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

Abstract

Fire-induced spalling of concrete continues to be an intriguing and intricate research problem. A deep dive into the open literature highlights the alarming discrepancy and inconsistency of existing theories, as well as the complexity of predicting spalling. This brings new challenges to creating fire-safe concretes and primes an opportunity to explore modern methods of investigation to tackle the spalling phenomenon. Thus, this paper leverages the latest advancements in explainable Artificial Intelligence (XAI) to vet existing theories on fire-induced spalling and to discover solutions/heuristics to predict spalling of concrete mixtures. The developed heuristics are in the form of graphs and nomograms . The proposed solutions allow interested researchers and engineers to graphically identify the propensity of a given concrete mixture to spalling directly and with ease. For example, we report that concrete mixtures with a combination of moderate water/binder ratio (of about 0.3), low heating rate (less than 2.5°C/min), moderate rise in temperature (less than 500°C), and have moisture content (less than 3%) are expected to be less prone to spalling. Further, findings from this research showcase the potential for developing simple (i.e., one-shot) and graphical (coding-free and formula-free) XAI-based solutions and web applications to address decades-long problems in the area of concrete research.

Simple Visual Aids for Predicting Fire Response of RC Columns: Nomograms via Machine Learning

“…Engineers, practitioners, and medical professionals historically used Nomograms, also known as alignment charts, to solve mathematical equations or to depict complex interactions within phenomena [46,47]. Typically, a Nomogram has one output variable and several input variables and can vary between simple parallel line scales or more intricate parabolic shapes.…”