A machine learning approach to predict explosive spalling of heated concrete

Abstract

Explosive spalling is an unfavorable phenomenon observed in concrete when exposed to heating load. It is a great potential threat to safety of concrete structures subjected to accidental thermal loads. Therefore, assessing explosive spalling risk of concrete is important for fire safety design of concrete structures. This paper proposed a popular machine learning approach, i.e., artificial neural network (ANN), to assess explosive spalling risk of concrete. Besides, the decision tree method was also used to execute the same mission for a comparison purpose. Twenty-eight groups of heating tests were conducted to validate the proposed ANN model. The ANN model behaved well in assessing explosive spalling of concrete, with a prediction accuracy of 82.1%. This study shows that ANN is a promising method for adequate classification of concrete as material resistant or not resistant to thermal explosive spalling.

Fire spalling behavior of high-strength concrete: A critical review

“…Since then, many authors, including Zhang et al [12], Yoon [13], and Sanjayan et al [6], recognized the extremely high risk of heated-induced spalling in dense concrete. Recently, new evidence, such as that reported by Liu [14], has confirmed this further. One of the most well-known examples of concrete spalling in real fires is the fire that broke out in the tunnel that connects Britain and France (named Great Belt Fixed Link) [15] and the one that erupted in the Danish tunnel beneath the Great Belt [16], which caused severe damage due to spalling of dense concretes.…”

Discovering Graphical Heuristics on Fire-Induced Spalling of Concrete Through Explainable Artificial Intelligence

“…A database containing 293 laboratory samples was collected from the open literature [ 32 – 34 , 44 – 65 ]. This 293 data point sample contains 11 independent variables and one dependent variable (output; classified as spalling/no spalling).…”

“…The authors would like the acknowledge the following works of Dr. Liu’s and Dr. Ye’s [ 32 – 34 , 89 , 90 ] group, who managed to compile and share the database used herein. We encourage our readers to visit such works.…”

“…For instance, Uysal and Tanyildizi [ 28 ] and McKinney and Ali [ 29 ] are perhaps some of the earliest works that tackled the spalling problem through AI. More recently, the use of modern algorithms and techniques has also been tried by our research group [ 5 , 12 , 29 – 31 ] and colleagues [ 32 – 34 ]. In hindsight, these recent studies examine the vulnerability of concrete elements or concrete mixes to spalling via investigating the influence of elemental features (such as geometrical, materials, and loading properties of load bearing members) or concrete mixtures (e.g., proportions of aggregates, sand, binders, etc.).…”

Artificial Neural Network with a Cross-Validation Technique to Predict the Material Design of Eco-Friendly Engineered Geopolymer Composites

“…In civil engineering research, ANN has been successfully applied to anticipate the strength criteria of hardened concrete [ 19 ] and the workability properties of fresh concrete [ 20 ]. In addition to these studies, several important and advanced parametric studies, such as those estimating the bond strength of structural concrete [ 21 , 22 ], the spalling [ 23 ] damage assessment of concrete [ 24 , 25 ], analyzing sections of deep beams [ 26 ], estimating the fracture parameters of geopolymer composites [ 27 ], and accessing the properties of FRP columns [ 28 ] have been successfully conducted. Additionally, durability studies on various factors such as corrosion inhibition [ 29 ], chloride penetration [ 30 , 31 ] and other aspects have also been successfully undertaken.…”