Abstract
Explosive spalling is a major concern to ultra-high-performance concrete at elevated temperatures. Previous physics-based numerical models for predicting explosive spalling of concrete are not validated sufficiently and still impractical for industrial applications. In this work, six machine learning models are developed to assess the thermal spalling risk of UHPC with hybrid polypropylene fibers and steel fibers, as well as to determine the minimal dosage of fibers required to eliminate spalling. Among the six models, five models are based on artificial neural network, support vector machine, decision tree, random forest, and extreme gradient boosting, respectively. Furthermore, a voting ensemble model is proposed based on the five individual machine learning models. To test the effectiveness of these six machine learning models, 36 groups of heating tests are conducted on hybrid fiber-reinforced UHPC specimens. The results show that among the six models, the XGBoost model shows the best performance with an accuracy of 97.2% and F1 score of 0.933. Parametric analyses are performed using the XGBoost model to study the influences of various parameters on the minimal dosage of fibers to prevent spalling. According to the analysis, PP fibers play a primary role in preventing explosive spalling of UHPC, and limiting the silica fume content reduces the minimal PP fiber dosage for spalling prevention. As the silica fume/binder ratio decreases from 0.25 to 0.05, the minimal PP fiber dosage decreases from 3.5 to 0.5 kg/m3.
Similar content being viewed by others
References
Pistol K, Weise F, Meng B, Schneider U (eds) (2011) The mode of action of polypropylene fibres in high performance concrete at high temperatures. In: 2nd international RILEM workshop on concrete spalling due to fire exposure; 2011: RILEM Publications SARL
Ozawa M, Morimoto H (2014) Effects of various fibres on high-temperature spalling in high-performance concrete. Constr Build Mater 71:83–92
Bangi MR, Horiguchi T (2011) Pore pressure development in hybrid fibre-reinforced high strength concrete at elevated temperatures. Cem Concr Res 41(11):1150–1156
CEN (2004) Eurocode 2: design of concrete structures—part 1–2: general rules—structural fire design. London
Gawin D, Pesavento F, Castells AG (2018) On reliable predicting risk and nature of thermal spalling in heated concrete. Arch Civ Mech Eng 18(4):1219–1227
Mazzucco G, Majorana C, Salomoni V (2015) Numerical simulation of polypropylene fibres in concrete materials under fire conditions. Comput Struct 154:17–28
Liu J-C, Zhang Y (2019) A simplified model to predict thermo-hygral behaviour and explosive spalling of concrete. J Adv Concr Technol 17(7):419–433
Zhang H, Davie C (2013) A numerical investigation of the influence of pore pressures and thermally induced stresses for spalling of concrete exposed to elevated temperatures. Fire Saf J 59:102–110
Iwama K, Higuchi K, Maekawa K (2020) Thermo-mechanistic multi-scale modeling of structural concrete at high temperature. J Adv Concr Technol 18(5):272–293
Yao Y, Guo H, Tan K (2020) An elastoplastic damage constitutive model of concrete considering the effects of dehydration and pore pressure at high temperatures. Mater Struct 53(1):19
Taffese WZ, Sistonen E (2017) Machine learning for durability and service-life assessment of reinforced concrete structures: recent advances and future directions. Autom Constr 77:1–14
Cha YJ, Choi W, Büyüköztürk O (2017) Deep learning-based crack damage detection using convolutional neural networks. Comput Aided Civ Infrastruct Eng 32(5):361–378
Almustafa M, Nehdi M (2020) Machine learning model for predicting structural response of RC slabs exposed to blast loading. Eng Struct 221:111109
Mangalathu S, Jeon J-S (2019) Machine learning-based failure mode recognition of circular reinforced concrete bridge columns: comparative study. J Struct Eng 145(10):04019104
Rafiei MH, Adeli H (2018) A novel unsupervised deep learning model for global and local health condition assessment of structures. Eng Struct 156:598–607
Naser M (2019) Heuristic machine cognition to predict fire-induced spalling and fire resistance of concrete structures. Autom Constr 106:102916
Cook R, Lapeyre J, Ma H, Kumar A (2019) Prediction of compressive strength of concrete: critical comparison of performance of a hybrid machine learning model with standalone models. J Mater Civ Eng 31(11):04019255
Ahmadi M, Naderpour H, Kheyroddin A (2017) ANN model for predicting the compressive strength of circular steel-confined concrete. Int J Civ Eng 15(2):213–221
Seitllari A, Naser M (2019) Leveraging artificial intelligence to assess explosive spalling in fire-exposed RC columns. Comput Concr 24:271–282
Liu J-C, Zhang Z (2020) A machine learning approach to predict explosive spalling of heated concrete. Arch Civ Mech Eng 20(4):134. https://doi.org/10.1007/s43452-020-00135-w
Chen T, Guestrin C (2016) (eds) Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining; 2016
Oral M, Oral EL, Aydın A (2012) Supervised vs. unsupervised learning for construction crew productivity prediction. Autom Constr 22:271–276
ISO. Fire resistance tests-elements of building construction. ISO 8341975
Mohd Ali A, Sanjayan J, Guerrieri M (2018) Specimens size, aggregate size, and aggregate type effect on spalling of concrete in fire. Fire Mater 42(1):59–68
Hager I, Mróz K, Tracz T (eds) Concrete propensity to fire spalling: testing and observations. MATEC web of conferences; 2018: EDP sciences
Phan LT, Lawson JR, Davis FL (2001) Effects of elevated temperature exposure on heating characteristics, spalling, and residual properties of high performance concrete. Mater Struct 34(2):83–91
Boström L, Wickström U, Adl-Zarrabi B (2007) Effect of specimen size and loading conditions on spalling of concrete. Fire Mater 31(3):173–186
Klingsch EW (2014) Explosive spalling of concrete in fire. IBK Bericht, p 356
Bosnjak J (2014) Explosive spalling and permeability of high performance concrete under fire: numerical and experimental investigations [Doctor Thesis]: Universität Stuttgart
Li M, Qian C, Sun W (2004) Mechanical properties of high-strength concrete after fire. Cem Concr Res 34(6):1001–1005
Zhao R, Sanjayan JG (2011) Geopolymer and Portland cement concretes in simulated fire. Mag Concrete Res 63(3):163–173
Akca AH, Zihnioğlu NÖ (2013) High performance concrete under elevated temperatures. Constr Build Mater 44:317–328
Zhang B (2011) Effects of moisture evaporation (weight loss) on fracture properties of high performance concrete subjected to high temperatures. Fire Saf J 46(8):543–549
Pan Z, Sanjayan JG, Kong DL (2012) Effect of aggregate size on spalling of geopolymer and Portland cement concretes subjected to elevated temperatures. Constr Build Mater 36:365–372
Arioz O (2007) Effects of elevated temperatures on properties of concrete. Fire Saf J 42(8):516–522
Sideris K, Manita P, Chaniotakis E (2009) Performance of thermally damaged fibre reinforced concretes. Constr Build Mater 23(3):1232–1239
Yermak N, Pliya P, Beaucour A-L, Simon A, Noumowé A (2017) Influence of steel and/or polypropylene fibres on the behaviour of concrete at high temperature: spalling, transfer and mechanical properties. Constr Build Mater 132:240–250
Chen B, Liu J (2004) Residual strength of hybrid-fiber-reinforced high-strength concrete after exposure to high temperatures. Cem Concr Res 34(6):1065–1069
Sideris KK (2007) Mechanical characteristics of self-consolidating concretes exposed to elevated temperatures. J Mater Civil Eng 19(8):648–654
Liu J-C, Tan KH (2018) Mechanism of PVA fibers in mitigating explosive spalling of engineered cementitious composite at elevated temperature. Cem Concr Compos 93:235–245
Bhat PS, Chang V, Li M (2014) Effect of elevated temperature on strain-hardening engineered cementitious composites. Constr Build Mater 69:370–380
Rashad AM (2015) An exploratory study on high-volume fly ash concrete incorporating silica fume subjected to thermal loads. J Clean Prod 87:735–744
Jang H-S, So H-S, So S (2016) The properties of reactive powder concrete using PP fiber and pozzolanic materials at elevated temperature. J Build Eng 8:225–230
Tai Y-S, Pan H-H, Kung Y-N (2011) Mechanical properties of steel fiber reinforced reactive powder concrete following exposure to high temperature reaching 800 C. Nucl Eng Des 241(7):2416–2424
Mugume RB, Horiguchi T (2014) Prediction of spalling in fibre-reinforced high strength concrete at elevated temperatures. Mater Struct 47(4):591–604
Ruano G, Isla F, Luccioni B, Zerbino R, Giaccio G (2018) Steel fibers pull-out after exposure to high temperatures and its contribution to the residual mechanical behavior of high strength concrete. Constr Build Mater 163:571–585
Shaikh F, Taweel M (2015) Compressive strength and failure behaviour of fibre reinforced concrete at elevated temperatures. Adv Concr Constr 3(4):283–293
Zhu Y, Thorne T, Lange D, Maluk C (2019) Experimental study on fire-induced concrete spalling: influences of micro PP fibres, concrete moisture content and heating conditions. In: 6th international conference on applications of structural fire engineering; Singapore
Van Rossum G, Drake FL (2009) Python 3 reference manual. Scotts Valley, CreateSpace
Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv:14126980
Normalisation Ced (2004) EN 1992-1-2: Eurocode 2: design of concrete structures—part 1–2: general rules-structural fire design. Brussels, Belgium
Majorana C, Salomoni V, Mazzucco G, Khoury G (2010) An approach for modelling concrete spalling in finite strains. Math Comput Simul 80(8):1694–1712
Hertz KD (2003) Limits of spalling of fire-exposed concrete. Fire Saf J 38(2):103–116
Behnam B (2016) On the effect of travelling fire on the stability of seismic-damaged large reinforced concrete structures. Int J Civ Eng 14(8):535–545
Connolly RJ (1998) The spalling of concrete in fires [PHD thesis]: Aston University
Liu J-C, Tan KH, Yao Y (2018) A new perspective on nature of fire-induced spalling in concrete. Constr Build Mater 184:581–590
Acknowledgements
The work is funded by the Innovation and Technology Support Programme of Innovation and Technology Fund of Hong Kong (Grant no: ITS/412/18). Any opinions, findings, conclusions or recommendations expressed in this material/event (or by members of the project team) do not reflect the views of the Government of the Hong Kong Special Administrative Region, the Innovation and Technology Commission or the Panel of Assessors for the Innovation and Technology Support Programme of the Innovation and Technology Fund.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
On behalf of all authors, the corresponding author states that there is no conflict of interest.
Rights and permissions
About this article
Cite this article
Liu, JC., Huang, L., Chen, Z. et al. A comparative study of artificial intelligent methods for explosive spalling diagnosis of hybrid fiber-reinforced ultra-high-performance concrete. Int J Civ Eng 20, 639–660 (2022). https://doi.org/10.1007/s40999-021-00689-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40999-021-00689-7