Advertisement

Environmental Science and Pollution Research

, Volume 21, Issue 22, pp 12856–12867 | Cite as

Neural networks and differential evolution algorithm applied for modelling the depollution process of some gaseous streams

  • Silvia Curteanu
  • Gabriel Dan Suditu
  • Adela Marina Buburuzan
  • Elena Niculina DragoiEmail author
Research Article

Abstract

The depollution of some gaseous streams containing n-hexane is studied by adsorption in a fixed bed column, under dynamic conditions, using granular activated carbon and two types of non-functionalized hypercross-linked polymeric resins. In order to model the process, a new neuro-evolutionary approach is proposed. It is a combination of a modified differential evolution (DE) with neural networks (NNs) and two local search algorithms, the global and local optimizers, working together to determine the optimal NN model. The main elements that characterize the applied variant of DE consist in using an opposition-based learning initialization, a simple self-adaptive procedure for the control parameters, and a modified mutation principle based on the fitness function as a criterion for reorganization. The results obtained prove that the proposed algorithm is able to determine a good model of the considered process, its performance being better than those of an available phenomenological model.

Keywords

Differential evolution Neural network Local search Backpropagation VOC adsorption Hypercross-linked polymeric adsorbents 

Notes

Acknowledgments

This work was supported by the “Partnership in priority areas—PN-II” program, financed by ANCS, CNDI-UEFISCDI, project PN-II-PT-PCCA-2011-3.2-0732, No. 23/2012.

References

  1. Ahmad AA, Hameed BH (2010) Fixed-bed adsorption of reactive azo dye onto granular activated carbon prepared from waste. J Hazard Mater 175:298–303CrossRefGoogle Scholar
  2. Brest, J. (2009). Constrained real-parameter optimization with e-self-adaptive differential evolution. In E. Mezura-Montes (Ed.), Constraint-handling in evolutionary optimization. Studies in Computational Intelligence Springer Berlin/Heidelberg, pp. 73-93.Google Scholar
  3. Buburuzan AM, Catrinescu C, Macoveanu M (2009) Adsorption of n-hexane vapors onto non-functionalised hypercrosslinked polymers (hypersol-macronettm) and activated carbon: thermodynamic and kinetic studies. Environ Eng Manag J 8:259–265Google Scholar
  4. Buburuzan AM, Catrinescu C, Macoveanu M (2010) Comparative study of the adsorption-desorption cycles of hexane over hypercrosslinked polymeric adsorbents and activated carbon. Environ Eng Manag J 9:125–132Google Scholar
  5. Caicedo Torres W, Quintana M, Pinzon H (2013) Differential diagnosis of hemorrhagic fevers using ARTMAP and artificial immune system. Int J Artif Intell 11:150–169Google Scholar
  6. Chandra A, Yao X (2006) Ensemble learning using multi-objective evolutionary algorithms. J Math Model Algoritm 5:417–445CrossRefGoogle Scholar
  7. Curteanu S, Cartwright H (2012) Neural networks applied in chemistry. I Determination of the optimal topology of multilayer perceptron neural networks J Chemom 25:527–549Google Scholar
  8. Das S, Suganthan PN (2011) Differential evolution: a survey of the state-of-the-art. IEEE Trans Evol Comput 15:4–31CrossRefGoogle Scholar
  9. Dragoi EN, Curteanu S, Leon F, Galaction AI, Cascaval D (2011) Modeling of oxygen mass transfer in the presence of oxygen-vectors using neural networks developed by differential evolution algorithm. Eng Appl Artif Intell 24:1214–1226CrossRefGoogle Scholar
  10. Dragoi EN, Curteanu S, Lisa C (2012a) A neuro-evolutive technique applied for predicting the liquid crystalline property of some organic compounds. Eng Optim 44:1261–1277CrossRefGoogle Scholar
  11. Dragoi EN, Curteanu S, Fissore D (2012b) Freeze-drying modeling and monitoring using a new neuro-evolutive technique. Chem Eng Sci 72:195–204CrossRefGoogle Scholar
  12. Dragoi EN, Curteanu S, Galaction AI, Cascaval D (2013) Optimization methodology based on neural networks and self-adaptive differential evolution algorithm applied to an aerobic fermentation process. Appl Soft Comput 13:222–238CrossRefGoogle Scholar
  13. Feoktistov, V. (2006). Differential evolution: in search of solutions. SpringerGoogle Scholar
  14. Floreano D, Durr P, Mattiussi C (2008) Neuroevolution: from architectures to learning. Evol Intell 1:47–62CrossRefGoogle Scholar
  15. Furtuna R, Curteanu S, Leon F (2012) Multi-objective optimization of a stacked neural network using an evolutionary hyper-heuristic. Appl Soft Comput 12:133–144CrossRefGoogle Scholar
  16. Gupta VK, Verma N (2002) Removal of volatile organic compounds by cryogenic condensation followed by adsorption. Chem Eng Sci 57:2679–2696CrossRefGoogle Scholar
  17. Halteta Buburuzan MB, Catrinescu C, Macoveanu M (2009) Adsorption of n-hexane vapors onto non-functionalized hypercrosslinked polymers (hypersol-macronettm) and activated carbon: equilibrium studies. Environ Eng Manag J 8:173–181Google Scholar
  18. Han L, Shi X, Wu W, Kirk FL, Luo J, Wang L et al (2005) Nanoparticle-structured sensing array materials and pattern recognition for VOC detection. Sens Actuators B: Chem 106:431–441CrossRefGoogle Scholar
  19. Hernandez RP, Alvarez-Gallegos J, Reyes J (1998) Simple recurrent neural network: a neural network structure for control systems. Neurocomput 3:277–289CrossRefGoogle Scholar
  20. Hu Q, Li JJ, Hao ZP, Li LD, Qiao SZ (2009) Dynamic adsorption of volatile organic compounds on organofunctionalized SBA-15 materials. Chem Eng J 149:281–288CrossRefGoogle Scholar
  21. Khan FI, Ghoshal A (2000) Removal of volatile organic compounds from polluted air. J Loss Prev Process Ind 13(6):527–545CrossRefGoogle Scholar
  22. Kim KJ, Kang CS, You YJ, Chung MC, Woo MW, Jeong WJ et al (2006) Adsorption-desorption characteristics of VOCs over impregnated activated carbons. Catal Today 111:223–228CrossRefGoogle Scholar
  23. Leeghim H, Seo IH, Bang H (2008) Adaptive nonlinear control using input normalized neural networks. J Mech Sci Technol 22:1073–1083CrossRefGoogle Scholar
  24. Lillo-Rodenas MA, Fletcher AJ, Thomas KM, Cazorla-Amoris D, Linares-Solano A (2006) Competitive adsorption of a benzene-toluene mixture on activated carbons at low concentration. Carbon 44:1455–1463CrossRefGoogle Scholar
  25. Llanos J, Rodrigo MA, Canizares P, Furtuna RP, Curteanu S (2013) Neuro-evolutionary modelling of the electrodeposition stage of a polymer-supported ultrafiltration-electrodeposition process for the recovery of heavy metals. Environ Model Softw 42:133–142CrossRefGoogle Scholar
  26. Matros YS, Noskov AS, Chumachenko VA, Goldman OV (1988) Theory and application of unsteady catalytic detoxication of effluent gases from sulfur dioxide, nitrogen oxides and organic compounds. Chem Eng Sci 43:2061–2066CrossRefGoogle Scholar
  27. Matthies M, Giupponi C, Ostendorf B (2007) Environmental decision support systems: current issues, methods and tools. Environ Model Softw 22:123–127CrossRefGoogle Scholar
  28. Neri F, Tirronen V (2010) Recent advances in differential evolution: a survey and experimental analysis. Artif Intell Rev 33:61–106CrossRefGoogle Scholar
  29. Odabasi M, Ongan O, Cetin E (2005) Quantitative analysis of volatile organic compounds (VOCs) in atmospheric particles. Atmospheric Environ 39:3763–3770CrossRefGoogle Scholar
  30. Pant M, Thangaraj R, Abraham A, Grosan C, Differential Evolution with Laplace mutation operator (2009) Proceedings of the Eleventh Conference on Congress on Evolutionary Computation, Trondheim. IEEE Press, Norway, pp 2841–2849Google Scholar
  31. Patan K, Approximation Abilities of Locally Recurrent Networks (2008) Artificial neural networks for the modelling and fault diagnosis of technical processes. Lecture notes in control and information sciences. Springer Berlin, Heidelberg, pp 65–75CrossRefGoogle Scholar
  32. Peng L, Wang Y (2010) Differential evolution using uniform-quasi-opposition for initializing the population. Inf Technol J 9:1629–1634CrossRefGoogle Scholar
  33. Pirdashti M, Curteanu S, Kamangar MH, Hassim M, Amid M (2013) Artificial neural networks: applications in chemical engineering. Rev Chem Eng 29:205–239CrossRefGoogle Scholar
  34. Precup RE, Tomescu ML, Preitl S (2007) Lorenz system stabilization using fuzzy controllers. Int J Comput Commun Control 2:279–287Google Scholar
  35. Shim WG, Lee JW, Moon H (2006) Adsorption equilibrium and column dynamics of VOCs on MCM-48 depending on pelletizing pressure. MicroporousMesoporous Mater 88:112–125CrossRefGoogle Scholar
  36. Silvestre-Albero A, Ramos-Fernandez JM, Martinez-Escandell M, Seplveda-Escribano A, Silvestre-Albero J, Rodriguez-Reinoso F (2010) High saturation capacity of activated carbons prepared from mesophase pitch in the removal of volatile organic compounds. Carbon 48:548–556CrossRefGoogle Scholar
  37. Srivastava AK (2003) Detection of volatile organic compounds (VOCs) using SnO2 gas-sensor array and artificial neural network. Sensors Actuators B Chem 96:24–37CrossRefGoogle Scholar
  38. Storn R, Differential Evolution Research - Trends and Open Questions. In U. Chakraborty (2008) Advances in differential evolution. Studies in computational intelligence. Springer Berlin, Heidelberg, pp 1–31Google Scholar
  39. Subudhi B, Jena D (2009) An improved differential evolution trained neural network scheme for nonlinear system identification. Int J Autom Comput 6:137–144CrossRefGoogle Scholar
  40. Tchoupo GN, Guiseppi-Elie A (2005) On pattern recognition dependency of desorption heat, activation energy, and temperature of polymer-based VOC sensors for the electronic NOSE. Sensors Actuators B Chem 110:81–88CrossRefGoogle Scholar
  41. Tizhoosh HR (2005) Opposition-based learning: a new scheme for machine intelligence. In: In: International Conference on Computational Intelligence for Modeling, Control and International Conference on Intelligent Agents, Web technologies and Internet Commerce. 28-30 Nov 2005., pp 695–701Google Scholar
  42. Vassileiou A, Maris F, Kitikidou K, Iliadis L (2012) Artificial neural networks for improved predictions in flow estimation. Int J Artif Intell 9:186–201Google Scholar
  43. Xin Y (1999) Evolving artificial neural networks. Proc IEEE 87:1423–1447CrossRefGoogle Scholar
  44. Yoon YH, Nelson JH (1984) Application of gas adsorption kinetics. I. A theoretical model for respirator cartridge service life. Am Ind Hyg Assoc J 45:509–516CrossRefGoogle Scholar
  45. Zarth, A., & Ludermir, T. B. (2009). Optimization of neural networks weights and architecture: a multimodal methodology. In: Ninth International Conference on Intelligent Systems Design and Applications (ISDA’09) pp. 209-214.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  • Silvia Curteanu
    • 1
  • Gabriel Dan Suditu
    • 1
  • Adela Marina Buburuzan
    • 1
  • Elena Niculina Dragoi
    • 1
    Email author
  1. 1.Faculty of Chemical Engineering and Environmental Protection“Gheorghe Asachi” Technical University of IasiIasiRomania

Personalised recommendations