Advertisement

Heat and Mass Transfer

, Volume 46, Issue 4, pp 431–436 | Cite as

Artificial neural network modeling of fixed bed biosorption using radial basis approach

  • Dipendu SahaEmail author
  • Avijit Bhowal
  • Siddhartha Datta
Original

Abstract

In modern day scenario, biosorption is a cost effective separation technology for the removal of various pollutants from wastewater and waste streams from various process industries. The difficulties associated in rigorous mathematical modeling of a fixed bed bio-adsorbing systems due to the complexities of the process often makes the development of pure black-box artificial neural network (ANN) models particularly useful in this field. In this work, radial basis function network has been employed as ANN to model the breakthrough curves in fixed bed biosorption. The prediction has been compared to the experimental breakthrough curves of Cadmium, Lanthanum and a dye available in the literature. Results show that this network gives fairly accurate representation of the actual breakthrough curves. The results obtained from ANN modeling approach shows the better agreement between experimental and predicted breakthrough curves as the error for all these situations are within 6%.

Keywords

Artificial Neural Network Biosorption Artificial Neural Network Modeling Breakthrough Curve Radial Basis Function Neural Network 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

List of symbols

Yj

Signal coming to the jth neuron of the radial basis layer of RBF neural network

Yk

Signal coming to the kth neuron of the output layer of RBF neural network

b1, b2

Biases for hidden and output layer of RBF neural network

p

Input vector coming to the input layer of RBF neural network

w

Weight vector

||.||

Euclidean norm or vectorial distance

\( \varphi (.) \)

Radial basis function

S

Spread

SSE

Sum squared error

tk

Target value for kth output

yk

Actual value for kth output

E

Error between experimental and simulated curve

C0

Feed concentration (mM)

Z

Bed height (m)

V

Velocity with the feed solution passes to bed (m h−1)

References

  1. 1.
    Venkata Mohan S, Vijay Bhaskar Y, Karthikeyan J (2003) Biological decolorization of simulated azo dye in aqueous phase by algae Spirogyra species. Int J Environ Pollut 21(3):211–222CrossRefGoogle Scholar
  2. 2.
    Trujillo EM, Jeffers TH, Ferguson C, Stevenson HQ (1991) Mathematically modeling the removal of heavy metals from a wastewater using immobilized biomass. Environ Sci Technol 25:1559–1565CrossRefGoogle Scholar
  3. 3.
    Abdel-Jabbar N, Al-Asheh S, Hader B (2001) Modeling, parametric estimation, and sensitivity analysis for copper adsorption with moss packed-bed. Sep Sci Technol 36:2811–2833CrossRefGoogle Scholar
  4. 4.
    Hatzikioseyian A, Tsezos M, Mavituna F (2000) Application of simplified rapid equilibrium models in simulating experimental breakthrough curves from fixed bed biosorption reactors. Hydrometallurgy 59:395–406CrossRefGoogle Scholar
  5. 5.
    Addour L, Bellhocine D, Boudries N, Comeau Y, Pauss A, Mameri N (1994) Zinc uptake by Streptomyces rimosus biomass using a packed-bed column. J Chem Technol Biotechnol 74:1089–1095CrossRefGoogle Scholar
  6. 6.
    Yan G, Viraraghavan T, Chen M (2001) A new model for heavy metal removal in a biosorption column. Adsorpt Sci Technol 19:25–43CrossRefGoogle Scholar
  7. 7.
    Chu KH (2004) Improved fixed bed models for metal biosorption. Chem Eng J 97:233–239CrossRefGoogle Scholar
  8. 8.
    Betler PA, Cussler EL, Hu W-S (1988) Bioseparations: downstream processing for biotechnology. Wiley, New YorkGoogle Scholar
  9. 9.
    McCulloch WS, Pitts W (1943) A logical calculus of the ideas imminent in nervous activity. Bull Math Biophys 5:115–133zbMATHCrossRefMathSciNetGoogle Scholar
  10. 10.
    Chang JS, Huang JC (1998) Selective adsorption/recovery of Pb, Cu and Cd with multiple fixed beds containing immobilized bacterial biomass. Biotechnol Prog 14:735–741CrossRefGoogle Scholar
  11. 11.
    Texier AC, Fraur Andres Y, Brasquet C, Le Cloirecm P (2002) Fixed-bed study for lanthanide (La, Eu, Yb) ions removal from aqueous solutions by immobilized Pseudomonas aeruginosa: experimental data and modelization. Chemosphere 47:333–342CrossRefGoogle Scholar
  12. 12.
    Chu KH (2003) Prediction of two-metal biosorption equilibria using neural network. Eur J Min Proc Environ Prot 3(2):119–127Google Scholar
  13. 13.
    Joorabian M, Taleghani Asl SMA, Agarwal RK (2004) Accurate fault locator for EHV transmission lines based on radial basis function neural networks. Electr Power Syst Res 71:195–202CrossRefGoogle Scholar
  14. 14.
    Chen S, Cowan CFN, Grant PM (1991) Orthogonal least squares learning algorithm for radial basis function networks. IEEE Trans Neural Netw 2(2):302–309CrossRefGoogle Scholar
  15. 15.
    Volesky B, Prasetyo I (1994) Cadmium removal in a biosorption column. Biotechnol Bioeng 43:1010–1015CrossRefGoogle Scholar
  16. 16.
    Padmesh TVN, Vijayaraghaban K, Sekakaran G, Velan M (2005) Batch and column studies of acid dyes on fresh water alga Azolla filiculoides. J Hazard Mater 125:121–129CrossRefGoogle Scholar

Copyright information

© Springer-Verlag 2010

Authors and Affiliations

  1. 1.Department of Chemical EngineeringNew Mexico State UniversityLas CrucesUSA
  2. 2.Department of Chemical EngineeringJadavpur UniversityKolkataIndia

Personalised recommendations