Optimisation of compression parameters with Al-based mathematical models

Abstract: This chapter describes a study of the influence of particle size and the settings of tableting parameters on tablet capping tendency. Artificial neural network (ANN) and fuzzy models were used for modelling the effect of particle size and tableting machine settings on the capping coefficient. The basic principles of the tableting process are described, followed by a description of principal components analysis, then ANN and fuzzy models. Finally, a real tableting case is presented. The suitability of routinely measured quantities for prediction of the tablet quality was tested. Results showed that model-based expert systems developed on the contemporary routinely measured quantities can significantly improve manual trial-and-error procedures; however, they cannot replace them. The results also suggest that where it is not possible to obtain a sufficient number of measurements to uniquely identify the model, it is beneficial to use several modelling techniques to estimate the quality of model prediction.

[1]  M. H. Rubinstein,et al.  The effects of slugging and recompression on pharmaceutical excipients , 1995 .

[2]  Jørn M Sonnergaard,et al.  Quantification of the compactibility of pharmaceutical powders. , 2006, European journal of pharmaceutics and biopharmaceutics : official journal of Arbeitsgemeinschaft fur Pharmazeutische Verfahrenstechnik e.V.

[3]  Martin T. Hagan,et al.  Neural network design , 1995 .

[4]  Mukesh C. Gohel,et al.  Functionality testing of a multifunctional directly compressible adjuvant containing lactose, polyvinylpyrrolidone, and croscarmellose sodium , 2002 .

[5]  G. Alderborn,et al.  Bonding Surface area and Bonding Mechanism-Two Important Factors fir the Understanding of Powder Comparability , 1993 .

[6]  V. Rudolph,et al.  Interparticle van der Waals force in powder flowability and compactibility. , 2004, International journal of pharmaceutics.

[7]  B. Leclerc,et al.  Compaction behaviour and new predictive approach to the compressibility of binary mixtures of pharmaceutical excipients. , 2006, European journal of pharmaceutics and biopharmaceutics : official journal of Arbeitsgemeinschaft fur Pharmazeutische Verfahrenstechnik e.V.

[8]  J. Geoffroy,et al.  Compression characteristics of binary mixtures , 1990 .

[9]  J. Fell,et al.  Bonding mechanisms in tabletting , 1990 .

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

[11]  Bart Kosko,et al.  Fuzzy Systems as Universal Approximators , 1994, IEEE Trans. Computers.

[12]  N. Draper,et al.  Applied Regression Analysis , 1967 .

[13]  G. Alderborn,et al.  The effect of moisture content on the compression and bond-formation properties of amorphous lactose particles , 1997 .

[14]  Cheng-Jian Lin,et al.  SISO Nonlinear System Identification Using a Fuzzy-Neural Hybrid System , 1997, Int. J. Neural Syst..

[15]  Lotfi A. Zadeh,et al.  Fuzzy Sets , 1996, Inf. Control..

[16]  Sibu Chakrabarti,et al.  Physical properties and compact analysis of commonly used direct compression binders , 2003, AAPS PharmSciTech.

[17]  Guanrong Chen,et al.  Necessary Conditions for Some Typical Fuzzy Systems as Universal Approximators , 1997, Autom..

[18]  R. Goldberg.  Methods of Real Analysis , 1964 .

[19]  Maribel Rios,et al.  Developments in powder flow testing , 2006 .

[20]  Igor Skrjanc,et al.  Minimisation of the capping tendency by tableting process optimisation with the application of artificial neural networks and fuzzy models. , 2009, European journal of pharmaceutics and biopharmaceutics : official journal of Arbeitsgemeinschaft fur Pharmazeutische Verfahrenstechnik e.V.

[21]  Igor Skrjanc,et al.  Tableting process optimisation with the application of fuzzy models. , 2010, International journal of pharmaceutics.

[22]  Jukka Ilkka,et al.  Prediction of the compression behaviour of powder mixtures by the Heckel equation , 1993 .

[23]  L X Wang,et al.  Fuzzy basis functions, universal approximation, and orthogonal least-squares learning , 1992, IEEE Trans. Neural Networks.

[24]  P. Schmidt,et al.  Dry granulation and compression of spray-dried plant extracts , 2005, AAPS PharmSciTech.

[25]  Franc Vrecer,et al.  Influence of dry granulation on compactibility and capping tendency of macrolide antibiotic formulation. , 2008, International journal of pharmaceutics.

[26]  K M Picker,et al.  Time Dependence of Elastic Recovery for Characterization of Tableting Materials , 2001, Pharmaceutical development and technology.

[27]  Bruno C. Hancock,et al.  Modelling the mechanical behaviour of pharmaceutical powders during compaction , 2005 .

[28]  L. Hovgaard,et al.  Bulk Characterization of Pharmaceutical Powders by Low-Pressure Compression II: Effect of Method Settings and Particle Size , 2006, Pharmaceutical development and technology.