effluent treatment. Chem Eng J 378:121952
Paul T, Sinharoy A, Pakshirajan K, Pugazhenthi G (2020) Lipid-rich bacterial biomass production using refinery wastewater in a bubble column bioreactor for bio-oil conversion by hydrothermal liquefaction. J Water Process Eng 37:101462
Khanongnuch R, Abubackar HN, Keskin T, Gungormusler M, Duman G, Aggarwal A, Behera SK, Li L, Bayar B, Rene ER (2022) Bioprocesses for resource recovery from waste gases: current trends and industrial applications. Renew Sustain Energy Rev 156:111926
Civelekoglu G, Yigit NO, Diamadopoulos E, Kitis M (2009) Modelling of COD removal in a biological wastewater treatment plant using adaptive neuro-fuzzy inference system and artificial neural network. Water Sci Technol 60:1475–1487
Cakmakci M (2007) Adaptive neuro-fuzzy modelling of anaerobic digestion of primary sedimentation sludge. Bioprocess Biosyst Eng 30:349–357
Taheri E, Amin MM, Fatehizadeh A, Rezakazemi M, Aminabhavi TM (2021) Artificial intelligence modelling to predict transmembrane pressure in anaerobic membrane bioreactor-sequencing batch reactor during biohydrogen production. J Environ Manag 292:112759
Vasaki M, Karri RR, Ravindran G, Paramasivan B (2021) Predictive capability evaluation and optimization of sustainable biodiesel production from oleaginous biomass grown on pulp and paper industrial wastewater. Renew Energ 168:204–215
Waewsak C, Nopharatana A, Chaiprasert P (2010) Neural-fuzzy control system application for monitoring process response and control of anaerobic hybrid reactor in wastewater treatment and biogas production. J Environ Sci 22:1883–1890
Mullai P, Arulselvi S, Ngo HH, Sabarathinam PL (2011) Experiments and ANFIS modelling for the biodegradation of penicillin-G wastewater using anaerobic hybrid reactor. Bioresour Technol 102:5492–5497
Saini R, Kumar P (2016) Optimization of chlorpyrifos degradation by Fenton oxidation using CCD and ANFIS computing technique. J Environ Chem Eng 4:2952–2963
Manu DS, Thalla AK (2017) Artificial intelligence models for predicting the performance of biological wastewater treatment plant in the removal of Kjeldahl Nitrogen from wastewater. Appl Water Sci 7:3783–3791
Asadi M, Guo H, McPhedran K (2020) Biogas production estimation using data-driven approaches for cold region municipal wastewater anaerobic digestion. J Environ Manag 253:109708
Sahinkaya E (2009) Biotreatment of zinc-containing wastewater in a sulfidogenic CSTR: performance and artificial neural network (ANN) modelling studies. J Hazard Mater 164:105–113
Sinharoy A, Pakshirajan K (2019) Heavy metal sequestration by sulfate reduction using carbon monoxide as the sole carbon and energy source. Process Biochem 82:135–143
Loyola-Gonzalez O (2019) Black-box vs. white-box: Understanding their advantages and weaknesses from a practical point of view. IEEE Access 7:154096–154113
Sainz GI, Fuente MJ, Vega P (2004) Recurrent neuro-fuzzy modelling of a wastewater treatment plant. Eur J Control 10:84–96
Giwa A, Daer S, Ahmed I, Marpu PR, Hasan SW (2016) Experimental investigation and artificial neural networks ANNs modelling of electrically-enhanced membrane bioreactor for wastewater treatment. J Water Process Eng 11:88–97
Pinto J, Mestre M, Ramos J, Costa RS, Striedner G, Oliveira R (2022) A general deep hybrid model for bioreactor systems: combining first principles with deep neural networks. Comput Chem Eng 165:107952
Rene ER, Veiga MC, Kennes C (2009) Performance of a biofilter for the removal of high concentrations of styrene under steady and non-steady state conditions. J Hazard Mater 168:282–290
Zhang L, Wang F, Xu B, Chi W, Wang Q, Sun T (2018) Prediction of stock prices based on LM-BP neural network and the estimation of overfitting point by RDCI. Neural Comput Appl 30:1425–1444
Samanataray S, Sahoo A (2021) A comparative study on prediction of monthly streamflow using hybrid ANFIS-PSO approaches. KSCE J Civ Eng 25:4032–4043
Meher SK, Behera SK, Rene ER, Park HS (2017) Comparative analysis on the application of neuro-fuzzy models for complex engineered systems: case study from a landfill and a boiler. Expert Syst 34:12215
Zaghloul MS, Hamza RA, Iorhemen OT, Tay JH (2020) 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
Pal SK, Mitra S (1992) Multilayer perceptron, fuzzy sets, and classification. IEEE Trans Neural Netw 3:683–697
Zadeh LA (1965) Fuzzy sets. Inf Control 8:338–353
Maier HR, Dandy GC (1998) The effect of internal parameters and geometry on the performance of back-propagation neural networks: an empirical study. Environ Modell Softw 13:193–209
Meher SK, Behera SK, Kim MC, Park HS (2015) Multiple decision expert systems for performance analysis of a boiler system. Appl Artif Intell 29:839–858
Sakizadeh M (2016) Artificial intelligence for the prediction of water quality index in groundwater systems. Model Earth Syst Environ 2:1–9
Fatih T (2022) The use of artificial neural networks for modeling color and chemical oxygen demand removal from olive mill wastewater using grape molasses soil. Environ Mod Assess 27(5):855–868
Abba SI, Usman AG, Danmaraya YA, Usman AG, Abdullahi HU (2020) Modelling of water treatment plant performance using artificial neural network: case study Tamburawa Kano - Nigeria. Dutse J Pure Appl Sci 6:135–144
Ahmed AN, Othman FB, Afan HA, Ibrahim RK, Fai CM, Hossain MS, Ehteram M, Elshafie A (2019) Machine learning methods for better water quality prediction. J Hydrol 578:124084
Rezaabad MZ, Ghazanfari S, Salajegheh M (2020) ANFIS modelling with ICA, BBO, TLBO, and IWO optimization algorithms and sensitivity analysis for predicting daily reference evapotranspiration. J Hydrol Eng 25:04020038
Kumar S, Gupta N, Pakshirajan K (2015) Simultaneous lipid production and dairy wastewater treatment using Rhodococcus opacus in a batch bioreactor for potential biodiesel application. J Environ Chem 3:1630–1636
Gupta N, Manikandan NA, Pakshirajan K (2018) Real-time lipid production and dairy wastewater treatment using Rhodococcus opacus in a bioreactor under fed-batch, continuous and continuous cell recycling modes for potential biodiesel application. Biofuels 9:239–245
Rene ER, López ME, Veiga MC, Kennes C (2011) Neural network models for biological waste-gas treatment systems. New Biotechnol 29:56–73
Visali K, Chitra M, Pappa N (2017) Automation and design of real-time controllers for a laboratory scale bioreactor. In: International conference on innovations in control, communication and information systems, pp 12–13
Petre E, Selişteanu D, Şendrescu D, Ionete C (2010) Neural networks-based adaptive control for a class of nonlinear bioprocesses. Neural Comput Appl 19:169–178
Awual MR (2019) An efficient composite material for selective lead (II) monitoring and removal from wastewater. J Environ Chem Eng 7:103087
Negi BB, Aliveli M, Behera SK, Das R, Sinharoy A, Rene ER, Pakshirajan K (2022) Predictive modelling and optimization of an airlift bioreactor for selenite removal from wastewater using artificial neural networks and particle swarm optimization. Environ Res 219:115073
Wang Q, Cao Z, Liu Q, Zhang J, Hu Y, Zhang J (2019) Enhancement of COD removal in constructed wetlands treating saline wastewater: intertidal wetland sediment as a novel inoculation. J Environ Manag 249:109398
Bhat AP, Gogate PR (2021) Cavitation-based pre-treatment of wastewater and waste sludge for improvement in the performance of biological processes: a review. J Environ Chem Eng 9:104743
Işik M, Sponza DT (2004) Anaerobic/aerobic sequential treatment of a cotton textile mill wastewater. J Chem Technol Biotechnol 79:1268–1274
Aravantinou AF, Manariotis ID (2016) Effect of operating conditions on Chlorococcum sp. growth and lipid production. J Environ Chem Eng 4:1217–1223
Wada N, Ueta R, Osakabe Y, Osakabe K (2020) Precision genome editing in plants: state-of-the-art in CRISPR/Cas9-based genome engineering. BMC Plant Biol 20:1–12
Zhuang X (2021) Spatially resolved single-cell genomics and transcriptomics by imaging. Nat methods 18:18–22
Acknowledgements
The authors would like to extend their appreciation to the Department of Biosciences and Bioengineering at the Indian Institute of Technology Guwahati, India, for making the experimental dataset available to perform this artificial intelligence (AI) based modeling study. Eldon R. Rene thanks IHE Delft (The Netherlands) for providing staff time and infrastructure support through the “Support to Society” project to collaborate with researchers in AI and its applications to environmental bioprocesses.
Funding
There was no specific grant for this research from public, private, or non-profit funding organisations.
Author information
Authors and Affiliations
Contributions
Tanushree Paul: Investigation; Ayushi Agarwal: Writing—original draft, Methodology, Software; Shishir Kumar Behera: Conceptualization, Writing—Review & Editing, Modelling supervision; Saroj Kumar Meher: Conceptualization-equal, Software, Writing—Review & Editing; Shradha Gupta: Writing—original draft, Methodology, Software; Divya Baskaran: Investigation; Eldon R. Rene: Writing—Review & Editing; Kannan Pakshirajan: Investigation, Resources, Experimental supervision; G. Pugazhenthi: Supervision.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no known competing personal or financial interests with any other person, organization or funding agency that would appear to influence this work.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Paul, T., Aggarwal, A., Behera, S.K. et al. Neuro-fuzzy modelling of a continuous stirred tank bioreactor with ceramic membrane technology for treating petroleum refinery effluent: a case study from Assam, India. Bioprocess Biosyst Eng 47, 91–103 (2024). https://doi.org/10.1007/s00449-023-02948-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00449-023-02948-4