Novel performance prediction model of a biofilm system treating domestic wastewater based on stacked denoising auto-encoders deep learning network

Abstract Stacked denoising auto-encoders (SDAE) deep learning network was used to predict the performance of a two-stage biofilm system, which was constructed based on traditional anaerobic/oxic process. Eight input variables were adopted for performance predicting, including concentrations of chemical oxygen demand (COD), ammonia (NH4+-N) and total nitrogen (TN) of biofilm system influent, concentrations of COD, NH4+-N and TN of anoxic biofilm reactor effluent, influent flow and reflux ratio of biofilm system. While concentrations of COD, NH4+-N and TN of biofilm system effluent were employed as output variables for COD, NH4+-N and TN prediction model, respectively. Root mean square error, mean absolute error, mean relative error and residuals were adopted for evaluating the fitness of the SDAE deep learning network model. Backpropagation neural network, support vector regression, extreme learning machine, gradient boosting decision tree and stacked auto-encoders were adopted for comparison to further demonstrate the effectiveness of the proposed method. Compared with the five contrast models, SDAE deep learning network model showed the best results, suggesting the possible application of performance prediction of the biofilm process with SDAE deep learning network model.

[1]  Christos S. Akratos,et al.  An artificial neural network model and design equations for BOD and COD removal prediction in horizontal subsurface flow constructed wetlands , 2008 .

[2]  J. J. Chen,et al.  Full scale case studies of a simplified aerated filter (BAF) for organics and nitrogen removal , 2000 .

[3]  En Shi,et al.  Estimation of biogas and methane yields in an UASB treating potato starch processing wastewater with backpropagation artificial neural network. , 2017, Bioresource technology.

[4]  Nadine Hajj,et al.  Deep belief networks and cortical algorithms: A comparative study for supervised classification , 2019, Applied Computing and Informatics.

[5]  Hans-Peter Kaballo.  Shock loading management with the sequencing batch biofilm reactor technology , 1997 .

[6]  J. M. Morgan-Sagastume,et al.  Evaluation of an aerobic submerged filter packed with volcanic scoria. , 2008, Bioresource technology.

[7]  Wei Zhang,et al.  Emotion recognition by assisted learning with convolutional neural networks , 2018, Neurocomputing.

[8]  M. Arivazhagan,et al.  Removal of high concentration of sulfate from pigment industry effluent by chemical precipitation using barium chloride: RSM and ANN modeling approach. , 2018, Journal of environmental management.

[9]  Yang Dong,et al.  A new method to measure and model dynamic oxygen microdistributions in moving biofilms. , 2017, Environmental pollution.

[10]  S. Hong,et al.  Effect of zeolite media for the treatment of textile wastewater in a biological aerated filter , 2002 .

[11]  L. Wu,et al.  Exogenous addition of cellular extract N-acyl-homoserine-lactones accelerated the granulation of autotrophic nitrifying sludge , 2017 .

[12]  Aníbal R. Figueiras-Vidal,et al.  On building ensembles of stacked denoising auto-encoding classifiers and their further improvement , 2018, Inf. Fusion.

[13]  Zhiwei Wang,et al.  Modeling of multimode anaerobic/anoxic/aerobic wastewater treatment process at low temperature for process optimization , 2015 .

[14]  Riccardo Poli,et al.  Particle swarm optimization , 1995, Swarm Intelligence.

[15]  Hang-sik Shin,et al.  Sequential modeling of fecal coliform removals in a full-scale activated-sludge wastewater treatment plant using an evolutionary process model induction system. , 2009, Water research.

[16]  Xin-She Yang,et al.  Quaternion-based Deep Belief Networks fine-tuning , 2017, Appl. Soft Comput..

[17]  Ying Peng,et al.  A prognosis method using age-dependent hidden semi-Markov model for equipment health prediction , 2011 .

[18]  Cong Wang,et al.  Construction of hierarchical diagnosis network based on deep learning and its application in the fault pattern recognition of rolling element bearings , 2016 .

[19]  Ting Liu,et al.  Recent advances in convolutional neural networks , 2015, Pattern Recognit..

[20]  Yangwu Chen,et al.  Mixed nitrifying bacteria culture under different temperature dropping strategies: Nitrification performance, activity, and community. , 2018, Chemosphere.

[21]  Jianzheng Li,et al.  Modeling the dynamic volatile fatty acids profiles with pH and hydraulic retention time in an anaerobic baffled reactor during the startup period. , 2016, Bioresource technology.

[22]  Feng Gao,et al.  Modeling and simulation of a biological process for treating different COD:N ratio wastewater using an extended ASM1 model , 2018 .

[23]  Jose A. Egea,et al.  Developments in microbial fuel cell modeling , 2015 .

[24]  Pascal Vincent,et al.  Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion , 2010, J. Mach. Learn. Res..

[25]  Joaquim Comas,et al.  Comparison of a deterministic and a data driven model to describe MBR fouling , 2015 .

[26]  Silvia Curteanu,et al.  Modeling of electrolysis process in wastewater treatment using different types of neural networks , 2011 .

[27]  Adewale Giwa,et al.  Experimental investigation and artificial neural networks ANNs modeling of electrically-enhanced membrane bioreactor for wastewater treatment , 2016 .

[28]  Zhiqiang Ge,et al.  Review on data-driven modeling and monitoring for plant-wide industrial processes , 2017 .

[29]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[30]  Patrick P. K. Chan,et al.  Sensitivity based robust learning for stacked autoencoder against evasion attack , 2017, Neurocomputing.

[31]  Taghi M. Khoshgoftaar,et al.  Deep learning applications and challenges in big data analytics , 2015, Journal of Big Data.

[32]  Ingmar Nopens,et al.  Simulations of reactive settling of activated sludge with a reduced biokinetic model , 2016, Comput. Chem. Eng..

[33]  Krist V. Gernaey,et al.  Reaction invariant-based reduction of the activated sludge model ASM1 for batch applications , 2016 .

[34]  Fernando Fdz-Polanco,et al.  Influence of the suspended and attached biomass on the nitrification in a two submerged biofilters in series system , 2000 .

[35]  J. González-López,et al.  Membrane bioreactor and hybrid moving bed biofilm reactor-membrane bioreactor for the treatment of variable salinity wastewater: influence of biomass concentration and hydraulic retention time. , 2018 .

[36]  E. Barca,et al.  Gross parameters prediction of a granular-attached biomass reactor by means of multi-objective genetic-designed artificial neural networks: touristic pressure management case , 2016, Environmental Science and Pollution Research.

[37]  Giancarlo Mauri,et al.  Fuzzy Self-Tuning PSO: A settings-free algorithm for global optimization , 2017, Swarm Evol. Comput..

[38]  Zhiguo Yuan,et al.  Modelling the long-term effect of wastewater compositions on maximum sulfide and methane production rates of sewer biofilm. , 2018, Water research.

[39]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[40]  Peng Hao,et al.  Transfer learning using computational intelligence: A survey , 2015, Knowl. Based Syst..

[41]  Mehmet Cakmakci,et al.  A review on anaerobic biofilm reactors for the treatment of dairy industry wastewater , 2015 .

[42]  N. Hilal,et al.  Artificial neural network simulation of combined humic substance coagulation and membrane filtration , 2008 .

[43]  Baikun Li,et al.  Long term effect of alkali types on waste activated sludge hydrolytic acidification and microbial community at low temperature. , 2016, Bioresource technology.

[44]  Ma Yanjun,et al.  Accelerated startup of moving bed biofilm process with novel electrophilic suspended biofilm carriers , 2017 .

[45]  A. S. Ciggin,et al.  A simple kinetic modeling approach for aerobic stabilization of real waste activated sludge , 2016 .

[46]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[47]  Haidong Shao,et al.  Rolling bearing fault detection using continuous deep belief network with locally linear embedding , 2018, Comput. Ind..

[48]  Yoshua Bengio,et al.  Extracting and composing robust features with denoising autoencoders , 2008, ICML '08.