Advertisement

Neural Computing and Applications

, Volume 29, Issue 7, pp 467–481 | Cite as

Predictive modeling of die filling of the pharmaceutical granules using the flexible neural tree

  • Varun Kumar Ojha
  • Serena Schiano
  • Chuan-Yu Wu
  • Václav Snášel
  • Ajith Abraham
Original Article

Abstract

In this work, a computational intelligence (CI) technique named flexible neural tree (FNT) was developed to predict die filling performance of pharmaceutical granules and to identify significant die filling process variables. FNT resembles feedforward neural network, which creates a tree-like structure by using genetic programming. To improve accuracy, FNT parameters were optimized by using differential evolution algorithm. The performance of the FNT-based CI model was evaluated and compared with other CI techniques: multilayer perceptron, Gaussian process regression, and reduced error pruning tree. The accuracy of the CI model was evaluated experimentally using die filling as a case study. The die filling experiments were performed using a model shoe system and three different grades of microcrystalline cellulose (MCC) powders (MCC PH 101, MCC PH 102, and MCC DG). The feed powders were roll-compacted and milled into granules. The granules were then sieved into samples of various size classes. The mass of granules deposited into the die at different shoe speeds was measured. From these experiments, a dataset consisting true density, mean diameter (d50), granule size, and shoe speed as the inputs and the deposited mass as the output was generated. Cross-validation (CV) methods such as 10FCV and 5x2FCV were applied to develop and to validate the predictive models. It was found that the FNT-based CI model (for both CV methods) performed much better than other CI models. Additionally, it was observed that process variables such as the granule size and the shoe speed had a higher impact on the predictability than that of the powder property such as d50. Furthermore, validation of model prediction with experimental data showed that the die filling behavior of coarse granules could be better predicted than that of fine granules.

Keywords

Predictive modeling Die filling Flowability Pharmaceutical granules Flexible neural tree Feature selection 

Notes

Acknowledgments

This work was supported by the IPROCOM Marie Curie Initial Training Network, funded through the People Programme (Marie Curie Actions) of the European Unions Seventh Framework Programme.

References

  1. 1.
    Coube O, Cocks A, Wu C-Y (2005) Experimental and numerical study of die filling, powder transfer and die compaction. Powder Metall 48(1):68–76CrossRefGoogle Scholar
  2. 2.
    Wu C-Y, Dihoru L, Cocks AC (2003) The flow of powder into simple and stepped dies. Powder Technol 134(1):24–39CrossRefGoogle Scholar
  3. 3.
    Schneider L, Sinka I, Cocks A (2007) Characterisation of the flow behaviour of pharmaceutical powders using a model die-shoe filling system. Powder Technol 173(1):59–71CrossRefGoogle Scholar
  4. 4.
    Wu C-Y (2008) Dem simulations of die filling during pharmaceutical tabletting. Particuology 6(6):412–418CrossRefGoogle Scholar
  5. 5.
    Mills L, Sinka I (2013) Effect of particle size and density on the die fill of powders. Eur J Pharm Biopharm 84(3):642–652CrossRefGoogle Scholar
  6. 6.
    Jackson S, Sinka I, Cocks A (2007) The effect of suction during die fill on a rotary tablet press. Eur J Pharm Biopharm 65(2):253–256CrossRefGoogle Scholar
  7. 7.
    Lawrence L, Beddow J (1968) Some effects of vibration upon powder segregation during die filling. Powder Technol 2(2):125–130CrossRefGoogle Scholar
  8. 8.
    Bocchini G (1987) Influence of small die width on filling and compacting densities. Powder Metall 30(4):261–266CrossRefGoogle Scholar
  9. 9.
    Rice E, Tengzelius J (1986) Die filling characteristics of metal powders. Powder Metall 29(3):183–194CrossRefGoogle Scholar
  10. 10.
    Mendez R, Muzzio FJ, Velazquez C (2012) Powder hydrophobicity and flow properties: effect of feed frame design and operating parameters. AIChE J 58(3):697–706CrossRefGoogle Scholar
  11. 11.
    Wu C-Y, Cocks A (2004) Flow behaviour of powders during die filling. Powder Metall 47(2):127–136CrossRefGoogle Scholar
  12. 12.
    Guo Y, Kafui K, Wu C-Y, Thornton C, Seville JP (2009) A coupled dem/cfd analysis of the effect of air on powder flow during die filling. AIChE J 55(1):49–62CrossRefGoogle Scholar
  13. 13.
    Guo Y, Wu C-Y, Thornton C (2011) The effects of air and particle density difference on segregation of powder mixtures during die filling. Chem Eng Sci 66(4):661–673CrossRefGoogle Scholar
  14. 14.
    Zhao C, Jain A, Hailemariam L, Suresh P, Akkisetty P, Joglekar G, Venkatasubramanian V, Reklaitis GV, Morris K, Basu P (2006) Toward intelligent decision support for pharmaceutical product development. J Pharm Innov 1(1):23–35CrossRefGoogle Scholar
  15. 15.
    Bourquin J, Schmidli H, van Hoogevest P, Leuenberger H (1998) Advantages of artificial neural networks (ANNs) as alternative modelling technique for data sets showing non-linear relationships using data from a galenical study on a solid dosage form. Eur J Pharm Sci 7(1):5–16CrossRefGoogle Scholar
  16. 16.
    Wu C-Y, Hsu Y-C (2002) Optimal shape design of an extrusion-forging die using a polynomial network and a genetic algorithm. Int J Adv Manuf Technol 20(2):128–137CrossRefGoogle Scholar
  17. 17.
    Kim D, Kim B (2000) Application of neural network and fem for metal forming processes. Int J Mach Tools Manuf 40(6):911–925CrossRefGoogle Scholar
  18. 18.
    Lam H-K, Nguyen HT (2012) Computational intelligence and its applications: evolutionary computation, fuzzy logic, neural network and support vector machine techniques. World Scientific, LondonCrossRefGoogle Scholar
  19. 19.
    Haykin S (2009) Neural networks and learning machines, vol 3. Pearson Education, Upper Saddle RiverMATHGoogle Scholar
  20. 20.
    Kohavi R, Quinlan JR (2002) Data mining tasks and methods: classification: decision-tree discovery. In: Klösgen W, Zytkow JM (eds) Handbook of data mining and knowledge discovery. Oxford University Press, Inc., pp 267–276Google Scholar
  21. 21.
    Rasmussen CE, Williams C (2006) Gaussian processes for machine learning, vol 2. The MIT Press, New York no. 3MATHGoogle Scholar
  22. 22.
  23. 23.
    Hall M, Frank E, Holmes G, Pfahringer B, Reutemann P, Witten IH (2009) The weka data mining software: an update. ACM SIGKDD Explor Newsl 11(1):10–18CrossRefGoogle Scholar
  24. 24.
    Chen Y, Yang B, Dong J (2004) Nonlinear system modelling via optimal design of neural trees. Int J Neural Syst 14(02):125–137CrossRefGoogle Scholar
  25. 25.
    Chen Y, Yang B, Dong J, Abraham A (2005) Time-series forecasting using flexible neural tree model. Inf Sci 174(3):219–235MathSciNetCrossRefGoogle Scholar
  26. 26.
    Poli R, Langdon WB, McPhee NF, Koza JR (2008) A field guide to genetic programming. Lulu.comGoogle Scholar
  27. 27.
    Shou-Ning Q, Zhao-lian L, Guang-qiang C, Bing Z, Su-juan W (2008) Modeling of cement decomposing furnace production process based on flexible neural tree. In: International conference on information management, innovation management and industrial engineering, 2008. ICIII’08, vol 3. IEEE, pp 128–133Google Scholar
  28. 28.
    Chen Y, Wu P, Wu Q (2008) Foreign exchange rate forecasting using higher order flexible neural tree. Artificial higher order neural networks for economics and business. IGI Global Publisher, HersheyGoogle Scholar
  29. 29.
    Yang B, Chen Y, Jiang M (2013) Reverse engineering of gene regulatory networks using flexible neural tree models. Neurocomputing 99:458–466CrossRefGoogle Scholar
  30. 30.
    Chen Z, Peng L, Gao C, Yang B, Chen Y, Li J (2015) Flexible neural trees based early stage identification for ip traffic. Soft Comput 1–12Google Scholar
  31. 31.
    Ojha VK, Abraham A, Snasel V (2016) Ensemble of heterogeneous flexible neural tree for the approximation and feature-selection of poly (lactic-co-glycolic acid) micro-and nanoparticle. In: Proceedings of the second international Afro-European conference for industrial advancement AECIA 2015. Springer, pp. 155–165Google Scholar
  32. 32.
    Yao X (1999) Evolving artificial neural networks. Proc IEEE 87(9):1423–1447CrossRefGoogle Scholar
  33. 33.
    Riedmiller M, Braun H (1993) A direct adaptive method for faster backpropagation learning: the rprop algorithm. In: IEEE international conference on neural networks. IEEE, pp 586–591Google Scholar
  34. 34.
    Storn R, Price K (1997) Differential evolution—a simple and efficient heuristic for global optimization over continuous spaces. J Glob Optim 11(4):341–359MathSciNetCrossRefMATHGoogle Scholar
  35. 35.
    Zhang J, Pei C, Schiano S, Heaps D, Wu CY (2016) The application of terahertz pulsed imaging in characterising density distribution of roll-compacted ribbons. Eur J Pharm Biopharm, 106(2016):20–25Google Scholar
  36. 36.
    Schiano S, Wu C-Y, Mirtic A, Reynolds G (2016) A novel use of friability testing for characterising ribbon milling behaviour. Eur J Pharm Biopharm 104:82–88CrossRefGoogle Scholar

Copyright information

© The Natural Computing Applications Forum 2016

Authors and Affiliations

  • Varun Kumar Ojha
    • 1
  • Serena Schiano
    • 2
  • Chuan-Yu Wu
    • 2
  • Václav Snášel
    • 1
  • Ajith Abraham
    • 3
  1. 1.IT4InnovationsVŠB-Technical University of OstravaOstravaCzech Republic
  2. 2.Department of Chemical and Process EngineeringUniversity of SurreyGuildfordUK
  3. 3.Machine Intelligence Research Labs (MIR Labs)AuburnUSA

Personalised recommendations