Efficient meta-modelling of complex process simulations with time-space-dependent outputs

Process simulations can become computationally too complex to be useful for model-based analysis and design purposes. Meta-modelling is an efficient technique to develop a surrogate model using “computer data”, which are collected from a small number of simulation runs. This paper considers meta-modelling with time–space-dependent outputs in order to investigate the dynamic/distributed behaviour of the process. The conventional method of treating temporal/spatial coordinates as model inputs results in dramatic increase of modelling data and is computationally inefficient. This paper applies principal component analysis to reduce the dimension of time–space-dependent output variables whilst retaining the essential information, prior to developing meta-models. Gaussian process regression (also termed kriging model) is adopted for meta-modelling, for its superior prediction accuracy when compared with more traditional neural networks. The proposed methodology is successfully validated on a computational fluid dynamic simulation of an aerosol dispersion process, which is potentially applicable to industrial and environmental safety assessment.

[1]  Darci Odloak,et al.  Using kriging models for real-time process optimisation , 2008 .

[2]  Constantinos Theodoropoulos,et al.  Order reduction for nonlinear dynamic models of distributed reacting systems , 2000 .

[3]  André I. Khuri,et al.  Response surface methodology , 2010 .

[4]  Heng Tao Shen,et al.  Principal Component Analysis , 2009, Encyclopedia of Biometrics.

[5]  Tao Chen,et al.  Bagging for Gaussian process regression , 2009, Neurocomputing.

[6]  D. Higdon,et al.  Computer Model Calibration Using High-Dimensional Output , 2008 .

[7]  Raghunathan Rengaswamy,et al.  A review of process fault detection and diagnosis: Part III: Process history based methods , 2003, Comput. Chem. Eng..

[8]  Elaine Martin,et al.  Bayesian linear regression and variable selection for spectroscopic calibration. , 2009, Analytica chimica acta.

[9]  Yanhui Yang,et al.  Response surface methodology using Gaussian processes : towards optimizing the trans-stilbene epoxidation over Co 2 +-NaX catalysts , 2009 .

[10]  Donald R. Jones,et al.  A Taxonomy of Global Optimization Methods Based on Response Surfaces , 2001, J. Glob. Optim..

[11]  J. Rougier.  Efficient Emulators for Multivariate Deterministic Functions , 2008 .

[12]  Russell R. Barton,et al.  A review on design, modeling and applications of computer experiments , 2006 .

[13]  Yanhui Yang,et al.  Response surface methodology using Gaussian processes: Towards optimizing the trans-stilbene epoxidation over Co2+-NaX catalysts , 2010 .

[14]  Jie Zhang,et al.  Prediction of polymer quality in batch polymerisation reactors using robust neural networks , 1998 .

[15]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[16]  George Chryssolouris,et al.  Confidence interval prediction for neural network models , 1996, IEEE Trans. Neural Networks.

[17]  David J. C. MacKay,et al.  A Practical Bayesian Framework for Backpropagation Networks , 1992, Neural Computation.

[18]  James S Brown.  Particle Inhalability at Low Wind Speeds , 2005, Inhalation toxicology.

[19]  Yong Zhang,et al.  Uniform Design: Theory and Application , 2000, Technometrics.

[20]  Michael E. Tipping,et al.  Probabilistic Principal Component Analysis , 1999 .

[21]  Carl E. Rasmussen,et al.  Evaluating Predictive Uncertainty Challenge , 2005, MLCW.

[22]  W. Ray,et al.  Identification and control of distributed parameter systems by means of the singular value decomposition , 1995 .

[23]  Ian T. Cameron,et al.  Process Modelling and Model Analysis , 2013 .

[24]  P. Salagnac,et al.  Optimization of Radiant-Convective Drying of a Porous Medium by Design of Experiment Methodology , 2006 .

[25]  Hans Henrik Thodberg,et al.  A review of Bayesian neural networks with an application to near infrared spectroscopy , 1996, IEEE Trans. Neural Networks.

[26]  Karlene A. Hoo,et al.  Low-order Control-relevant Models for A Class of Distributed Parameter Systems , 2001 .

[27]  Ľudovít Jelemenský,et al.  CFD dispersion modelling for emergency preparadnes. , 2009 .

[28]  I. Grossmann,et al.  An algorithm for the use of surrogate models in modular flowsheet optimization , 2008 .

[29]  A. OHagan,et al.  Bayesian analysis of computer code outputs: A tutorial , 2006, Reliab. Eng. Syst. Saf..

[30]  Bojan Likar,et al.  Predictive control of a gas-liquid separation plant based on a Gaussian process model , 2007, Comput. Chem. Eng..

[31]  D. Gidaspow.  Multiphase Flow and Fluidization: Continuum and Kinetic Theory Descriptions , 1994 .

[32]  Richard J. Beckman,et al.  A Comparison of Three Methods for Selecting Values of Input Variables in the Analysis of Output From a Computer Code , 2000, Technometrics.

[33]  Matthew J. Realff,et al.  Metamodeling Approach to Optimization of Steady-State Flowsheet Simulations: Model Generation , 2002 .

[34]  Urmila M. Diwekar,et al.  An efficient sampling technique for off-line quality control , 1997 .

[35]  Raghunathan Rengaswamy,et al.  A review of process fault detection and diagnosis: Part I: Quantitative model-based methods , 2003, Comput. Chem. Eng..

[36]  Sonja Kuhnt,et al.  Design and analysis of computer experiments , 2010 .

[37]  Constantinos Theodoropoulos,et al.  Order Reduction of Nonlinear Dynamic Models for Distributed Reacting Systems , 1998 .

[38]  Wolfgang Marquardt,et al.  A grey-box modeling approach for the reduction of nonlinear systems , 2008 .

[39]  A. O'Hagan,et al.  Bayesian calibration of computer models , 2001 .

[40]  Tao Yu,et al.  Reliable multi-objective optimization of high-speed WEDM process based on Gaussian process regression , 2008 .

[41]  M. J. Bayarri,et al.  Computer model validation with functional output , 2007, 0711.3271.

[42]  Lehel Csató,et al.  Sparse On-Line Gaussian Processes , 2002, Neural Computation.

[43]  Thomas J. Santner,et al.  The Design and Analysis of Computer Experiments , 2003, Springer Series in Statistics.

[44]  C. Holmes,et al.  A probabilistic nearest neighbour method for statistical pattern recognition , 2002 .

[45]  I. Grossmann,et al.  Rigorous flowsheet optimization using process simulators and surrogate models , 2008 .