ISSN 0253-2778

CN 34-1054/N

open
Free to Publish. Free to Read.
Open AccessOpen Access JUSTC Engineering and Materials Science

Temperature predictions of a single-room fire based on the CoKriging model

  • State Key Laboratory of Fire Science, University of Science and Technology of China, Hefei 230027, China

Funds:  National Natural Science Foundation of China (51576183) and the Fundamental Research Funds for the Central Universities (WK2320000048 & WK2320000042).
Cite this:
https://doi.org/10.52396/JUST-2020-1140
More Information
  • Author Bio:

    Shen Di is a postgraduate student under the supervision of Prof. Jiang Yong at University of Science and Technology of China (USTC). She received her bachelor's degree in Safety Engineering from Sichuan University (SCU) in 2018. Her research mainly focuses on the application of machine learning in fire forecasting and source intensity back-calculation.

  • Corresponding author: Jiang Yong (Corresponding author) is a doctoral supervisor and Professor at University of Science and Technology of China (USTC), and is currently the director of Computer Simulation Research Office, State Key Laboratory of Fire Science. His research interests mainly include: precision diagnostic experimental technology of fire and combustion, computer simulation and emulation of fire and combustion, measurement and model of combustion reaction kinetics, thermal safety and artificial intelligence in energy utilization. E-mail: yjjiang@ustc.edu.cn
  • Publish Date: 31 January 2021
    Abstract

  • Abstract

    This paper aims at accurately predict the smoke temperature in a single-room fire. Since both high-fidelity simulations and single-fidelity surrogate models cost much computational time, it is hard to meet the emergency needs of fire safety management. Therefore, a multi-fidelity model named CoKriging was introduced , which made use of the simulation data from Consolidate Fire and Smoke Transport (CFAST) and Fire Dynamic Simulator (FDS) for training. The leave-one-out cross-validation suggests that this model has been effectively trained when the data ratio of CFAST to FDS is 10∶1. Further comparisons among different methods show that the prediction accuracy of CoKriging is comparable to that of artificial neural network (ANN) and Kriging, while the modeling time is only 1/10 of the latter. Additionally, the predicted temperatures of CoKriging are very close to the simulated results of FDS, and once the CoKriging model is successfully constructed, much less time will be taken to make a new prediction than that of FDS. The exploratory research on the proportion of high-and low-fidelity data to the prediction results of CoKriging shows that there is no obvious correlation between them, and the prediction accuracy can still be ensured even if only a small amount of FDS data participates in model testing. In conclusion, the CoKriging model could be used as a fast and effective regression analysis method for the temperature prediction in a single-room fire.

    Abstract

    This paper aims at accurately predict the smoke temperature in a single-room fire. Since both high-fidelity simulations and single-fidelity surrogate models cost much computational time, it is hard to meet the emergency needs of fire safety management. Therefore, a multi-fidelity model named CoKriging was introduced , which made use of the simulation data from Consolidate Fire and Smoke Transport (CFAST) and Fire Dynamic Simulator (FDS) for training. The leave-one-out cross-validation suggests that this model has been effectively trained when the data ratio of CFAST to FDS is 10∶1. Further comparisons among different methods show that the prediction accuracy of CoKriging is comparable to that of artificial neural network (ANN) and Kriging, while the modeling time is only 1/10 of the latter. Additionally, the predicted temperatures of CoKriging are very close to the simulated results of FDS, and once the CoKriging model is successfully constructed, much less time will be taken to make a new prediction than that of FDS. The exploratory research on the proportion of high-and low-fidelity data to the prediction results of CoKriging shows that there is no obvious correlation between them, and the prediction accuracy can still be ensured even if only a small amount of FDS data participates in model testing. In conclusion, the CoKriging model could be used as a fast and effective regression analysis method for the temperature prediction in a single-room fire.
    • FullText(HTML)
  • loading
    • References(36)
  • [1]
    Kajero O T, Chen T, Yao Y, et al. Meta-modeling in chemical process system engineering. Journal of the Taiwan Institute of Chemical Engineers, 2017, 73(6): 135-145.
    [2]
    Worrell C, Luangkesorn L, Haight J, et al. Machine learning of fire hazard model simulations for use in probabilistic safety assessments at Nuclear Power Plants. Reliability Engineering & System Safety, 2019, 183: 128-142.
    [3]
    Al-Janabi S, Al-Shourbaji I, Salman M A. Assessing the suitability of soft computing approaches for forest fires prediction. Applied Computing & Informatics, 2018, 14(2): 214-224.
    [4]
    Demeyer S, Fischer N, Marquis D. Surrogate model based sequential sampling estimation of conformance probability for computationally expensive systems: Application to fire safety science. Journal De La Société Française de Statistique, 2017, 158(1): 111-138.
    [5]
    Li N, Lee E, Cheung S, et al. Multi-fidelity surrogate algorithm for fire origin determination in compartment fires. Engineering with Computers, 2019, 29: 1-18.
    [6]
    Journel A G, Huijbregts C J. Mining Geostatistics. New York: Academic Press, 1978.
    [7]
    Kennedy M C, O'Hagan A. Predicting the Output from a Complex Computer Code When Fast Approximations Are Available. Biometrika, 1998, 87(1): 1-13.
    [8]
    Xiao M Y, Zhang G H, Breitkop F P, et al. Extended CoKriging interpolation method based on multi-fidelity data. Applied Mathematics and Computation, 2018, 323: 120-131.
    [9]
    Giraldo R, Herrera L, Leiva V. CoKriging prediction using as secondary variable a functional random field with application in environmental pollution. Mathematics, 2020, 8(8): 1305.
    [10]
    Pardo E, Chica M, Luque J, et al. Compositional CoKriging for mapping the probability risk of groundwater contamination by nitrates. Science of The Total Environment, 2015, 532: 162-175.
    [11]
    Wang L Q, Dai L J, Li L F, et al. Multivariable CoKriging prediction and source analysis of potentially toxic elements (Cr, Cu, Cd, Pb, and Zn) in surface sediments from Dongting Lake, China. Ecological Indicators, 2018, 94(1): 312-319.
    [12]
    Thelen A S, Leifsson L T, Beran P S. Multifidelity flutter prediction using regression CoKriging with adaptive sampling. Journal of Fluids and Structures, 2020, 97: 103081.
    [13]
    Du X S, Leifsson L. Multifidelity model-assisted probability of detection via CoKriging. NDT & E International, 2019, 108: 102156.
    [14]
    Bae B, Kim H, Lim H, et al. Missing data imputation for traffic flow speed using spatio-temporal CoKriging. Transportation Research Part C: Emerging Technologies, 2018, 88: 124-139.
    [15]
    Emery X. CoKriging random fields with means related by known linear combinations. Computers & Geoscience, 2012, 38(1): 136-144.
    [16]
    Gratiet L L, Garnier J. Recursive CoKriging model for design of computer experiments with multiple levels of fidelity. International Journal for Uncertainty Quantification, 2012, 4(5): 365-386.
    [17]
    Yang X, Barajas-Solano D, Tartakovsky G, et al. Physics-informed CoKriging: A Gaussian-process-regression-based multifidelity method for data-model convergence. Journal of Computational Physics, 2019, 395: 410-431.
    [18]
    Ankenman B E, Nelson B L, Staum J. Stochastic Kriging for simulation metamodeling. Proceedings of the Winter Simulation Conference. Florida: IEEE, 2008: 362-370.
    [19]
    Elsayed K. Optimization of the cyclone separator geometry for minimum pressure drop using CoKriging. Powder Technology, 2015, 269: 409-424.
    [20]
    Stroh R, Bect J, Demeyer S, et al. Assessing fire safety using complex numerical models with a Bayesian multi-fidelity approach. Fire Safety Journal, 2017, 91: 1016-1025.
    [21]
    Zaefferer M, Gaida D, Bartz-Beielstein T. Multi-fidelity modeling and optimization of biogas plants. Applied Soft Computing, 2016, 48: 13-28.
    [22]
    Wang Y M. Research on multi-fidelity simulation methods for wind farm wake and output power. Dissertation, Beijing: North China Electric Power University, 2018.
    [23]
    Steckler K D, Quintiere J G, Rinkinen W J. Flow induced by fire in a compartment. 19th Symposium (International) on Combustion. Netherlands: Elsevier, 1982, 19 (1): 913-920.
    [24]
    Fernández-Godino G, Park C, Kim N H, et al. Review of multi-fidelity models. AIAA Journal, 2019, 57 (5): 2039-2054.
    [25]
    Mcgrattan K, Hostikka S, Mcdernott R, et al. Fire Dynamics Simulator User's Guide. 6ed, National Institute of Standards and Technology (NIST), NIST, https://doi.org/10.6028/NIST.sp.1019.
    [26]
    Peacock R, Reneke P, Forney G.CFAST-Consolidated Model of Fire Growth and Smoke Transport User's Guide. 7ed. [2020-08-27] http://dx.doi.org/10.6028/NIST.TN.1889v2.
    [27]
    Song Y, Cheng Y P, Wang L. Numerical simulation analysis of vent flow in FDS. Fire Science and Technology, 2010, 29(11): 965-968.
    [28]
    Total D J J. Some considerations regarding the use of multi-fidelity Kriging in the construction of surrogate models. Structural and Multidisciplinary Optimization, 2015, 51: 1223-1245
    [29]
    Li Y J. Multivariate Statistical Analysis. Beijing: Beijing University of Posts and Telecommunications Press, 2018: 86.
    [30]
    Buda A , Jarynowsk A. Life time of correlations and its applications.ABRASCO: Associação Brasileira de Saúde Coletiva, 2010: 5-21.
    [31]
    Cohen J. Statistical power analysis for the behavioral sciences. 2ed, Academic Press, 1977: 1-17.
    [32]
    Fang X Y, Chen X J, Feng Y J, et al. Study of spatial distribution for Dosidicus GIGAS abundance off Peru based on a comprehensive environmental factor. Acta Oceanologica Sinica, 2017, 39(02): 62-71.
    [33]
    Bect J, Vazquez E, Stroh R, et al. STK: A small (MATLAB/Octave) toolbox for Kriging. Release 2.4, 2014.
    [34]
    Gratiet L L. Multi-fidelity CoKriging models. version 1.2, 2012.
    [35]
    Roustant O, Ginsbourger D, Deville Y. DiceKriging, DiceOptim: Two R packages for the analysis of computer experiments by Kriging-based metamodeling and optimization. Journal of Statistical Software, 2012, 51(1): 1-55.
    [36]
    Wang Y J. Analysis of correlation coefficient and determination coefficient. Annual Conference of the Cooperative Network of Scientific journals in the Yangtze River Basin and NorthWest China. Xiamen, China: IEEE, 2008.
    • Supplements(0)
    • Related Articles
    • Track Citations
  • 加载中

Catalog

    Get Citation
    PDF
    XML
    [1]
    Kajero O T, Chen T, Yao Y, et al. Meta-modeling in chemical process system engineering. Journal of the Taiwan Institute of Chemical Engineers, 2017, 73(6): 135-145.
    [2]
    Worrell C, Luangkesorn L, Haight J, et al. Machine learning of fire hazard model simulations for use in probabilistic safety assessments at Nuclear Power Plants. Reliability Engineering & System Safety, 2019, 183: 128-142.
    [3]
    Al-Janabi S, Al-Shourbaji I, Salman M A. Assessing the suitability of soft computing approaches for forest fires prediction. Applied Computing & Informatics, 2018, 14(2): 214-224.
    [4]
    Demeyer S, Fischer N, Marquis D. Surrogate model based sequential sampling estimation of conformance probability for computationally expensive systems: Application to fire safety science. Journal De La Société Française de Statistique, 2017, 158(1): 111-138.
    [5]
    Li N, Lee E, Cheung S, et al. Multi-fidelity surrogate algorithm for fire origin determination in compartment fires. Engineering with Computers, 2019, 29: 1-18.
    [6]
    Journel A G, Huijbregts C J. Mining Geostatistics. New York: Academic Press, 1978.
    [7]
    Kennedy M C, O'Hagan A. Predicting the Output from a Complex Computer Code When Fast Approximations Are Available. Biometrika, 1998, 87(1): 1-13.
    [8]
    Xiao M Y, Zhang G H, Breitkop F P, et al. Extended CoKriging interpolation method based on multi-fidelity data. Applied Mathematics and Computation, 2018, 323: 120-131.
    [9]
    Giraldo R, Herrera L, Leiva V. CoKriging prediction using as secondary variable a functional random field with application in environmental pollution. Mathematics, 2020, 8(8): 1305.
    [10]
    Pardo E, Chica M, Luque J, et al. Compositional CoKriging for mapping the probability risk of groundwater contamination by nitrates. Science of The Total Environment, 2015, 532: 162-175.
    [11]
    Wang L Q, Dai L J, Li L F, et al. Multivariable CoKriging prediction and source analysis of potentially toxic elements (Cr, Cu, Cd, Pb, and Zn) in surface sediments from Dongting Lake, China. Ecological Indicators, 2018, 94(1): 312-319.
    [12]
    Thelen A S, Leifsson L T, Beran P S. Multifidelity flutter prediction using regression CoKriging with adaptive sampling. Journal of Fluids and Structures, 2020, 97: 103081.
    [13]
    Du X S, Leifsson L. Multifidelity model-assisted probability of detection via CoKriging. NDT & E International, 2019, 108: 102156.
    [14]
    Bae B, Kim H, Lim H, et al. Missing data imputation for traffic flow speed using spatio-temporal CoKriging. Transportation Research Part C: Emerging Technologies, 2018, 88: 124-139.
    [15]
    Emery X. CoKriging random fields with means related by known linear combinations. Computers & Geoscience, 2012, 38(1): 136-144.
    [16]
    Gratiet L L, Garnier J. Recursive CoKriging model for design of computer experiments with multiple levels of fidelity. International Journal for Uncertainty Quantification, 2012, 4(5): 365-386.
    [17]
    Yang X, Barajas-Solano D, Tartakovsky G, et al. Physics-informed CoKriging: A Gaussian-process-regression-based multifidelity method for data-model convergence. Journal of Computational Physics, 2019, 395: 410-431.
    [18]
    Ankenman B E, Nelson B L, Staum J. Stochastic Kriging for simulation metamodeling. Proceedings of the Winter Simulation Conference. Florida: IEEE, 2008: 362-370.
    [19]
    Elsayed K. Optimization of the cyclone separator geometry for minimum pressure drop using CoKriging. Powder Technology, 2015, 269: 409-424.
    [20]
    Stroh R, Bect J, Demeyer S, et al. Assessing fire safety using complex numerical models with a Bayesian multi-fidelity approach. Fire Safety Journal, 2017, 91: 1016-1025.
    [21]
    Zaefferer M, Gaida D, Bartz-Beielstein T. Multi-fidelity modeling and optimization of biogas plants. Applied Soft Computing, 2016, 48: 13-28.
    [22]
    Wang Y M. Research on multi-fidelity simulation methods for wind farm wake and output power. Dissertation, Beijing: North China Electric Power University, 2018.
    [23]
    Steckler K D, Quintiere J G, Rinkinen W J. Flow induced by fire in a compartment. 19th Symposium (International) on Combustion. Netherlands: Elsevier, 1982, 19 (1): 913-920.
    [24]
    Fernández-Godino G, Park C, Kim N H, et al. Review of multi-fidelity models. AIAA Journal, 2019, 57 (5): 2039-2054.
    [25]
    Mcgrattan K, Hostikka S, Mcdernott R, et al. Fire Dynamics Simulator User's Guide. 6ed, National Institute of Standards and Technology (NIST), NIST, https://doi.org/10.6028/NIST.sp.1019.
    [26]
    Peacock R, Reneke P, Forney G.CFAST-Consolidated Model of Fire Growth and Smoke Transport User's Guide. 7ed. [2020-08-27] http://dx.doi.org/10.6028/NIST.TN.1889v2.
    [27]
    Song Y, Cheng Y P, Wang L. Numerical simulation analysis of vent flow in FDS. Fire Science and Technology, 2010, 29(11): 965-968.
    [28]
    Total D J J. Some considerations regarding the use of multi-fidelity Kriging in the construction of surrogate models. Structural and Multidisciplinary Optimization, 2015, 51: 1223-1245
    [29]
    Li Y J. Multivariate Statistical Analysis. Beijing: Beijing University of Posts and Telecommunications Press, 2018: 86.
    [30]
    Buda A , Jarynowsk A. Life time of correlations and its applications.ABRASCO: Associação Brasileira de Saúde Coletiva, 2010: 5-21.
    [31]
    Cohen J. Statistical power analysis for the behavioral sciences. 2ed, Academic Press, 1977: 1-17.
    [32]
    Fang X Y, Chen X J, Feng Y J, et al. Study of spatial distribution for Dosidicus GIGAS abundance off Peru based on a comprehensive environmental factor. Acta Oceanologica Sinica, 2017, 39(02): 62-71.
    [33]
    Bect J, Vazquez E, Stroh R, et al. STK: A small (MATLAB/Octave) toolbox for Kriging. Release 2.4, 2014.
    [34]
    Gratiet L L. Multi-fidelity CoKriging models. version 1.2, 2012.
    [35]
    Roustant O, Ginsbourger D, Deville Y. DiceKriging, DiceOptim: Two R packages for the analysis of computer experiments by Kriging-based metamodeling and optimization. Journal of Statistical Software, 2012, 51(1): 1-55.
    [36]
    Wang Y J. Analysis of correlation coefficient and determination coefficient. Annual Conference of the Cooperative Network of Scientific journals in the Yangtze River Basin and NorthWest China. Xiamen, China: IEEE, 2008.
    Recommended articles
    TrendMD
    Volume 51 Issue 1 page: 75-86
    Cover

    Article Metrics

    Article views (376) PDF downloads(571)
    Proportional views

    Copyright © Editorial Office of JUSTC, All Rights Reserved. 皖ICP备05002528号

    Supported by: Beijing Renhe Information Technology Co. Ltd    

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return