Neural Computing and Applications

, Volume 31, Issue 1, pp 239–248 | Cite as

Application of ANN and RSM techniques for modeling electrospinning process of polycaprolactone

  • Tahere Khatti
  • Hossein Naderi-ManeshEmail author
  • Seyed Mehdi Kalantar
Original Article


Due to increasing application of nanofibers in many research fields, comprehensive knowledge of the electrospinning process as the most popular method of fiber production is essential. Modeling techniques are valuable tools for managing contributing factors in the electrospinning process, prior to the more expensive experimental techniques. In the present research, effective parameters on the diameter of electrospun polycaprolactone (PCL) nanofibers are analyzed using artificial neural networks (ANN) and response surface methodology (RSM). The assessed parameters include polymer concentration, voltage, and nozzle-to-collector distance. Response surface methodology based on the Box-Behnken design is utilized to develop a mathematical model as well as to determine the optimum condition for production of nanofiber with minimum diameter. In addition, multilayer perceptron neural networks are designed and trained by the sets of input-output patterns using the Levenberg-Marquardt backpropagation algorithm. The high regression coefficient value (R2 ≥ 0.97) and low root-mean-square error (RMSE ≤3.81) of the two models indicate that both models performed well in predicting PCL fiber diameter, although the RSM model slightly outperformed the ANN model in accuracy. The represented models could assist researchers in fabricating electrospun scaffolds with a defined fiber diameter, thus specializing such scaffolds in particular applications.


Electrospining Nanofiber Artificial neural networks Response surface methodology Polycaprolactone 


Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.


  1. 1.
    Woodruff MA, Hutmacher DW (2010) The return of a forgotten polymer—polycaprolactone in the 21st century. Prog Polym Sci 35(10):1217–1256Google Scholar
  2. 2.
    Alves da Silva M, Martins A, Costa-Pinto A, Costa P, Faria S, Gomes M, Reis R, Neves N (2010) Cartilage tissue engineering using electrospun PCL nanofiber meshes and MSCs. Biomacromolecules 11(12):3228–3236Google Scholar
  3. 3.
    Sinha V, Bansal K, Kaushik R, Kumria R, Trehan A (2004) Poly-ϵ-caprolactone microspheres and nanospheres: an overview. Int J Pharm 278(1):1–23Google Scholar
  4. 4.
    Ng KW, Achuth HN, Moochhala S, Lim TC, Hutmacher DW (2007) In vivo evaluation of an ultra-thin polycaprolactone film as a wound dressing. J Biomater Sci Polym Ed 18(7):925–938Google Scholar
  5. 5.
    Middleton JC, Tipton AJ (2000) Synthetic biodegradable polymers as orthopedic devices. Biomaterials 21(23):2335–2346Google Scholar
  6. 6.
    Freiberg S, Zhu X (2004) Polymer microspheres for controlled drug release. Int J Pharm 282(1):1–18Google Scholar
  7. 7.
    Gaucher G, Dufresne M-H, Sant VP, Kang N, Maysinger D, Leroux J-C (2005) Block copolymer micelles: preparation, characterization and application in drug delivery. J Control Release 109(1):169–188Google Scholar
  8. 8.
    Marrazzo C, Di Maio E, Iannace S (2008) Conventional and nanometric nucleating agents in poly (ϵ-caprolactone) foaming: crystals vs. bubbles nucleation. Polym Eng Sci 48(2):336–344Google Scholar
  9. 9.
    Lee K, Kim H, Khil M, Ra Y, Lee D (2003) Characterization of nano-structured poly (ε-caprolactone) nonwoven mats via electrospinning. Polymer 44(4):1287–1294Google Scholar
  10. 10.
    Hong S, Kim G (2011) Fabrication of size-controlled three-dimensional structures consisting of electrohydrodynamically produced polycaprolactone micro/nanofibers. Applied Physics A 103(4):1009–1014Google Scholar
  11. 11.
    Van de Witte P, Dijkstra P, Van den Berg J, Feijen J (1996) Phase separation processes in polymer solutions in relation to membrane formation. J Membr Sci 117(1):1–31Google Scholar
  12. 12.
    Chakarvarti S, Vetter J (1998) Template synthesis—a membrane based technology for generation of nano−/micro materials: a review. Radiat Meas 29(2):149–159Google Scholar
  13. 13.
    Teo W, Ramakrishna S (2006) A review on electrospinning design and nanofibre assemblies. Nanotechnology 17(14):R89Google Scholar
  14. 14.
    Andrady AL (2008) Science and technology of polymer nanofibers. John Wiley & Sons, HobokenGoogle Scholar
  15. 15.
    Huang Z-M, Zhang Y-Z, Kotaki M, Ramakrishna S (2003) A review on polymer nanofibers by electrospinning and their applications in nanocomposites. Compos Sci Technol 63(15):2223–2253Google Scholar
  16. 16.
    Agarwal P, Mishra P, Srivastava P (2012) Statistical optimization of the electrospinning process for chitosan/polylactide nanofabrication using response surface methodology. J Mater Sci 47(10):4262–4269Google Scholar
  17. 17.
    Doustgani A, Vasheghani-Farahani E, Soleimani M, Hashemi-Najafabadi S (2012) Optimizing the mechanical properties of electrospun polycaprolactone and nanohydroxyapatite composite nanofibers. Compos Part B 43(4):1830–1836Google Scholar
  18. 18.
    Nasouri K, Bahrambeygi H, Rabbi A, Shoushtari AM, Kaflou A (2012) Modeling and optimization of electrospun PAN nanofiber diameter using response surface methodology and artificial neural networks. J Appl Polym Sci 126(1):127–135Google Scholar
  19. 19.
    Gunoglu K, Demir N, Akkurt I, Demirci ZN (2013) ANN modeling of the bremsstrahlung photon flux in tantalum target. Neural Comput & Applic 23(6):1591–1595Google Scholar
  20. 20.
    El-Shafie A (2014) Neural network nonlinear modeling for hydrogen production using anaerobic fermentation. Neural Comput & Applic 24(3–4):539–547Google Scholar
  21. 21.
    Sha W, Edwards K (2007) The use of artificial neural networks in materials science based research. Mater Des 28(6):1747–1752Google Scholar
  22. 22.
    Yördem O, Papila M, Menceloğlu YZ (2008) Effects of electrospinning parameters on polyacrylonitrile nanofiber diameter: an investigation by response surface methodology. Mater Des 29(1):34–44Google Scholar
  23. 23.
    Gu S, Ren J, Vancso G (2005) Process optimization and empirical modeling for electrospun polyacrylonitrile (PAN) nanofiber precursor of carbon nanofibers. Eur Polym J 41(11):2559–2568Google Scholar
  24. 24.
    Khanlou HM, Sadollah A, Ang BC, Kim JH, Talebian S, Ghadimi A (2014) Prediction and optimization of electrospinning parameters for polymethyl methacrylate nanofiber fabrication using response surface methodology and artificial neural networks. Neural Comput & Applic 25(3–4):767–777Google Scholar
  25. 25.
    Sadan MK, Ahn H-J, Chauhan G, Reddy N (2016) Quantitative estimation of poly (methyl methacrylate) nano-fiber membrane diameter by artificial neural networks. Eur Polym J 74:91–100Google Scholar
  26. 26.
    Sarkar K, Ghalia MB, Wu Z, Bose SC (2009) A neural network model for the numerical prediction of the diameter of electro-spun polyethylene oxide nanofibers. J Mater Process Technol 209(7):3156–3165Google Scholar
  27. 27.
    Rabbi A, Nasouri K, Bahrambeygi H, Shoushtari AM, Babaei MR (2012) RSM and ANN approaches for modeling and optimizing of electrospun polyurethane nanofibers morphology. Fibers and Polymers 13(8):1007–1014Google Scholar
  28. 28.
    Sarlak N, Nejad MAF, Shakhesi S, Shabani K (2012) Effects of electrospinning parameters on titanium dioxide nanofibers diameter and morphology: an investigation by Box–Wilson central composite design (CCD). Chem Eng J 210:410–416Google Scholar
  29. 29.
    Sadollah A, Ghadimi A, Metselaar IH, Bahreininejad A (2013) Prediction and optimization of stability parameters for titanium dioxide nanofluid using response surface methodology and artificial neural networks. Sci Eng Compos Mater 20(4):319–330Google Scholar
  30. 30.
    Faridi-Majidi R, Ziyadi H, Naderi N, Amani A (2012) Use of artificial neural networks to determine parameters controlling the nanofibers diameter in electrospinning of nylon-6,6. J Appl Polym Sci 124(2):1589–1597Google Scholar
  31. 31.
    Ali AA, Eltabey M, Farouk W, Zoalfakar SH (2014) Electrospun precursor carbon nanofibers optimization by using response surface methodology. J Electrost 72(6):462–469Google Scholar
  32. 32.
    Gu SY, Ren J (2005) Process optimization and empirical modeling for electrospun poly (D,L-lactide) fibers using response surface methodology. Macromol Mater Eng 290(11):1097–1105Google Scholar
  33. 33.
    Naghibzadeh M, Adabi M (2014) Evaluation of effective electrospinning parameters controlling gelatin nanofibers diameter via modelling artificial neural networks. Fibers and Polymers 15(4):767–777Google Scholar
  34. 34.
    Khalili S, Khorasani SN, Saadatkish N, Khoshakhlagh K (2016) Characterization of gelatin/cellulose acetate nanofibrous scaffolds: prediction and optimization by response surface methodology and artificial neural networks. Polymer Science Series A 58(3):399–408Google Scholar
  35. 35.
    Gönen SÖ, Taygun ME, Küçükbayrak S (2015) Effects of electrospinning parameters on gelatin/poly (ϵ-caprolactone) nanofiber diameter. Chemical Engineering & Technology 38(5):844–850Google Scholar
  36. 36.
    Karimi MA, Pourhakkak P, Adabi M, Firoozi S, Adabi M, Naghibzadeh M (2015) Using an artificial neural network for the evaluation of the parameters controlling PVA/chitosan electrospun nanofibers diameter. E-Polymers 15(2):127–138Google Scholar
  37. 37.
    Ketabchi N, Naghibzadeh M, Adabi M, Esnaashari SS, Faridi-Majidi R (2016) Preparation and optimization of chitosan/polyethylene oxide nanofiber diameter using artificial neural networks. Neural Computing and Applications:1–13Google Scholar
  38. 38.
    Hsu CM, Shivkumar S (2004) N, N-Dimethylformamide additions to the solution for the electrospinning of poly (ε-caprolactone) nanofibers. Macromol Mater Eng 289(4):334–340Google Scholar
  39. 39.
    Chen M, Patra PK, Warner SB, Bhowmick S (2007) Role of fiber diameter in adhesion and proliferation of NIH 3T3 fibroblast on electrospun polycaprolactone scaffolds. Tissue Eng 13(3):579–587Google Scholar
  40. 40.
    Box GE, Behnken DW (1960) Some new three level designs for the study of quantitative variables. Technometrics 2(4):455–475MathSciNetGoogle Scholar
  41. 41.
    Manohar M, Joseph J, Selvaraj T, Sivakumar D (2013) Application of Box Behnken design to optimize the parameters for turning Inconel 718 using coated carbide tools. International Journal of Scientific & Engineering Research 4(4):620–642Google Scholar
  42. 42.
    Bölgen N, Menceloğlu YZ, Acatay K, Vargel I, Pişkin E (2005) In vitro and in vivo degradation of non-woven materials made of poly (ε-caprolactone) nanofibers prepared by electrospinning under different conditions. J Biomater Sci Polym Ed 16(12):1537–1555Google Scholar
  43. 43.
    Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2(5):359–366zbMATHGoogle Scholar
  44. 44.
    Kecman V (2001) Learning and soft computing: support vector machines, neural networks, and fuzzy logic models. MIT Press, CambridgezbMATHGoogle Scholar
  45. 45.
    Wang L, Fu X (2006) Data mining with computational intelligence. Springer Science & Business Media, BerlinzbMATHGoogle Scholar
  46. 46.
    Fu X, Wang L (2003) Data dimensionality reduction with application to simplifying RBF network structure and improving classification performance. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics) 33(3):399–409Google Scholar

Copyright information

© The Natural Computing Applications Forum 2017

Authors and Affiliations

  • Tahere Khatti
    • 1
  • Hossein Naderi-Manesh
    • 1
    Email author
  • Seyed Mehdi Kalantar
    • 2
  1. 1.Department of Nanobiotechnology, Faculty of Biological SciencesTarbiat Modares UniversityTehranIran
  2. 2.Department of Genetics, Research and Clinical Center for InfertilityShahid Sadoughi University of Medical SciencesYazdIran

Personalised recommendations