Dynamic Data-Driven Modeling of Pharmaceutical Processes

被引:42
作者
Boukouvala, F. [1 ]
Muzzio, F. J. [1 ]
Ierapetritou, Marianthi G. [1 ]
机构
[1] Rutgers State Univ, Dept Chem & Biochem Engn, Piscataway, NJ 08854 USA
基金
美国国家科学基金会;
关键词
ARTIFICIAL NEURAL-NETWORKS; BLACK-BOX FUNCTIONS; NONLINEAR PROGRAMS;
D O I
10.1021/ie102305a
中图分类号
TQ [化学工业];
学科分类号
0817 ;
摘要
In many pharmaceutical process operations, first-principle models describing the behavior of the processed powders are difficult to derive or computationally very expensive and thus can be considered as "black-box" processes. Kriging is an efficient data-driven methodology that has been shown previously to predict steady-state operation of black-box processes while providing error estimates for each prediction. In this work, the ability of Kriging to capture the dynamic behavior of processes is evaluated and compared to the performance of dynamic Neural Network (NN) models. Design of Experiment (DoE) concepts are employed to collect the necessary dynamic input-output information that forms the initial rnultivariate database of the model. The most important feature of the proposed dynamic Kriging methodology is the ability to improve its predictive efficiency as the database is augmented by additional useful information while the process operates. An error tolerance is used in the adaptive procedure, so that only predictions that satisfy a strict accuracy constraint are added to the database. The performance of the proposed method is compared to that of dynamic NN modeling, through their application to a roller compactor process. Results indicate that dynamic Kriging has a better ability to adapt to continuous transitions in the operating conditions, compared to NN modeling. This on-the-fly approach can have significant applications in real-time optimization and control of systems for which a closed-form model is not available.
引用
收藏
页码:6743 / 6754
页数:12
相关论文
共 26 条
[1]   Basic concepts of artificial neural network (ANN) modeling and its application in pharmaceutical research [J].
Agatonovic-Kustrin, S ;
Beresford, R .
JOURNAL OF PHARMACEUTICAL AND BIOMEDICAL ANALYSIS, 2000, 22 (05) :717-727
[2]  
ANDRES H, 2009, 10 INT S PROC SYST E
[3]  
[Anonymous], 1989, Applied Geostatistics, 551.72 ISA
[4]   Application of Gaussian processes for black-box modelling of biosystems [J].
Azman, K. ;
Kocijan, J. .
ISA TRANSACTIONS, 2007, 46 (04) :443-457
[5]   Variogram or semivariogram? Understanding the variances in a variogram [J].
Bachmaier, Martin ;
Backes, Matthias .
PRECISION AGRICULTURE, 2008, 9 (03) :173-175
[6]   Artificial neural networks: fundamentals, computing, design, and application [J].
Basheer, IA ;
Hajmeer, M .
JOURNAL OF MICROBIOLOGICAL METHODS, 2000, 43 (01) :3-31
[7]  
Beale M.H., 2010, Neural Network ToolboxTM 7: User's Guide
[8]   Comparison between two types of Artificial Neural Networks used for validation of pharmaceutical processes [J].
Behzadi, Sharareh Salar ;
Prakasvudhisarn, Chakguy ;
Klocker, Johanna ;
Wolschann, Peter ;
Viernstein, Helmut .
POWDER TECHNOLOGY, 2009, 195 (02) :150-157
[9]  
BOUKOUVALA F, 2010, AICHE J
[10]  
Cressie N., 1993, Statistics for spatial data