Evaluation of artificial neural network models for online monitoring of alkalinity in anaerobic co-digestion system

Abstract Compared to pH monitoring during the anaerobic digestion process, alkalinity as an indicator could provide earlier warning for instability of digestion process, which is very important for efficient operation of biogas digesters, especially for multiple feeding substances. However, the online monitoring of alkalinity is still unavailable until now. In this study, available online measured parameters such as pH, oxidation and reduction potential (ORP), and electrical conductivity were selected as inputs, and the soft sensor method based on artificial neural network (ANN) was applied for alkalinity modeling to develop an online monitoring strategy. The dataset was obtained from a 6 month continuously operating anaerobic co-digestion system of cow manure, corn straw, and fruit and vegetable waste, and splited randomly by cross-validation. The results show that the optimum ANN model for total alkalinity prediction is 3-2-1 structure based on back propagation-feedforward neural network. The constructed ANN model was proved to be reliable through the predictive accuracy analysis and sensitivity analysis. The coefficient of determination (R2) of 0.9948 was obtained. ORP is the most significant model factor with the highest sensitivity degree. The online alkalinity monitoring may effectively prevent the failure of anaerobic digestion process and improve the anaerobic digestion efficiency practically.

[1]  Wei Wang,et al.  Two-phase anaerobic digestion of municipal solid wastes enhanced by hydrothermal pretreatment: Viability, performance and microbial community evaluation , 2017 .

[2]  Mohsen Assadi,et al.  Experimental evaluation and ANN modeling of a recuperative micro gas turbine burning mixtures of natural gas and biogas , 2014 .

[3]  A. E. Greenberg,et al.  Standard methods for the examination of water and wastewater : supplement to the sixteenth edition , 1988 .

[4]  F. Lichti,et al.  Near-infrared spectroscopy (NIRS) for a real time monitoring of the biogas process. , 2018, Bioresource technology.

[5]  S. Khanal,et al.  Biological strategies for enhanced hydrolysis of lignocellulosic biomass during anaerobic digestion: Current status and future perspectives. , 2017, Bioresource technology.

[6]  Bryan A. Tolson,et al.  A New Formulation for Feedforward Neural Networks , 2011, IEEE Transactions on Neural Networks.

[7]  L. Rao,et al.  High alcohol production by solid substrate fermentation from starchy substrates using thermotolerant Saccharomyces cerevisiae , 1999 .

[8]  Holger R. Maier,et al.  Protocol for developing ANN models and its application to the assessment of the quality of the ANN model development process in drinking water quality modelling , 2014, Environ. Model. Softw..

[9]  B Mattiasson,et al.  Evaluation of new methods for the monitoring of alkalinity, dissolved hydrogen and the microbial community in anaerobic digestion. , 2001, Water research.

[10]  K. P. Sudheer,et al.  Methods used for the development of neural networks for the prediction of water resource variables in river systems: Current status and future directions , 2010, Environ. Model. Softw..

[11]  Víctor González-Álvarez,et al.  Anaerobic treatment of Tequila vinasses in a CSTR-type digester  , 2010, Biodegradation.

[12]  J. Bouvier.  On-line titrimetric sensor for the control of VFA and/or alkalinity in anaerobic digestion processes treating industrial vinas , 2002 .

[13]  S. V. Channapattana,et al.  Optimisation of operating parameters of DI-CI engine fueled with second generation Bio-fuel and development of ANN based prediction model , 2017 .

[14]  M. J. Taylor,et al.  Establishing impacts of the inputs in a feedforward neural network , 1998, Neural Computing & Applications.

[15]  Anastasios Argyropoulos,et al.  Soft sensor development and process control of anaerobic digestion , 2013 .

[16]  Araceli Sanchis,et al.  Time series forecasting using a weighted cross-validation evolutionary artificial neural network ensemble , 2013, Neurocomputing.

[17]  M. F. Colmenarejo,et al.  Performance evaluation of an anaerobic fluidized bed reactor with natural zeolite as support material when treating high-strength distillery wastewater , 2008 .

[18]  V. Alcaraz-González,et al.  Regulation of Volatile Fatty Acids and Total Alkalinity in Anaerobic Digesters , 2008 .

[19]  Bo Mattiasson,et al.  An automated spectrophotometric system for monitoring buffer capacity in anaerobic digestion processes. , 2004, Water research.

[20]  Gurjeet Singh.  Construction of efficient sampling strategies in survey sampling , 2011 .

[21]  R. Dinsdale,et al.  An improved titration model reducing over estimation of total volatile fatty acids in anaerobic digestion of energy crop, animal slurry and food waste. , 2014, Water research.

[22]  M. S. Rao,et al.  Bioenergy conversion studies of organic fraction of MSW: kinetic studies and gas yield--organic loading relationships for process optimisation. , 2004, Bioresource technology.

[23]  S. R. Jenkins,et al.  Measuring anaerobic sludge digestion and growth by a simple alkalimetric titration , 1983 .

[24]  Qin Cao,et al.  Instability mechanisms and early warning indicators for mesophilic anaerobic digestion of vegetable waste. , 2017, Bioresource technology.

[25]  Xiaofen Wang,et al.  Effect of dairy manure to switchgrass co-digestion ratio on methane production and the bacterial community in batch anaerobic digestion , 2015 .

[26]  J. C. Converse,et al.  Improved alkalimetric monitoring for anaerobic digestion of high-strength wastes , 1986 .

[27]  Vittorio Cesarotti,et al.  Energy consumption control automation using Artificial Neural Networks and adaptive algorithms: Proposal of a new methodology and case study , 2016 .

[28]  É. Latrille,et al.  Online estimation of VFA, alkalinity and bicarbonate concentrations by electrical conductivity measurement during anaerobic fermentation. , 2012, Water science and technology : a journal of the International Association on Water Pollution Research.

[29]  P. Hobbs,et al.  Evaluation of near infrared spectroscopy and software sensor methods for determination of total alkalinity in anaerobic digesters. , 2011, Bioresource technology.

[30]  G. Crespo,et al.  Direct alkalinity detection with ion-selective chronopotentiometry. , 2014, Analytical chemistry.

[31]  Molof Ah,et al.  Electrode potential monitoring and electrolytic control in anaerobic digestion. , 1973, Journal - Water Pollution Control Federation.

[32]  Jincan Chen,et al.  A self‐adaptive genetic algorithm‐artificial neural network algorithm with leave‐one‐out cross validation for descriptor selection in QSAR study , 2010, J. Comput. Chem..

[33]  B Mattiasson,et al.  A simple spectrophotometric method based on pH‐indicators for monitoring partial and total alkalinity in anaerobic processes , 2003, Environmental technology.

[34]  Juan M. Lema,et al.  Pilot-Scale Validation of a New Sensor for On-Line Analysis of Volatile Fatty Acids and Alkalinity in Anaerobic Wastewater Treatment Plants , 2009 .