Paper Info
Title
Efficient meta-modelling of complex process simulations with time–space-dependent outputs
Abstract
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.
Year
DOI
Venue
2011
10.1016/j.compchemeng.2010.05.013
Computers & Chemical Engineering
Keywords
Field
DocType
Computer experiments,Design of experiments,Gaussian process,Kriging model,Meta-model,Principal component analysis
Kriging,Data modeling,Computer experiment,Data mining,Mathematical optimization,Simulation,Surrogate model,Gaussian process,Artificial neural network,Mathematics,Metamodeling,Dynamic simulation
Journal
Volume
Issue
ISSN
35
3
0098-1354
Citations 
PageRank 
References 
5
0.69
10
Authors
4
Name
Order
Citations
PageRank
Tao Chen112511.27
Kunn Hadinoto250.69
Wenjin Yan350.69
Yifei Ma4387.20