CLEMSON: An Automated Machine-Learning Virtual Assistant for Accelerated, Simulation-Free, Transparent, Reduced-Order, and Inference-Based Reconstruction of Fire Response of Structural Members
Publication: Journal of Structural Engineering
Volume 148, Issue 9
Abstract
This paper introduces CLEMSON, an automated machine-learning (AutoML) virtual assistant (VA) that enables engineers to carry acCeLErated, siMulation-free, tranSparent, reduced-Order, and infereNce-based fire resistance analysis with ease. This VA learns from physical observations taken from real fire tests to bypass bottlenecks and ab initio calculations associated with traditional structural fire engineering methods. CLEMSON leverages a competitive ML algorithm search to identify those most suited for a given problem and then blend them into a cohesive ensemble to realize faster and reduced-order assimilation of predictions, thereby attaining higher accuracy and reliability. In addition, this VA is designed to be transparent and hence is supplemented with explainability measures to allow users to identify key factors driving its rationale and predictions. Once fully realized, CLEMSON augments its inner workings into a graphical user interface that can be used in a coding-free manner and with enriched visualization tools to allow users to directly harness the power of ML without the need for special software. To showcase the merit of the proposed VA, CLEMSON is applied to assess classification and regression problems by means of evaluating fire resistance rating, as well as temperature rise history and deformation history of concrete-filled steel tubular (CFST) columns via five algorithms, namely: extreme gradient boosted trees, light gradient boosted trees, neural networks, random forest, and TensorFlow. Finally, this work also introduces three new and functional performance metrics that are explicitly derived for structural fire engineering applications and hence can be used to cross-check the validity of ML models.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or code that support the findings of this study are available from the corresponding author upon reasonable request.
Acknowledgments
The author would like to thank the Editor and Reviewers for their support of this work and constructive comments that enhanced the quality of this manuscript.
References
Abadi, M. 2016. “TensorFlow: Learning functions at scale.” In Proc., 21st ACM SIGPLAN Int. Conf. on Functional Programming. New York: Springer.
Abdollahi-Arpanahi, R., D. Gianola, and F. Peñagaricano. 2020. “Deep learning versus parametric and ensemble methods for genomic prediction of complex phenotypes.” Genet. Sel. Evol. 52 (1): 1–15. https://doi.org/10.1186/s12711-020-00531-z.
ACI (American Concrete Institute). 2021. “The concrete industry in the era of artificial intelligence.” Accessed May 18, 2021. https://www.concrete.org/news/newsdetail.aspx?f=51732604.
Altmann, A., L. Toloşi, O. Sander, and T. Lengauer. 2010. “Permutation importance: A corrected feature importance measure.” Bioinformatics 26 (10): 1340–1347. https://doi.org/10.1093/bioinformatics/btq134.
Bishop, C. M. 2007. Pattern recognition and machine learning: Information science and statistics, edited by M. I. Jordan, Robert Nowak, and Bernhard Schoelkopf, 738. New York: Springer.
Boehmke, B., B. Greenwell, B. Boehmke, and B. Greenwell. 2020. “Interpretable machine learning.” In Hands-on machine learning with R. London: Chapman & Hall.
Botchkarev, A. 2019. “A new typology design of performance metrics to measure errors in machine learning regression algorithms.” Interdiscip. J. Inf. Knowl. Manage. 14 (Jan): 45–76. https://doi.org/10.28945/4184.
Botu, V., and R. Ramprasad. 2015. “Adaptive machine learning framework to accelerate ab initio molecular dynamics.” Int. J. Quantum Chem. 115 (16): 1074–1083. https://doi.org/10.1002/qua.24836.
Buchanan, A., and A. Abu. 2017. Structural design for fire safety. Chichester, UK: Wiley.
Chaudhary, R. K., R. Van Coile, and T. Gernay. 2021. “Potential of surrogate modelling for probabilistic fire analysis of structures.” Fire Technol. 57 (6): 3151–3177. https://doi.org/10.1007/s10694-021-01126-w.
Chou, J. S., and A. D. Pham. 2013. “Enhanced artificial intelligence for ensemble approach to predicting high performance concrete compressive strength.” Constr. Build. Mater. 49 (Dec): 554–563. https://doi.org/10.1016/j.conbuildmat.2013.08.078.
Cremonesi, P., Y. Koren, and R. Turrin. 2010. “Performance of recommender algorithms on top-N recommendation tasks categories and subject descriptors.” In Proc., 4th ACM Conf. on Recommender Systems, 39–46. New York: Association for Computing Machinery.
Cuevas-Zuviría, B., and L. F. Pacios. 2020. “Analytical model of electron density and its machine learning inference.” J. Chem. Inf. Model. 60 (8): 3831–3842. https://doi.org/10.1021/acs.jcim.0c00197.
Doran, D., S. Schulz, and T. R. Besold. 2018. “What does explainable AI really mean? A new conceptualization of perspectives.” In Proc., CEUR Workshop. Ithaca, NY: Cornell Univ.
Dosilovic, F. K., M. Brcic, and N. Hlupic. 2018. “Explainable artificial intelligence: A survey.” In Proc., 2018 41st Int. Convention on Information and Communication Technology, Electronics and Microelectronics, MIPRO 2018. New York: IEEE.
Dudley, J. J., and P. O. Kristensson. 2018. “A review of user interface design for interactive machine learning.” ACM Trans. Interact. Intell. Syst. 8 (2): 1–37. https://doi.org/10.1145/3185517.
Freund, Y., and R. E. Schapire. 1996. “Experiments with a new boosting algorithm.” In Proc., 13th Int. Conf. on Machine Learning. San Francisco: Morgan Kaufmann Publishers.
Freund, Y., and R. E. Schapire. 1997. “A decision-theoretic generalization of on-line learning and an application to boosting.” J. Comput. Syst. Sci. 55 (1): 119–139. https://doi.org/10.1006/jcss.1997.1504.
Friedman, J. H. 2001. “Greedy function approximation: A gradient boosting machine.” Ann. Stat. 29 (5): 1189–1232. https://doi.org/10.1214/aos/1013203451.
Fu, F. 2020. “Fire induced progressive collapse potential assessment of steel framed buildings using machine learning.” J. Constr. Steel Res. 166 (Mar): 105918. https://doi.org/10.1016/j.jcsr.2019.105918.
García-Martín, E., C. F. Rodrigues, G. Riley, and H. Grahn. 2019. “Estimation of energy consumption in machine learning.” J. Parallel Distrib. Comput. 134 (Dec): 75–88. https://doi.org/10.1016/j.jpdc.2019.07.007.
Hamori, S., M. Kawai, T. Kume, Y. Murakami, and C. Watanabe. 2018. “Ensemble learning or deep learning? Application to default risk analysis.” J. Risk Finance Manage. 11 (1): 12. https://doi.org/10.3390/jrfm11010012.
Han, J., Y. Dong, and Z. Xu. 2009. “Study on fire-resistance performance of reinforced concrete filled steel tubular columns.” Supplement, J. Build. Struct. 30 (S2): 265–270.
Han, L., X. Zhao, Y. Yang, and J. Feng. 2003. “Experimental study and calculation of fire resistance of concrete-filled hollow steel columns.” J. Struct. Eng. 129 (3): 346–356. https://doi.org/10.1061/(ASCE)0733-9445(2003)129:3(346).
Han, L. H., F. Chen, F. Y. Liao, Z. Tao, and B. Uy. 2013. “Fire performance of concrete filled stainless steel tubular columns.” Eng. Struct. 56 (Nov): 165–181. https://doi.org/10.1016/j.engstruct.2013.05.005.
Hastie, T., R. Tibshirani, and J. Friedman. 2011. “The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Second Edition (Springer Series in Statistics) (9780387848570): Trevor Hastie, Robert Tibshirani, Jerome Friedman: Books.” In The elements of statistical learning: Data mining, inference, and prediction. New York: Springer.
Hindman, M. 2015. “Building better models: Prediction, replication, and machine learning in the social sciences.” Ann. Am. Acad. Political Soc. Sci. 659 (1): 48–62. https://doi.org/10.1177/0002716215570279.
Jackson, R. 2019. A roadmap to reducing greenhouse gas emissions 50 percent by 2030. Stanford, CA: Stanford Woods Institute for the Environment.
Jiang, L., Y. Jiang, Z. Zhang, and A. Usmani. 2021. “Thermal analysis infrastructure in OpenSees for fire and its smart application interface towards natural fire modeling.” Fire Technol. 57 (6): 2955–2980. https://doi.org/10.1007/s10694-020-01071-0.
Keras. 2020. “GitHub—keras-team/keras: Deep learning for humans.” Accessed February 9, 2021. https://github.com/keras-team/keras.
Ketkar, N., and N. Ketkar. 2017. “Introduction to Keras.” In Deep learning with Python. Berkeley, CA: Apress.
Kodur, V., S. M. Alogla, and S. Venkatachari. 2021. “Guidance for treatment of high-temperature creep in fire resistance analysis of concrete structures.” Fire Technol. 57 (3): 1167–1197. https://doi.org/10.1007/s10694-020-01039-0.
Kodur, V., and M. Z. Naser. 2020. Structural fire engineering. New York: McGraw Hill Professional.
Laszczyk, M., and P. B. Myszkowski. 2019. “Survey of quality measures for multi-objective optimization: Construction of complementary set of multi-objective quality measures.” Swarm Evol. Comput. 48 (Aug): 109–133. https://doi.org/10.1016/j.swevo.2019.04.001.
Li, H., Z. Xu, G. Taylor, C. Studer, and T. Goldstein. 2018. “Visualizing the loss landscape of neural nets.” Proc., 32nd Conf. on Neural Information Processing Systems (NeurIPS 2018). Red Hook, NY: Curran Associates.
Liaw, A., and M. Wiener. 2002. “Classification and regression by RandomForest.” R News 2 (3): 18–22.
Lie, T. T., and M. Chabot. 1992. Experimental studies on the fire resistance of hollow steel columns filled with plain concrete. Ottawa: National Research Council Canada.
LightGBM. 2020. “Welcome to LightGBM’s documentation!—LightGBM 3.1.1.99 documentation.” Accessed February 9, 2021. https://lightgbm.readthedocs.io/en/latest/.
Litman, T. 2014. “Autonomous vehicle implementation predictions: Implications for transport planning.” In Proc., Transportation Research Board Annual Meeting. Victoria, BC, Canada: Victoria Transport Policy Institute.
Lu, H., X. L. Zhao, and L. H. Han. 2009. “Fire behaviour of high strength self-consolidating concrete filled steel tubular stub columns.” J. Constr. Steel Res. 65 (10–11): 1995–2010. https://doi.org/10.1016/j.jcsr.2009.06.013.
McNamee, M., et al. 2019. “IAFSS agenda 2030 for a fire safe world.” Fire Saf. J. 110 (Dec): 102889. https://doi.org/10.1016/j.firesaf.2019.102889.
Naser, M. Z. 2019a. “AI-based cognitive framework for evaluating response of concrete structures in extreme conditions.” Eng. Appl. Artif. Intell. 81 (May): 437–449. https://doi.org/10.1016/j.engappai.2019.03.004.
Naser, M. Z. 2019b. “Fire resistance evaluation through artificial intelligence: A case for timber structures.” Fire Saf. J. 105 (Apr): 1–18. https://doi.org/10.1016/j.firesaf.2019.02.002.
Naser, M. Z. 2021a. “An engineer’s guide to eXplainable artificial intelligence and interpretable machine learning: Navigating causality, forced goodness, and the false perception of inference.” Autom. Constr. 129 (Sep): 103821. https://doi.org/10.1016/j.autcon.2021.103821.
Naser, M. Z. 2021b. “Mechanistically informed machine learning and artificial intelligence in fire engineering and sciences.” Fire Technol. 57 (6): 2741–2784. https://doi.org/10.1007/s10694-020-01069-8.
Naser, M. Z., and A. Alavi. 2020. “Insights into performance fitness and error metrics for machine learning.” Preprint, submitted May 19, 2020. http://arxiv.org/abs/2006.00887.
Ouache, R., K. M. Nahiduzzaman, K. Hewage, and R. Sadiq. 2021. “Performance investigation of fire protection and intervention strategies: Artificial neural network-based assessment framework.” J. Build. Eng. 42 (Oct): 102439. https://doi.org/10.1016/j.jobe.2021.102439.
Panev, Y., P. Kotsovinos, S. Deeny, and G. Flint. 2021. “The use of machine learning for the prediction of fire resistance of composite shallow floor systems.” Fire Technol. 57 (6): 3079–3100. https://doi.org/10.1007/s10694-021-01108-y.
Peskova, K., and R. Neruda. 2019. “Hyperparameters search methods for machine learning linear workflows.” In Proc., 18th IEEE Int. Conf. on Machine Learning and Applications, ICMLA 2019. New York: IEEE.
Polikar, R. 2009. “Ensemble learning.” Scholarpedia 4 (1): 2776. https://doi.org/10.4249/scholarpedia.2776.
Schmidhuber, J. 2015. “Deep learning in neural networks: An overview.” Neural Networks 61 (Jan): 85–117. https://doi.org/10.1016/j.neunet.2014.09.003.
Schmidt, M. D., and H. Lipson. 2010. “Age-fitness pareto optimization.” In Genetic programming theory and practice VIII, 129–146. New York: Springer.
Scikit. 2020a. “sklearn.ensemble.GradientBoostingRegressor: scikit-learn 0.24.1 documentation.” Accessed February 9, 2021. https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.GradientBoostingRegressor.html.
Scikit. 2020b. “sklearn.ensemble.RandomForestClassifier: scikit-learn 0.24.1 documentation.” Accessed February 9, 2021. https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.RandomForestClassifier.html.
Scikit. 2021. “4.1. Partial Dependence and Individual Conditional Expectation plots: scikit-learn 0.24.1 documentation.” Accessed February 9, 2021. https://scikit-learn.org/stable/modules/partial_dependence.html.
Strubell, E., A. Ganesh, and A. McCallum. 2020. “Energy and policy considerations for modern deep learning research.” In Proc., AAAI Conf. on Artificial Intelligence. Menlo Park, CA: Association for the Advancement of Artificial Intelligence.
Su, L., X. Wu, X. Zhang, and X. Huang. 2021. “Smart performance-based design for building fire safety: Prediction of smoke motion via AI.” J. Build. Eng. 43 (Nov): 102529. https://doi.org/10.1016/j.jobe.2021.102529.
Tanveer, M., T. Rajani, R. Rastogi, Y. H. Shao, M. A. Ganaie. 2022. “Comprehensive review on twin support vector machines.” Ann. Oper. Res. https://doi.org/10.1007/s10479-022-04575-w.
Tarassoli, S. P. 2019. “Artificial intelligence, regenerative surgery, robotics? What is realistic for the future of surgery?” Ann. Med. Surg. 41 (May): 53–55. https://doi.org/10.1016/j.amsu.2019.04.001.
TensorFlow. 2020. “GitHub: Tensorflow/tensorflow: An open source machine learning framework for everyone.” Accessed February 9, 2021. https://github.com/tensorflow/tensorflow.
Wan, C. Y., X. X. Zha, and J. B. M. Dassekpo. 2017. “Analysis of axially loaded concrete filled circular hollow double steel tubular columns exposed to fire.” Fire Saf. J. 88 (Mar): 1–12. https://doi.org/10.1016/j.firesaf.2016.12.007.
Witten, I. H., E. Frank, M. A. Hall, and C. J. Pal. 2016. Data mining: Practical machine learning tools and techniques. San Diego: Elsevier.
Wolpert, D. H., and W. G. Macready. 1997. “No free lunch theorems for optimization.” IEEE Trans. Evol. Comput. 1 (1): 67–82. https://doi.org/10.1109/4235.585893.
Wu, C. J., et al. 2019. “Machine learning at Facebook: Understanding inference at the edge.” In Proc., 25th IEEE Int. Symp. on High Performance Computer Architecture, HPCA 2019. New York: IEEE.
Wu, X., X. Zhang, X. Huang, F. Xiao, and A. Usmani. 2021. “A real-time forecast of tunnel fire based on numerical database and artificial intelligence.” In Vol. 15 of Building simulation, 511–524. Beijing: Tsinghua University Press.
XGBoost Python Package. 2020. “Python package introduction: XGBoost 1.4.0-SNAPSHOT documentation.” Accessed February 10, 2021. https://xgboost.readthedocs.io/en/latest/python/python_intro.html#early-stopping.
Information & Authors
Information
Published In
Journal of Structural Engineering
Volume 148 • Issue 9 • September 2022
Copyright
© 2022 American Society of Civil Engineers.
History
Received: May 19, 2021
Accepted: Mar 16, 2022
Published online: Jun 27, 2022
Published in print: Sep 1, 2022
Discussion open until: Nov 27, 2022
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.
Cited by
- M.Z. Naser, Machine learning for all! Benchmarking automated, explainable, and coding-free platforms on civil and environmental engineering problems, Journal of Infrastructure Intelligence and Resilience, 10.1016/j.iintel.2023.100028, 2, 1, (100028), (2023).