Predictive modelling of the granulation process using a systems-engineering approach

Abstract The granulation process is considered to be a crucial operation in many industrial applications. The modelling of the granulation process is, therefore, an important step towards controlling and optimizing the downstream processes, and ensuring optimal product quality. In this research paper, a new integrated network based on Artificial Intelligence (AI) is proposed to model a high shear granulation (HSG) process. Such a network consists of two phases: in the first phase the inputs and the target outputs are used to train a number of models, where the predicted outputs from this phase and the target are used to train another model in the second phase to lead to the final predicted output. Because of the complex nature of the granulation process, the error residual is exploited further in order to improve the model performance using a Gaussian mixture model (GMM). The overall proposed network successfully predicts the properties of the granules produced by HSG, and outperforms also other modelling frameworks in terms of modelling performance and generalization capability. In addition, the error modelling using the GMM leads to a significant improvement in prediction.

[1]  M. Mahfouf,et al.  Modelling of hot strip rolling process using a hybrid neural network approach , 2008 .

[2]  Jonathan Seville,et al.  Using intelligent software to predict the effects of formulation and processing parameters on roller compaction , 2008 .

[3]  M. Hounslow,et al.  An investigation into the kinetics of liquid distribution and growth in high shear mixer agglomeration , 1998 .

[4]  Masayuki Matsui,et al.  An application of the computer optimization technique to wet granulation process involving explosive growth of particles , 1997 .

[5]  Gavin K. Reynolds,et al.  Breakage in granulation: A review , 2005 .

[6]  Mahdi Mahfouf,et al.  Optimal input selection for neural fuzzy modelling with application to Charpy energy prediction , 2011, 2011 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2011).

[7]  K. Leiviskä,et al.  The advantages by the use of neural networks in modelling the fluidized bed granulation process , 1994 .

[8]  Johan A. Westerhuis,et al.  Multivariate modelling of the tablet manufacturing process with wet granulation for tablet optimization and in-process control , 1997 .

[9]  Jinsheng Fu,et al.  Prediction of the Particle Size Distribution Parameters in a High Shear Granulation Process Using a Key Parameter Definition Combined Artificial Neural Network Model , 2015 .

[10]  Simon Rogers,et al.  A First Course in Machine Learning , 2011, Chapman and Hall / CRC machine learning and pattern recognition series.

[11]  D. Opitz,et al.  Popular Ensemble Methods: An Empirical Study , 1999, J. Artif. Intell. Res..

[12]  Michael J. Hounslow,et al.  Development of a predictive high-shear granulation model , 2003 .

[13]  Derek A. Linkens,et al.  Modelling and multivariable control in anaesthesia using neural-fuzzy paradigms: Part I. Classification of depth of anaesthesia and development of a patient model , 2005, Artif. Intell. Medicine.

[14]  J. Leader.  Numerical Analysis and Scientific Computation , 2022 .

[15]  Mahdi Mahfouf,et al.  Grain Growth Modelling for Continuous Reheating Process — A Neural Network-based Approach , 2003 .

[16]  Yun Zhang,et al.  Design of ensemble neural network using entropy theory , 2011, Adv. Eng. Softw..

[17]  Torben Schæfer,et al.  Melt Granulation in A Laboratory Scale High Shear Mixer , 1990 .

[18]  James D. Litster,et al.  Growth regime map for liquid-bound granules , 1998 .

[19]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[20]  P. V. Danckwerts,et al.  GRANULE FORMATION BY THE AGGLOMERATION OF DAMP POWDERS PART I: THE MECHANISM OF GRANULE GROWTH , 1981 .

[21]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[22]  Gavin K. Reynolds,et al.  An experimental study of the variability in the properties and quality of wet granules , 2004 .

[23]  Michael J. Hounslow,et al.  Binder addition methods and binder distribution in high shear and fluidised bed granulation , 2011 .

[24]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

[25]  Magnus Karlsson,et al.  Empirical to mechanistic modelling in high shear granulation , 2005 .

[26]  Jonathan Seville,et al.  Exploring the regime map for high-shear mixer granulation , 2009 .

[27]  Yoshinobu Sato,et al.  Application of a neural network to granulation scale-up , 1997 .

[28]  Mehrdji Hemati,et al.  Wet granulation in laboratory scale high shear mixers: Effect of binder properties , 2011 .

[29]  Mahdi Mahfouf,et al.  ‘Symbiotic’ data-driven modelling for the accurate prediction of mechanical properties of alloy steels , 2010, 2010 5th IEEE International Conference Intelligent Systems.

[30]  G. McLachlan,et al.  The EM algorithm and extensions , 1996 .

[31]  S. Iveson,et al.  Limitations of one-dimensional population balance models of wet granulation processes☆ , 2002 .

[32]  Derek A. Linkens,et al.  Modelling and multivariable control in anaesthesia using neural-fuzzy paradigms: Part II. Closed-loop control of simultaneous administration of propofol and remifentanil , 2005, Artif. Intell. Medicine.

[33]  Witold Pedrycz,et al.  Advances in Fuzzy Clustering and its Applications , 2007 .

[34]  Gavin K. Reynolds,et al.  Non-uniformity of binder distribution in high-shear granulation , 2004 .

[35]  Markus Kraft,et al.  Modelling and validation of granulation with heterogeneous binder dispersion and chemical reaction , 2007 .

[36]  José Alberto Mauricio.  Computing and using residuals in time series models , 2008, Comput. Stat. Data Anal..

[37]  P. Sheskey,et al.  Preliminary Report of the Discovery of a New Pharmaceutical Granulation Process Using Foamed Aqueous Binders , 2004, Drug development and industrial pharmacy.

[38]  Michael J. Hounslow,et al.  DIRECT EVIDENCE OF HETEROGENEITY DURING HIGH-SHEAR GRANULATION , 2000 .

[39]  Miroslav Pavlović,et al.  The best approximation and composition with inner functions. , 1995 .

[40]  C. Micchelli,et al.  Approximation by superposition of sigmoidal and radial basis functions , 1992 .

[41]  Geoffrey J. McLachlan,et al.  Mixture models : inference and applications to clustering , 1989 .

[42]  George Panoutsos,et al.  Probabilistic characterisation of model error using Gaussian mixture model—With application to Charpy impact energy prediction for alloy steel , 2012 .