Artificial neural network for prediction of SO2 removal and volumetric mass transfer coefficient in spray tower

Abstract Sulfur dioxide has serious effects on the environment and on humans, and can cause bad odors and severe respiratory diseases. One of the most common methods for controlling SO2 is the process of desulfurization using a spray tower. Despite this process being able to eliminate much of the SO2, two of the most important parameters that need to be evaluated are the removal efficiency and the volumetric coefficient of mass transfer of the gas phase (kga). Due to the large number of parameters to be evaluated and the process complexity, there are difficulties in the proposal of mathematical models to predict those parameters over a wide range of the operation conditions of a spray tower. To overcome these drawbacks artificial intelligence methods can be an alternative. The aim of this study was to obtain an artificial neural network (ANN) to predict the removal efficiency and the kga of the SO2 removal in a spray tower. The input parameters considered were the spray nozzle orifice diameter, number of nozzles, liquid flow rate, gas flow rate and SO2 inlet concentration. Four different training algorithms, different combinations of transfer functions, and several networks structures were tested in search of the best ANN. The results showed that the choosing of the best model from the training and validation steps did not generate reliable results. The best structure was defined by analyzing the results of a simulation step, which used independent data. The best model was obtained with the structure 5-9-2, trained using the Levenberg-Marquardt algorithm with Bayesian Regularization and having the softmax and linear transfer functions in the hidden and output layers, respectively. This ANN presented accurate results and predicted the behavior of experimental data as expected. The best network presented an average error of 8.44% for the outlet SO2 concentration and 4.53% for the kga, which was lower than those obtained with the usual empirical correlations. This work showed that the use of neural networks is promising in the prediction of important variables in the processes of removal of air pollutants in spray towers.

[1]  Martin Fodslette Møller,et al.  A scaled conjugate gradient algorithm for fast supervised learning , 1993, Neural Networks.

[2]  N. Nevers,et al.  Air Pollution Control Engineering , 1994 .

[3]  Nianping Li,et al.  Investigation on the thermal performance of a novel spray tower with upward spraying and downward gas flow , 2018, Applied Energy.

[4]  Martin A. Riedmiller,et al.  A direct adaptive method for faster backpropagation learning: the RPROP algorithm , 1993, IEEE International Conference on Neural Networks.

[5]  R. Maciel Filho,et al.  Artificial neural networks for prediction of recurrent venous thromboembolism , 2020, Int. J. Medical Informatics.

[6]  Jianfeng Chen,et al.  Absorption of SO2 with calcium-based solution in a rotating packed bed , 2019, Separation and Purification Technology.

[7]  Md. Raisuddin Khan,et al.  Identification and predictive control of spray tower system using artificial neural network and differential evolution algorithm , 2015, 2015 10th Asian Control Conference (ASCC).

[8]  T. Mahmud,et al.  Enhancement of Mass Transfer in a Spray Tower Using Swirling Gas Flow , 2006 .

[9]  G. Bianchi,et al.  A Bayesian neural network methodology to predict the liquid phase diffusion coefficient , 2020 .

[10]  A. Erto,et al.  Seawater Desulphurization of Simulated Flue Gas in Spray and Packed Columns: an Experimental and Modelling Comparison , 2018 .

[11]  Y. Kang,et al.  Estimation of finish cooling temperature by artificial neural networks of backpropagation during accelerated control cooling process , 2018, International Journal of Heat and Mass Transfer.

[12]  Isa N Cruz,et al.  Estimation of vaporization properties of pure substances using artificial neural networks , 2020 .

[13]  W. A. Bizzo,et al.  Mass Transfer and Liquid‐Film Formation in a Spray Tower for SO2 Removal in Sodium Hydroxide Solution , 2016 .

[14]  M. N. Biswas,et al.  CO2 capture in a spray column using a critical flow atomizer , 2012 .

[15]  Jianfeng Chen,et al.  Mass-Transfer Performance for CO2 Absorption by 2-(2-Aminoethylamino)ethanol Solution in a Rotating Packed Bed , 2017 .

[16]  V. Cortés,et al.  Pilot-Plant Technical Assessment of Wet Flue Gas Desulfurization Using Limestone. , 2006 .

[17]  M. Hatamipour,et al.  SO2 removal by seawater in a spray tower: Experimental study and mathematical modeling , 2016 .

[18]  Min-Young Yi,et al.  Performance Characteristics of CO2 Capture Using Aqueous Ammonia in a Single-Nozzle Spray Tower , 2013 .

[19]  Chakravarthy Balaji,et al.  A new ANN driven MCMC method for multi-parameter estimation in two-dimensional conduction with heat generation , 2010 .

[20]  S. Ebrahim,et al.  Prediction of the minimum film boiling temperature using artificial neural network , 2020 .

[21]  M. Jafari,et al.  Experimental optimization of a spray tower for ammonia removal , 2018, Atmospheric Pollution Research.

[22]  Y. Islamoglu,et al.  Heat transfer analysis using ANNs with experimental data for air flowing in corrugated channels , 2004 .

[23]  Teerawat Sema,et al.  Predictions of equilibrium solubility and mass transfer coefficient for CO2 absorption into aqueous solutions of 4-diethylamino-2-butanol using artificial neural networks , 2018 .

[24]  Kaan Yetilmezsoy,et al.  Stochastic modeling approaches based on neural network and linear–nonlinear regression techniques for the determination of single droplet collection efficiency of countercurrent spray towers , 2007 .

[25]  Waldir Antonio Bizzo,et al.  Experimental study of the SO2 removal efficiency and volumetric mass transfer coefficients in a pilot-scale multi-nozzle spray tower , 2013 .

[26]  Gongnan Xie,et al.  Performance predictions of laminar and turbulent heat transfer and fluid flow of heat exchangers having large tube-diameter and large tube-row by artificial neural networks , 2009 .

[27]  Chirag R. Kharangate,et al.  An artificial neural network model to predict mini/micro-channels saturated flow boiling heat transfer coefficient based on universal consolidated data , 2020, International Journal of Heat and Mass Transfer.

[28]  Paisarn Naphon,et al.  Artificial neural network analysis the pulsating Nusselt number and friction factor of TiO2/water nanofluids in the spirally coiled tube with magnetic field , 2018 .

[29]  Kaiyun Fu,et al.  Experimental study on mass transfer and prediction using artificial neural network for CO2 absorption into aqueous DETA , 2013 .

[30]  Liang-liang Zhang,et al.  Simultaneous Absorption of H2S and CO2 into the MDEA + PZ Aqueous Solution in a Rotating Packed Bed , 2020, Industrial & Engineering Chemistry Research.

[31]  L. Shao,et al.  Artificial neural network modeling on the prediction of mass transfer coefficient for ozone absorption in RPB , 2019 .

[32]  Anas A. Rahman,et al.  Prediction of oscillatory heat transfer coefficient for a thermoacoustic heat exchanger through artificial neural network technique , 2018, International Journal of Heat and Mass Transfer.

[33]  M. N. Biswas,et al.  Modeling of SO(2) scrubbing in spray towers. , 2007, The Science of the total environment.

[34]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[35]  Yishan Guo,et al.  Modeling and optimization of wet flue gas desulfurization system based on a hybrid modeling method , 2019, Journal of the Air & Waste Management Association.

[36]  C. Faúndez,et al.  Misleading results on the use of artificial neural networks for correlating and predicting properties of fluids. A case on the solubility of refrigerant R-32 in ionic liquids , 2020 .

[37]  Guangxue Zhang,et al.  Absorption of Sulfur Dioxide with Sodium Hydroxide Solution in Spray Columns , 2015 .

[38]  A. Couvert,et al.  Experimental study of mass transfer and H2S removal efficiency in a spray tower , 2008 .

[39]  David J. C. MacKay,et al.  Bayesian Interpolation , 1992, Neural Computation.

[41]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[42]  T. D. Martins,et al.  A neural network correlation for molar density and specific heat of water: Predictions at pressures up to 100 MPa , 2020 .

[43]  Zhen-hua Liu,et al.  Modeling and experimental studies of ammonia absorption in a spray tower , 2015, Korean Journal of Chemical Engineering.