Performance evaluation of the machine learning approaches in modeling of CO2 equilibrium absorption in Piperazine aqueous solution

Abstract Accurate knowledge of equilibrium solubility of CO2 in solvents is crucial for optimal design and operation of the absorption-based CO2 capture systems. This study aims at evaluation of the performance of four machine learning approaches including artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS), least squares support vector machine (LSSVM), and adaptive boosting in conjunction with the classification and regression tree (AdaBoost-CART) in calculating the CO2 equilibrium absorption in Piperazine (PZ) aqueous solution. To this end, an extensive databank covering wide ranges of temperature, pressure, and solvent concentration was collected from literature. With an overall absolute relative deviation in percent (AARD%) equal to 18.69, 15.99, and 16.23, the results from the error analysis reveal that none of the ANN, ANFIS, and LSSVM methods are capable to reliably model the equilibrium system of CO2 + water + PZ. On the other hand, the AdaBoost-CART model shows much higher accuracy and robustness in representing the equilibrium solubility of CO2 in PZ solution. The AdaBoost-CART model reproduces the experimental targets with an AARD% = 0.93 and a R2 = 0.9934 which demonstrates excellent agreement between the outputs and corresponding experimental values.

[1]  Meng-Hui Li,et al.  Equilibrium solubility of carbon dioxide in the amine solvent system of (triethanolamine + piperazine + water) , 2010 .

[2]  Ali Abbas,et al.  A novel modeling approach to optimize oxygen–steam ratios in coal gasification process , 2015 .

[3]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[4]  A. Mohammadi,et al.  Rigorous modeling of CO2 equilibrium absorption in MEA, DEA, and TEA aqueous solutions , 2014 .

[5]  A. Ghaemi,et al.  Experimental investigation of CO2 removal using Piperazine solution in a stirrer bubble column , 2017 .

[6]  Johan A. K. Suykens,et al.  Coupled Simulated Annealing , 2010, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[7]  I. Sreedhar,et al.  Carbon capture by absorption – Path covered and ahead , 2017 .

[8]  Jozsef Gaspar,et al.  Practical enhancement factor model based on GM for multiple parallel reactions: Piperazine (PZ) CO2 capture , 2017 .

[9]  A. A. Khan,et al.  Experimental investigation on efficient carbon dioxide capture using piperazine (PZ) activated aqueous methyldiethanolamine (MDEA) solution in a packed column , 2017 .

[10]  M. Fang,et al.  Process Simulations of CO2 Desorption in the Interaction between the Novel Direct Steam Stripping Process and Solvents , 2017 .

[11]  A. Bahadori,et al.  Prediction of solubility of carbon dioxide in different polymers using support vector machine algorithm , 2015 .

[12]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[13]  Alireza Bahadori,et al.  Novel methods predict equilibrium vapor methanol content during gas hydrate inhibition , 2013 .

[14]  Vladimir Vapnik,et al.  An overview of statistical learning theory , 1999, IEEE Trans. Neural Networks.

[15]  Fei Liu,et al.  Reaction kinetics of carbon dioxide absorption in aqueous solutions of piperazine, N-(2-aminoethyl) ethanolamine and their blends , 2017 .

[16]  Harris Drucker,et al.  Improving Regressors using Boosting Techniques , 1997, ICML.

[17]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

[18]  Domingo Cillero,et al.  Experimental studies of CO2 capture by a hybrid catalyst/adsorbent system applicable to IGCC processes , 2015 .

[19]  Bin Zhao,et al.  Enhancing the energetic efficiency of MDEA/PZ-based CO2 capture technology for a 650MW power plant: Process improvement , 2017 .

[20]  A. Bahadori,et al.  Estimation of triethylene glycol (TEG) purity in natural gas dehydration units using fuzzy neural network , 2014 .

[21]  Geert Versteeg,et al.  Solubility of carbon dioxide in aqueous piperazine solutions , 2005 .

[22]  Zongguo Wen,et al.  Analysis of potential energy conservation and CO2 emissions reduction in China's non-ferrous metals industry from a technology perspective , 2014 .

[23]  Gary T. Rochelle,et al.  Amine volatility in CO2 capture , 2010 .

[24]  G. Rochelle,et al.  Thermal degradation of novel piperazine-based amine blends for CO2 capture , 2016 .

[25]  Jun Zhang,et al.  CO2 capture by adsorption: Materials and process development , 2007 .

[27]  Ebrahim H. Mamdani,et al.  An Experiment in Linguistic Synthesis with a Fuzzy Logic Controller , 1999, Int. J. Hum. Comput. Stud..

[28]  Farhad Gharagheizi,et al.  Intelligent model for prediction of CO2 – Reservoir oil minimum miscibility pressure , 2013 .

[29]  Phase equilibrium modeling of gas hydrate systems for CO2 capture , 2012 .

[30]  Yiyu Lu,et al.  Precombustion CO2 capture using a hybrid process of adsorption and gas hydrate formation , 2016 .

[31]  P. Keshavarz,et al.  Experimental and Theoretical Study of CO2 Absorption with Piperazine-Promoted Potassium Carbonate Solution in Hollow Fiber Membrane Contactors , 2017 .

[32]  Mahmood Amani,et al.  Implementation of SVM framework to estimate PVT properties of reservoir oil , 2013 .

[33]  G. Rochelle,et al.  Piperazine/4-hydroxy-1-methylpiperidine for CO2 capture , 2017 .

[34]  A. Mohammadi,et al.  CO2 capture with aqueous solution of sodium glycinate: Modeling using an ensemble method , 2017 .

[35]  Meihong Wang,et al.  Modelling and process analysis of post-combustion carbon capture with the blend of 2-amino-2-methyl-1-propanol and piperazine , 2017 .

[36]  G. Maurer,et al.  Solubility of CO2 in (H2O+piperazine) and in (H2O+MDEA+piperazine) , 2003 .

[37]  A. K. Datta,et al.  Optimization of membrane unit for removing carbon dioxide from natural gas , 2006 .

[38]  Yoram Singer,et al.  Improved Boosting Algorithms Using Confidence-rated Predictions , 1998, COLT' 98.

[39]  Hallvard F. Svendsen,et al.  Solubility of Carbon Dioxide in 30 mass % Monoethanolamine and 50 mass % Methyldiethanolamine Solutions , 2005 .

[40]  Pascal Mougin,et al.  High throughput screening of CO2 solubility in aqueous monoamine solutions. , 2011, Environmental science & technology.

[41]  Sung Hyun Kim,et al.  Correlation and Prediction of the Solubility of Carbon Dioxide in Aqueous Alkanolamine and Mixed Alkanolamine Solutions , 2002 .

[42]  K. K. Lau,et al.  Modelling of high pressure CO2 absorption using PZ+AMP blended solution in a packed absorption column , 2016 .

[43]  A. Mohammadi,et al.  Comparison of two soft computing approaches for predicting CO2 solubility in aqueous solution of piperazine , 2016 .

[44]  Farhad Gharagheizi,et al.  Toward an intelligent approach for determination of saturation pressure of crude oil , 2013 .

[45]  S. Shahhosseini,et al.  CO2 chemical absorption into aqueous solutions of piperazine: modeling of kinetics and mass transfer rate , 2015 .

[46]  Amir H. Mohammadi,et al.  Application of decision tree learning in modelling CO2 equilibrium absorption in ionic liquids , 2017 .

[47]  M. Ghiasi,et al.  Practical use of statistical learning theory for modeling freezing point depression of electrolyte solutions: LSSVM model , 2014 .

[48]  William H. Press,et al.  The Art of Scientific Computing Second Edition , 1998 .

[49]  A. Bahadori,et al.  Prediction of methanol loss in liquid hydrocarbon phase during natural gas hydrate inhibition using rigorous models , 2015 .

[50]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[51]  J. Ross Quinlan,et al.  Induction of Decision Trees , 1986, Machine Learning.

[52]  Amir H. Mohammadi,et al.  Application of ANFIS soft computing technique in modeling the CO2 capture with MEA, DEA, and TEA aqueous solutions , 2016 .

[53]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[54]  Alireza Bahadori,et al.  Prediction of CO2–oil molecular diffusion using adaptive neuro-fuzzy inference system and particle swarm optimization technique , 2016 .

[55]  H. Modarress,et al.  CO2 absorption into aqueous solutions of monoethanolamine, piperazine and their blends: Quantum mechanics and molecular dynamics studies , 2017 .

[56]  G. Rochelle,et al.  Modeling of absorber pilot plant performance for CO2 capture with aqueous piperazine , 2017 .

[57]  Mohammad R.M. Abu-Zahra,et al.  Evaluation of amine-blend solvent systems for CO2 post-combustion capture applications☆ , 2013 .

[58]  Jozsef Gaspar,et al.  Multivariable Optimization of the Piperazine CO2 Post-Combustion Process , 2016 .

[59]  Eugeniusz Mokrzycki,et al.  CO2 emissions from Polish cement industry , 2010 .

[60]  Jong-Hyeon Jung,et al.  Removal characteristics of CO2 using aqueous MEA/AMP solutions in the absorption and regeneration process. , 2009, Journal of environmental sciences.

[61]  R. Idem,et al.  Screening tests of aqueous alkanolamine solutions based on primary, secondary, and tertiary structure for blended aqueous amine solution selection in post combustion CO2 capture , 2017 .

[62]  Amit Chakma,et al.  Effectiveness of membranes and hybrid membrane processes in comparison with absorption using amines for post-combustion CO2 capture , 2014 .

[63]  Michio Sugeno,et al.  Fuzzy identification of systems and its applications to modeling and control , 1985, IEEE Transactions on Systems, Man, and Cybernetics.

[64]  Rahul Anantharaman,et al.  Cost-optimal CO2 capture ratio for membrane-based capture from different CO2 sources , 2017 .

[65]  A. Mohammadi,et al.  Modeling of stability conditions of natural gas clathrate hydrates using least squares support vector machine approach , 2016 .

[66]  A. Mohammadi,et al.  Analyzing the experimental data of CO2 equilibrium absorption in the aqueous solution of DEA + MDEA with Random Forest and Leverage method , 2017 .

[67]  Alexander J. Smola,et al.  Support Vector Regression Machines , 1996, NIPS.

[68]  Eric F. May,et al.  The removal of CO2 and N2 from natural gas: A review of conventional and emerging process technologies , 2012 .

[69]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[70]  Paul A. Webley,et al.  Adsorption technology for CO2 separation and capture: a perspective , 2014, Adsorption.

[71]  I. Hatono,et al.  Fuzzy decision trees by fuzzy ID3 algorithm and its application to diagnosis systems , 1994, Proceedings of 1994 IEEE 3rd International Fuzzy Systems Conference.

[72]  Ahnaf Rashik Hassan,et al.  Computer-aided obstructive sleep apnea detection using normal inverse Gaussian parameters and adaptive boosting , 2016, Biomed. Signal Process. Control..

[73]  R. Bounaceur,et al.  Energy Penalty of a Single Stage Gas Permeation Process for CO2 Capture in Post-combustion: A Rigorous Parametric Analysis of Temperature, Humidity and Membrane Performances , 2017 .

[74]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machine Classifiers , 1999, Neural Processing Letters.

[75]  Amar Nath Samanta,et al.  Experimental and theoretical investigation of solubility of carbon dioxide in concentrated aqueous solution of 2-amino-2-methyl-1-propanol and piperazine , 2012 .

[76]  M. Michelsen,et al.  A Model for Estimating CO~2 Solubility in Aqueous Alkanolamines , 2005 .

[77]  M. A. Bustam,et al.  High pressure CO2 absorption from natural gas using piperazine promoted 2-amino-2-methyl-1-propanol in a packed absorption column , 2015 .

[78]  Maria C. Iliuta,et al.  CO2 Absorption in Aqueous Piperazine Solutions: Experimental Study and Modeling , 2011 .

[79]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[80]  Pailin M Muchan,et al.  Selection of components for formulation of amine blends for post combustion CO2 capture based on the side chain structure of primary, secondary and tertiary amines , 2017 .

[81]  G. Rochelle,et al.  Capacity and absorption rate of tertiary and hindered amines blended with piperazine for CO2 capture , 2016 .

[82]  Huiyong Kim,et al.  Energy analysis of an absorption-based CO2 capture process , 2017 .

[83]  Carl Tim Kelley,et al.  Iterative methods for optimization , 1999, Frontiers in applied mathematics.

[84]  Rached Ben-Mansour,et al.  Carbon capture by physical adsorption: Materials, experimental investigations and numerical modeling and simulations – A review , 2016 .

[85]  M. Kundu,et al.  Vapor–Liquid Equilibrium and Physicochemical Properties of Novel Aqueous Blends of (2-Diethylaminoethanol + Piperazine) for CO2 Appropriation , 2017 .

[86]  M. Tadé,et al.  CO 2 capture using piperazine-promoted, aqueous ammonia solution: Rate-based modelling and process simulation , 2017 .

[87]  Gary T. Rochelle,et al.  Absorption of carbon dioxide into aqueous piperazine: reaction kinetics, mass transfer and solubility , 2000 .