Global Sensitivity Analysis Methodology for Construction Simulation Models: Multiple Linear Regressions versus Multilayer Perceptions
Publication: Journal of Construction Engineering and Management
Volume 150, Issue 5
Abstract
In this research, the multilayer perceptron (MLP), also known as error backpropagation neural networks, is made transparent and explainable by contrasting with the commonly applied multiple linear regression (MLR). A novel MLP-based method for performing global sensitivity analysis is formalized to tackle complicated, nonexplainable simulation models or artificial intelligence (AI) models, which were developed to support critical decisions in construction engineering. The sensitivity analysis results serve as further evidence to validate the decision support models and lend new insights into the problems under investigation. The proposed new method was applied in two case studies in construction engineering, they are: precast viaduct installation cycles and concrete strength development. In both applications, the results of sensitivity analysis were represented in straightforward forms and effectively cross-checked with the existing knowledge of the problem domain or the experiences of construction practitioners.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
The authors confirm that the data supporting the findings of the first case study is included in the appendix. Data used in the second case study is sourced from the University of California, Irvine open data repository (Yeh 2007) and is available at: https://doi.org/10.24432/C5PK67. Models, or code that support the findings of this study are available from the corresponding author upon reasonable request.
Acknowledgments
The presented research was funded by National Science and Engineering Research Council (NSERC) of Canada (Grant No. NSERC RGPIN-2023-04398 Lu).
References
Alipour, A., K. Jafarzadegan, and H. Moradkhani. 2022. “Global sensitivity analysis in hydrodynamic modeling and flood inundation mapping.” Environ. Modell. Software 152 (Jun): 105398. https://doi.org/10.1016/j.envsoft.2022.105398.
Alsmadi, M. K., K. B. Omar, S. A. Noah, and I. Almarashdah. 2009. “Performance comparison of multi-layer perceptron (back propagation, delta rule and perceptron) algorithms in neural networks.” In Proc., 2009 IEEE Int. Advance Computing Conf., IACC 2009, 296–299. New York: IEEE.
Aruntaş, H. Y., S. Cemalgil, O. Şimşek, G. Durmuş, and M. Erdal. 2008. “Effects of super plasticizer and curing conditions on properties of concrete with and without fiber.” Mater. Lett. 62 (19): 3441–3443. https://doi.org/10.1016/j.matlet.2008.02.064.
Berry, W. D., W. D. Berry, S. Feldman, and D. Stanley Feldman. 1985. Multiple regression in practice, 7–50. Newbury Park, CA: SAGE.
Boger, Z., and H. Guterman. 1997. “Knowledge extraction from artificial neural networks models.” In Vol. 4 of Proc., IEEE Int. Conf. on Systems, Man and Cybernetics, 3030–3035. New York: IEEE.
Borgonovo, E., and E. Plischke. 2016. “Sensitivity analysis: A review of recent advances.” Eur. J. Oper. Res. 248 (3): 869–887. https://doi.org/10.1016/j.ejor.2015.06.032.
Chan, W. H., and M. Lu. 2008. “Materials handling system simulation in precast viaduct construction: Modeling, analysis, and implementation.” J. Constr. Eng. Manage. 134 (4): 300–310. https://doi.org/10.1061/(ASCE)0733-9364(2008)134:4(300).
Cheng, K., Z. Lu, Y. Zhou, Y. Shi, and Y. Wei. 2017. “Global sensitivity analysis using support vector regression.” Appl. Math. Modell. 49 (Sep): 587–598. https://doi.org/10.1016/j.apm.2017.05.026.
Chiappini, F. A., F. Allegrini, H. C. Goicoechea, and A. C. Olivieri. 2020. “Sensitivity for multivariate calibration based on multilayer perceptron artificial neural networks.” Anal. Chem. 92 (18): 12265–12272. https://doi.org/10.1021/acs.analchem.0c01863.
Da Silva, I. N., D. H. Spatti, R. A. Flauzino, L. H. B. Liboni, and S. F. dos Reis Alves. 2016. Artificial neural networks: A practical course, 1–307. Cham, Switzerland: Springer.
Dong, M., Y. Li, D. Song, J. Yang, M. Su, X. Deng, L. Huang, M. H. Elkholy, and Y. H. Joo. 2021. “Uncertainty and global sensitivity analysis of levelized cost of energy in wind power generation.” Energy Convers. Manage. 229 (Feb): 113781. https://doi.org/10.1016/j.enconman.2020.113781.
Ebrahimy, Y., S. M. AbouRizk, S. Fernando, and Y. Mohamed. 2011. “Simulation modeling and sensitivity analysis of a tunneling construction project’s supply chain.” Eng. Constr. Archit. Manage. 18 (5): 462–480. https://doi.org/10.1108/09699981011074600.
Gardner, M. W., and S. R. Dorling. 1998. “Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences.” Atmos. Environ. 32 (14–15): 2627–2636. https://doi.org/10.1016/S1352-2310(97)00447-0.
Goodarzizad, P., E. Mohammadi Golafshani, and M. Arashpour. 2023. “Predicting the construction labour productivity using artificial neural network and grasshopper optimisation algorithm.” Int. J. Construct. Manage. 23 (5): 763–779. https://doi.org/10.1080/15623599.2021.1927363.
Hamby, D. M. 1994. “A review of techniques for parameter sensitivity analysis of environmental models.” Environ. Monit. Assess. 32 (Sep): 135–154. https://doi.org/10.1007/BF00547132.
Hashemi, M., P. Shafigh, M. R. B. Karim, and C. D. Atis. 2018. “The effect of course to fine aggregate ratio on the fresh and hardened properties of roller-compacted concrete pavement.” Constr. Build. Mater. 169 (Apr): 553–566. https://doi.org/10.1016/j.conbuildmat.2018.02.216.
Hover, K. C. 2011. “The influence of water on the performance of concrete.” Constr. Build. Mater. 25 (7): 3003–3013. https://doi.org/10.1016/j.conbuildmat.2011.01.010.
Hu, D., and Y. Mohamed. 2014. “A dynamic programming solution to automate fabrication sequencing of industrial construction components.” Autom. Constr. 40 (Apr): 9–20. https://doi.org/10.1016/j.autcon.2013.12.013.
Iooss, B., and P. Lemaître. 2015. “A review on global sensitivity analysis methods.” In Uncertainty management in simulation-optimization of complex systems: Algorithms and applications, 101–122. Boston: Springer.
Jobson, J. D. 1991. “Multiple linear regression.” In Applied multivariate data analysis, 219–398. New York: Springer.
Kala, Z. 2019. “Global sensitivity analysis of reliability of structural bridge system.” Eng. Struct. 194 (Sep): 36–45. https://doi.org/10.1016/j.engstruct.2019.05.045.
Lagaros, N. D. 2023. “Artificial neural networks applied in civil engineering.” Appl. Sci. 13 (2): 1131. https://doi.org/10.3390/app13021131.
Lu, M., D. S. Yeung, and W. W. Y. Ng. 2006. “Applying undistorted neural network sensitivity analysis in iris plant classification and construction productivity prediction.” Soft Comput. 10 (1): 68–77. https://doi.org/10.1007/s00500-005-0469-9.
Minderer, M., J. Djolonga, R. Romijnders, F. Hubis, X. Zhai, N. Houlsby, D. Tran, and M. Lucic. 2021. “Revisiting the calibration of modern neural networks.” In Vol. 34 of Proc., Advances in Neural Information Processing Systems, 15682–15694. San Diego: Neural Information Processing Systems Foundation.
Mohsenijam, A., M. F. F. Siu, and M. Lu. 2016. “Modified stepwise regression approach to streamlining predictive analytics for construction engineering applications.” J. Comput. Civ. Eng. 31 (3): 04016066. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000636.
Montevechi, J. A. B., R. D. C. Miranda, and J. D. Friend. 2012. “Sensitivity analysis in discrete-event simulation using design of experiments.” In Discrete event simulations—Development and applications, edited by E. W. C. Lim, 63–102. London: IntechOpen.
Nance, R. E. 1996. “A history of discrete event simulation programming languages.” In Proc., 2nd ACM SIGPLAN Conf. on History of Programming Languages (HOPL-II), 149–175. New York: Association for Computing Machinery.
Ni, F., M. Nijhuis, P. H. Nguyen, and J. F. G. Cobben. 2018. “Variance-based global sensitivity analysis for power systems.” IEEE Trans. Power Syst. 33 (2): 1670–1682. https://doi.org/10.1109/TPWRS.2017.2719046.
Oner, A., S. Akyuz, and R. Yildiz. 2005. “An experimental study on strength development of concrete containing fly ash and optimum usage of fly ash in concrete.” Cem. Concr. Res. 35 (6): 1165–1171. https://doi.org/10.1016/j.cemconres.2004.09.031.
Pandis, N. 2016. “Multiple linear regression analysis.” Am. J. Orthodontics Dentofacial Orthopedics 149 (4): 581. https://doi.org/10.1016/j.ajodo.2016.01.012.
Pidd, M. 1998. Computer simulation in management science. New York: Wiley.
Qin, Y., Z. Wang, C. Xiang, M. Dong, C. Hu, and R. Wang. 2019. “A novel global sensitivity analysis on the observation accuracy of the coupled vehicle model.” Veh. Syst. Dyn. 57 (10): 1445–1466. https://doi.org/10.1080/00423114.2018.1517219.
Rafiq, M. Y., G. Bugmann, and D. J. Easterbrook. 2001. “Neural network design for engineering applications.” Comput. Struct. 79 (17): 1541–1552. https://doi.org/10.1016/S0045-7949(01)00039-6.
Savage, J., F. Pianosi, P. Bates, J. Freer, and T. Wagener. 2016. “Quantifying the importance of spatial resolution and other factors through global sensitivity analysis of a flood inundation model.” Water Resour. Res. 52 (11): 9146–9163. https://doi.org/10.1002/2015WR018198.
Wang, S. Q., and D. W. Halpin. 2004. “Simulation experiment for improving construction processes.” In Proc., 2004 Winter Simulation Conf., 1252–1259. New York: IEEE. https://doi.org/10.1109/WSC.2004.1371457.
Yan, X., and X. Su. 2009. Linear regression analysis: Theory and computing. Singapore: World Scientific.
Yeh, I.-C. 2007. “Concrete compressive strength.” UCI Machine Learning Repository. Accessed August 2, 2007. https://archive.ics.uci.edu/dataset/165/concrete+compressive+strength.
Yi, C., and M. Lu. 2019. “Mixed-integer linear programming–based sensitivity analysis in optimization of temporary haul road layout design for earthmoving operations.” J. Comput. Civ. Eng. 33 (3): 04019021. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000838.
Information & Authors
Information
Published In
Journal of Construction Engineering and Management
Volume 150 • Issue 5 • May 2024
Copyright
© 2024 American Society of Civil Engineers.
History
Received: May 24, 2023
Accepted: Jan 2, 2024
Published online: Mar 11, 2024
Published in print: May 1, 2024
Discussion open until: Aug 11, 2024
ASCE Technical Topics:
- Analysis (by type)
- Artificial intelligence and machine learning
- Computer programming
- Computing in civil engineering
- Construction engineering
- Construction methods
- Engineering fundamentals
- Linear analysis
- Models (by type)
- Regression analysis
- Sensitivity analysis
- Simulation models
- Statistical analysis (by type)
- Structural analysis
- Structural engineering
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.